system

Abstract

Provide a system. The method includes: a means for collecting data from various data sources; A means of converting the collected data into a unified format; a means for storing the data converted into the unified format in a database; A means of consolidating data in the database and removing duplicate data; a means for generating a sales forecast using a machine learning algorithm; A means to automatically generate reports based on specified templates; A means to accumulate customer characteristic information and automatically provide it to new staff members, A system including:

Description

[Technical Field]

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

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

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

[0004] In modern business management, collecting information from multiple data sources and integrating, analyzing, and reporting this information is extremely time-consuming. Furthermore, transferring information when personnel change is also time-consuming, hindering efficient business execution. Against this backdrop, the following main challenges exist:

[0005] 1. The time and effort required to collect and synthesize data.

[0006] 2. The hassle of detecting and correcting incomplete or inaccurate data.

[0007] 3. Accuracy of sales forecasts and data analysis for that purpose.

[0008] 4. Effective reporting.

[0009] 5. The hassle of transferring customer information. [Means for solving the problem]

[0010] The present invention provides a system that collects data from various data sources, converts it into a unified format, and stores it in a database. It also has the functionality to consolidate data in the database, remove duplicate data, and generate sales forecasts using machine learning algorithms. It also automates report creation based on specified templates, accumulates customer characteristics, and automatically provides information to new sales representatives. Specifically, it has the following means:

[0011] 1. A means of collecting data periodically from various data sources.

[0012] 2. A means of converting collected data into a uniform format.

[0013] 3. A means of storing the conversion data in a database.

[0014] 4. A means of consolidating data within a database and detecting and removing duplicate data.

[0015] 5. A means of correcting incomplete or inaccurate data through data cleaning.

[0016] 6. A means of forecasting sales using machine learning algorithms.

[0017] 7. A means of periodically training models based on historical data.

[0018] 8. A means to automatically generate and distribute reports to stakeholders.

[0019] 9. A means of continually accumulating customer information and assisting in the handover to new personnel.

[0020] A "data source" refers to a system, database, mail server, etc. from which information is collected.

[0021] "Unified format" refers to standards and rules for converting data obtained from different data sources into the same format and structure.

[0022] A "database" refers to a collection of information that is organized and stored so that collected data can be searched and retrieved later.

[0023] A "machine learning algorithm" refers to a program or method that learns patterns from data and makes predictions or classifications based on those patterns.

[0024] "Sales forecasting" refers to the process of predicting future sales based on past data and current conditions.

[0025] "Report" means a written or digital document that organizes and presents specific data or information in a format.

[0026] "Duplicate data" refers to a situation in which data with the same content exists multiple times.

[0027] "Data cleaning" refers to the process of detecting and correcting or removing incomplete, inaccurate, or irrelevant data.

[0028] "Customer characteristic information" refers to information such as attributes, history, and business status related to a specific customer.

[0029] "New person in charge" refers to a person who takes over from the previous person in charge and takes on new duties. [Brief explanation of the drawings]

[0030] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0031] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0032] First, the terms used in the following description will be explained.

[0033] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0034] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0035] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0036] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0037] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0038] [First embodiment]

[0039] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0040] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0041] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0042] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0043] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0044] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0045] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0046] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0047] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0048] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0049] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0050] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0051] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. A specific embodiment of the system will be described below.

[0052] Data collection and conversion into a unified format

[0053] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[0054] Data storage and integration

[0055] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[0056] Generate sales forecasts

[0057] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[0058] Automated reporting

[0059] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[0060] Accumulation and utilization of customer information

[0061] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[0062] Specific examples

[0063] Example 1: Importing and merging order data

[0064] The user registers new order data in the order management system.

[0065] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0066] The server compares the data with existing data and merges any duplicate order data.

[0067] Example 2: Generating and viewing a sales forecast

[0068] A user logs in to the dashboard and reviews the forecast for next month.

[0069] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0070] The server displays the generated sales forecast in a graphical format on a dashboard.

[0071] Example 3: Automatic report generation and distribution

[0072] The server automatically generates a sales report for the previous month on the 1st of each month.

[0073] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0074] The user views the received report and makes minor corrections as necessary.

[0075] Example 4: Transferring customer information

[0076] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0077] The server displays important information on a dashboard when a new person logs into the system.

[0078] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0079] The system of the present invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving business efficiency.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] The server connects to various data sources (email server, project management system, ERP system, etc.) at the specified time to collect new data. For example, it retrieves emails from business partners from the mail server and retrieves new project data from the project management system.

[0083] Step 2:

[0084] The server converts the collected data into a unified format, for example, converting date formats obtained from different data sources into a unified format (e.g., YYYY-MM-DD).

[0085] Step 3:

[0086] The server saves the data converted into the unified format in the database, while checking the consistency and integrity of the data.

[0087] Step 4:

[0088] The server consolidates data in the database and detects and removes duplicates, for example, merging the same order information from multiple data sources into a single record.

[0089] Step 5:

[0090] The server runs a data cleaning process to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs from other information.

[0091] Step 6:

[0092] The server uses machine learning algorithms to train a sales forecasting model based on past data, and the model is periodically updated to improve forecast accuracy.

[0093] Step 7:

[0094] The server applies the sales forecasting model to the new data as input to predict future sales, for example, calculating the sales forecast for the next month and saving it in a database.

[0095] Step 8:

[0096] The server automatically generates reports based on predefined report templates, such as a monthly report containing sales forecasts, actual results, inventory status, and order status.

[0097] Step 9:

[0098] The server automatically emails the generated report to the designated parties, with the report attached as a document file in PDF format or other format.

[0099] Step 10:

[0100] The server stores customer characteristics information and automatically provides it to new staff members. For example, when a new staff member logs in to the system after a change of staff member, relevant customer information is displayed on the dashboard.

[0101] Step 11:

[0102] Users can log in to the dashboard to check next month's sales forecast and the latest customer information, eliminating the need for additional inquiries or research and allowing them to get started quickly.

[0103] Example 1

[0104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] With conventional data collection systems, it was difficult to efficiently collect and integrate data from various data sources. As a result, manual deduplication and correction of inaccurate data were required, reducing operational efficiency. Furthermore, operating machine learning algorithms for sales forecasting and report generation was time-consuming, and there was an issue of not being able to provide the latest forecast data or integrated information in real time. Furthermore, when personnel were changed, there was insufficient information handover to allow new personnel to quickly start work.

[0106] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0107] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and removing duplicate data, means for detecting and correcting incomplete or inaccurate data, means for generating sales forecasts using a machine learning algorithm, means for periodically training a model using past data, means for automatically generating reports based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new sales representative, means for displaying information in real time on a dashboard based on the collected data, and means for collecting email correspondence with business partners and storing it in a database. This allows for efficient collection and integration while maintaining data consistency, automatic generation of sales forecasts and reports, and smooth information transfer when sales representatives are changed.

[0108] "Various data sources" refers to different data providers such as mail servers, project management systems, order management systems, inventory management systems, and quotation management systems.

[0109] "Means of collecting data" refers to the methods and technologies that the server uses to connect to various data sources and obtain the required information.

[0110] A "unified format" refers to data obtained from different data sources converted into a common format or structure.

[0111] "Means of converting data into a unified format" refers to the methods and techniques used to convert collected data into a consistent format.

[0112] "Means of storing in a database" refers to the methods and techniques used to store the converted data in an organized manner and make it easily accessible.

[0113] "Means for integrating data and removing duplicate data" refers to methods and technologies for integrating data obtained from multiple data sources and deleting duplicate data when it exists multiple times, thereby consolidating it into one.

[0114] "Means for detecting and correcting incomplete or inaccurate data" refers to methods and techniques for detecting missing values ​​or erroneous information in data and correcting them to make them accurate.

[0115] A "machine learning algorithm" refers to an algorithm that trains a model based on past data and predicts future sales, etc.

[0116] "Means for generating sales forecasts" means methods or techniques for forecasting future sales using machine learning algorithms.

[0117] "Model training methods" refers to methods and techniques for using historical data to improve the performance of machine learning algorithms.

[0118] "Means for automated report generation" means methods or technologies for automatically generating periodic reports based on sales forecasts or consolidated data.

[0119] "Customer characteristic information" refers to important information related to commercial transactions, such as transaction history, response history, and business status.

[0120] "Means for automatically providing to a new person in charge" refers to a method or technology for automatically providing the necessary customer information to a new person in charge when the person in charge is changed.

[0121] "Means for displaying information on a dashboard in real time" refers to methods and technologies for instantly displaying collected data and forecast results on a user interface.

[0122] "Means of collecting email correspondence with business partners and storing it in a database" refers to methods and technologies for obtaining communication content with business partners from a mail server and storing it in a database.

[0123] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report generation, and customer information handover. Specific embodiments of the system are described below.

[0124] Data collection and conversion into a unified format

[0125] The server periodically connects to various data sources (e.g., mail server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. A Python script is used to collect the data, and its periodic execution is managed by a Cron job. After collection, the server uses libraries such as Pandas and NumPy to convert the data obtained from each data source into a unified format.

[0126] Data storage

[0127] The server saves the converted data in a database such as PostgreSQL or MySQL (registered trademark). At this time, it connects to the database using SQLAlchemy and inserts the data into a table. During the data saving process, it performs transaction management and performs a rollback process if an error occurs.

[0128] Data integration and cleaning

[0129] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and merge identical order information into a single record. It also detects incomplete or inaccurate data and corrects it by applying appropriate defaults or imputed data using OpenRefine and Pandas.

[0130] Generate sales forecasts

[0131] The server runs machine learning algorithms using Scikit-learn and TENSORFLOW (registered trademark) to generate sales forecasts for the next month. Past sales data, current inventory data, and the latest order information are used to train the model. Hyperopt and GridSearchCV are also used to improve the accuracy of the forecast model.

[0132] Automated reporting

[0133] The server automatically generates daily, weekly, and monthly reports in Excel and PDF formats based on predefined report templates using openpyxl and xlsxwriter for Excel generation and ReportLab for PDF generation, and sends the generated reports via email to designated parties using an SMTP server.

[0134] Accumulation and utilization of customer information

[0135] The server continuously accumulates and centrally manages customer-specific information. This includes, for example, transaction history, response history, and business status. When a customer changes contact person, the server displays relevant information in real time on the dashboard when the new contact person logs in to the system, supporting a smooth transition. The dashboard was developed using Django and Flask on the backend and React and Vue.js on the frontend.

[0136] Specific examples

[0137] Example 1: Importing and merging order data

[0138] The user registers new order data in the order management system.

[0139] The server periodically collects new order data from the order management system, converts it into a unified format using Pandas, and stores it in the database.

[0140] The server compares the data with existing data and merges any duplicate order data.

[0141] Example 2: Generating and viewing a sales forecast

[0142] A user logs in to the dashboard and reviews the forecast for next month.

[0143] The server uses Scikit-learn to run a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0144] The server displays the generated sales forecast in a graphical format on a dashboard.

[0145] Example 3: Automatic report generation and distribution

[0146] The server automatically generates the previous month's sales report using openpyxl on the 1st of each month.

[0147] The server formats the report content based on a pre-configured template and sends it to the relevant parties via email using an SMTP server.

[0148] The user views the received report and makes minor corrections as necessary.

[0149] Example 4: Transferring customer information

[0150] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0151] When a new person logs into the system, the server displays important information on a dashboard using React.

[0152] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0153] Prompt Sentence Examples

[0154] Below are some example prompts to be input to the generative AI model:

[0155] This system implements programs that automate data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. For example, new data is collected from an order management system, converted into a unified format, and stored in a database. Sales forecasts are then generated and can be viewed on a dashboard. This system uses software such as Scikit-learn, Pandas, Django, and React. Could you please tell me the detailed process flow?

[0156]

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1: Data collection

[0159] The server periodically connects to various data sources to collect new data. For example, it uses Python scripts and Cron jobs to collect emails from clients from the mail server and retrieves new case information from the case management system. In this process, it retrieves email data using the IMAP protocol and case data via the REST API.

[0160] The input is new data from various data sources and the output is the raw data captured on the server.

[0161] Specific behavior:

[0162] The server periodically connects to the mail server to retrieve new mail.

[0163] The server sends an HTTP request to the project management system's API to retrieve new project data.

[0164] Step 2: Convert the data format

[0165] The server converts the collected data into a unified format, using the Python Pandas library to convert CSV and JSON-formatted data into a DataFrame with consistent column names and data types.

[0166] The input is raw data and the output is data converted into a unified format.

[0167] Specific behavior:

[0168] The email data obtained by the server is read into a Pandas DataFrame and the column names are unified.

[0169] The server converts the job data from JSON format to a DataFrame and extracts the necessary information.

[0170] Step 3: Save your data

[0171] The server saves the converted data in a database (PostgreSQL or MySQL). It connects to the database using SQLAlchemy and inserts the data into a table. Transaction management allows for rollback if an error occurs.

[0172] The input is data converted into a unified format, and the output is data stored in a database.

[0173] Specific behavior:

[0174] The server uses the SQLAlchemy engine to connect to the database and saves the data according to the table structure.

[0175] The server begins a transaction and commits it if successful, or rolls it back if an error occurs.

[0176] Step 4: Integrate and clean the data

[0177] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and fix problematic data.

[0178] The input is the data stored in the database, and the output is the cleaned and consolidated data.

[0179] Specific behavior:

[0180] The server retrieves data from the database and uses Pandas to detect duplicate records.

[0181] The server detects incomplete data and fills in appropriate defaults.

[0182] Step 5: Generate a sales forecast

[0183] The server generates sales forecasts using machine learning algorithms, such as Scikit-learn and TensorFlow, to generate a predictive model based on past sales data, current inventory data, and the latest order information.

[0184] The input is the cleaned integrated data and the output is the predicted sales data.

[0185] Specific behavior:

[0186] The server generates features based on past sales data and current data.

[0187] The server trains the machine learning model and generates sales forecasts.

[0188] Step 6: Reporting

[0189] The server automatically generates reports containing sales forecast results and other business insights. Openpyxl and ReportLab are used to create reports in Excel and PDF formats.

[0190] The inputs are the forecasted sales data and the consolidated data, and the output is the generated report.

[0191] Specific behavior:

[0192] The server generates the sales forecast results as an Excel file and inserts the necessary graphs and tables.

[0193] The server creates a report in PDF format and formats the content according to the specified format.

[0194] Step 7: Distributing the report

[0195] The server sends the generated report to the designated parties via email using an SMTP server.

[0196] The input is the report generated and the output is the report sent to the interested party.

[0197] Specific behavior:

[0198] The server connects to the SMTP server and creates a message containing the email body and any attachments.

[0199] The server sends the email and records the sending log.

[0200] Step 8: Accumulating and utilizing customer information

[0201] The server stores customer characteristics information and automatically provides it to new staff members. When a user logs in to the system, relevant information is displayed in real time on a dashboard.

[0202] The input is customer information and login information, and the output is the information displayed on the dashboard.

[0203] Specific behavior:

[0204] The server extracts customer information from a database and filters the information relevant to the logged-in user.

[0205] The server uses React to display information on a dashboard in real time.

[0206] (Application example 1)

[0207] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0208] In today's business environment, automating data collection, management, analysis, and report generation is a key challenge. Especially in fields that handle large volumes of data, such as online shopping sites, there is a need to check data consistency, forecast sales, generate reports, and consolidate customer information. However, performing these processes manually is extremely time-consuming and inefficient. Furthermore, when duplicate data or inaccuracies occur, the process of detecting and correcting them is complex. Furthermore, the lack of a way to check sales forecasts and report generation in real time makes it difficult to make quick decisions. Therefore, to solve these challenges, a system that automatically collects, consolidates, analyzes, forecasts, and generates reports is needed.

[0209] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0210] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new person in charge, means for displaying the sales forecast in real time via a dashboard on a smartphone or tablet, and means for sending the report by email to relevant parties. This enables automatic collection, integration, analysis, prediction, and report generation of data.

[0211] "Various data sources" refers to different data sources such as a mail server, a case management system, an order management system, an inventory management system, and an estimate management system.

[0212] "Means of collecting data" refers to the function for periodically obtaining new data from various data sources.

[0213] "Means for converting into a unified format" refers to the ability to convert data of different formats or structures into a consistent format.

[0214] "Means for saving in a database" means a function for saving the converted data in a database for centralized management.

[0215] "Means for integrating data and removing duplicate data" means a function that combines identical data obtained from multiple data sources into a single record and eliminates duplication.

[0216] "Machine learning algorithm" refers to a computational model for making sales forecasts based on data.

[0217] "Means for generating sales forecasts" refers to the function of predicting sales based on past sales data, current order information, inventory data, etc.

[0218] "Means for automatically generating a report based on a specified template" means a function for automatically generating a report in accordance with a pre-set format.

[0219] "A means of accumulating customer-specific information and automatically providing it to new staff" refers to a function that continuously manages transaction history, response history, business status, etc., and makes it easy for new staff to access.

[0220] "A means of displaying sales forecasts in real time through a dashboard on a smartphone or tablet" means the ability to view sales forecasts through a dashboard on a mobile device.

[0221] "Means for sending reports to relevant parties by email" refers to a function that automatically sends generated reports to designated recipients by email.

[0222] The system for carrying out the present invention can efficiently collect data, automatically forecast sales, generate reports, and manage customer information on an online shopping site. A specific embodiment of the system will be described below.

[0223] Data collection and conversion into a unified format

[0224] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[0225] Data storage and integration

[0226] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[0227] Generate sales forecasts

[0228] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information. To do this, it uses Python and the Scikit-learn library. The server also periodically trains the model to improve the accuracy of its predictions.

[0229] Automated reporting

[0230] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual sales, inventory status, and order status. The generated reports are then emailed to designated parties. For this purpose, the Smtplib library is used.

[0231] Accumulation and utilization of customer information

[0232] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new customer when the customer is replaced, and is displayed on the dashboard to support a smooth transition.

[0233] View sales forecasts on the dashboard and send reports

[0234] The application installed on a smartphone or tablet displays sales forecasts from the server in real time when the user logs in to the dashboard. The generated reports are automatically sent to the relevant parties via email. For example, the application displays the sales forecast for the next month and sends a monthly report via email.

[0235] Specific examples

[0236] For example, a user may log in to a dashboard on a smartphone app to check the sales forecast for the next month. The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate the sales forecast for the next month and displays it in graph form. The server also automatically generates a sales report for the previous month on the first day of each month, formats it based on a specified template, and sends it to relevant parties by email.

[0237] Prompt Sentence Examples

[0238] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[0239] This system enables automatic data collection, integration, analysis, prediction, and report generation, dramatically improving operational efficiency.

[0240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0241] Step 1:

[0242] The server periodically connects to various data sources (e.g., mail server, case management system, order management system, inventory management system, quotation management system, etc.) to collect new data. In this case, the server retrieves data obtained from each system (e.g., new order information from the order management system and email correspondence with business partners from the mail server), even if the data is in different formats and forms. The input is the raw data collected from different data sources, and the output is all the raw data collected.

[0243] Step 2:

[0244] The server converts the data collected from each data source into a unified format. During this process, the server converts data of different formats into a consistent format to maintain data integrity. For example, it converts data in XML format into JSON format and aligns the structure. This conversion process allows data from different data sources to be treated as consistent data. The input is raw data collected from various data sources, and the output is data converted into a unified format.

[0245] Step 3:

[0246] The server saves the data converted into a unified format in a database. In this step, the organized data is saved in a centrally managed database, allowing for efficient data access in subsequent processing. The input is the data converted into a unified format, and the output is the data saved in the database.

[0247] Step 4:

[0248] The server consolidates data in the database and removes duplicates. This process involves merging identical order information from multiple data sources into a single record. It also performs data cleaning processes to detect and correct incomplete or inaccurate data. For example, it detects and completes data with incomplete address information. The input is the data stored in the database, and the output is the consolidated data after duplicates have been removed.

[0249] Step 5:

[0250] The server runs a machine learning algorithm based on past data and current conditions to generate sales forecasts. This algorithm is implemented using Python and the Scikit-learn library, and calculates next month's sales forecasts using sales data from the past few years, current inventory status, and the latest order information. In addition, the server periodically performs model training to improve the accuracy of the forecasts. The inputs are past sales data, inventory information, and order information, and the output is next month's sales forecast data.

[0251] Step 6:

[0252] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The reports are sent by email to designated parties. This is implemented using the Smtplib library. The input is the sales forecast data and a report template, and the output is the generated report.

[0253] Step 7:

[0254] The server continuously accumulates and centrally manages customer characteristic information. This information includes, for example, transaction history, response history, and business status. When a person in charge is changed, this information is automatically provided to the new person in charge and displayed on a dashboard to support a smooth handover. The input is customer characteristic information, and the output is centrally managed customer information.

[0255] Step 8:

[0256] Users can log in to the application dashboard using a smartphone or tablet and check sales forecasts in real time from the server. The generated reports are automatically sent to relevant parties by email. The input is the user's login information and sales forecast data obtained from the server, and the output is sales forecast data displayed in real time.

[0257] Prompt Sentence Examples

[0258] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[0259] In this way, automated data collection, integration, analysis, prediction, and report generation are facilitated, improving operational efficiency.

[0260] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0261] The system of the present invention aims to significantly improve business efficiency by automating data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover, and by combining it with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[0262] Data collection and conversion into a unified format

[0263] The server periodically connects to various data sources (email server, case management system, ERP system, etc.) to collect new data. For example, it retrieves client emails from the mail server and retrieves new case data from the case management system. After collecting the data, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[0264] Data storage and integration

[0265] The server saves the unified data to the database, checking for consistency and integrity before inserting it. After saving, the server consolidates the data in the database and detects and removes duplicate data. For example, if the same order information comes from multiple data sources, it will be merged into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[0266] Generate sales forecasts

[0267] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[0268] Automated reporting

[0269] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[0270] Accumulation and utilization of customer information

[0271] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[0272] Introducing the Emotion Engine

[0273] The server uses an emotion engine to recognize the user's emotions and adjust the system's behavior accordingly. For example, if the user is feeling stressed, the server will change the content and color of the report to provide a more relaxing environment. It will also customize the report content based on the user's emotions to provide more accurate information.

[0274] Specific examples

[0275] Example 1: Importing and merging order data

[0276] The user registers new order data in the order management system.

[0277] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0278] The server compares the data with existing data and merges any duplicate order data.

[0279] Example 2: Generating and viewing a sales forecast

[0280] A user logs in to the dashboard and reviews the forecast for next month.

[0281] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0282] The server displays the generated sales forecast in a graphical format on a dashboard.

[0283] Example 3: Automatic report generation and distribution

[0284] The server automatically generates a sales report for the previous month on the 1st of each month.

[0285] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0286] The user views the received report and makes minor corrections as necessary.

[0287] Example 4: Transferring customer information

[0288] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0289] The server displays important information on a dashboard when a new person logs into the system.

[0290] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0291] Example 5: Using the Emotion Engine

[0292] A user logs into the system and the emotion engine analyzes the user's emotional state.

[0293] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[0294] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[0295] The system of this invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving work efficiency. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotional state, providing a more effective work environment.

[0296] The processing flow will be explained below.

[0297] Step 1:

[0298] The server connects to various data sources (e.g., email servers, case management systems, ERP systems, etc.) to collect new data. This process is scheduled periodically, for example, every day at 3:00 AM, and executes API calls and database queries to each data source to extract new data.

[0299] Step 2:

[0300] The server converts the collected data into a unified format, for example, converting date formats (such as YYYY / MM / DD or MM-DD-YYYY) obtained from different data sources into a unified format (e.g., YYYY-MM-DD), ensuring consistency in subsequent processing.

[0301] Step 3:

[0302] The server saves the data converted into a unified format into the database, while checking the consistency and integrity of the data during insertion. For example, it checks for duplicate records, and if any are found, it updates the existing data or ignores them.

[0303] Step 4:

[0304] The server consolidates data in the database, detects and removes duplicates (for example, if the same order information comes from multiple data sources, it consolidates them into a single record), and performs checks to ensure data consistency.

[0305] Step 5:

[0306] The server runs data cleaning processes to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs or incomplete address information with other information to improve consistency.

[0307] Step 6:

[0308] The server uses a machine learning algorithm to train a sales forecasting model based on past data. This model is periodically updated to improve forecast accuracy. For example, at the beginning of each month, the model is retrained using sales data from the past year.

[0309] Step 7:

[0310] The server applies the sales forecasting model to new data as input to predict future sales. For example, it calculates the sales forecast for the next month and saves the results in a database, allowing access to the latest forecast data.

[0311] Step 8:

[0312] The server automatically generates reports based on predefined report templates. For example, a monthly report might include sales forecasts, actual results, inventory status, and order status. The generated reports are saved in formats such as PDF.

[0313] Step 9:

[0314] The server automatically emails the generated report to designated parties based on a pre-defined schedule, with the report being sent at the specified time.

[0315] Step 10:

[0316] The server stores customer characteristics and automatically provides them to new staff members. For example, when a staff member logs in to the system, relevant customer information is displayed on the dashboard. This information includes transaction history and correspondence history.

[0317] Step 11:

[0318] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the user's input patterns and voice data to recognize emotions. Based on the analysis results, it determines the user's emotional state.

[0319] Step 12:

[0320] The server adjusts the system's behavior based on the analyzed emotional data. For example, if the user is feeling stressed, the content and color of the dashboard display will be changed to provide a more relaxing environment. This content adjustment is done in real time.

[0321] Step 13:

[0322] The server customizes the report content based on the user's emotions. For example, if the user is feeling stressed, the server will highlight important information in the report to make it easier to understand. It also omits unnecessary information to reduce the user's burden.

[0323] Step 14:

[0324] Before the login session ends, the server re-analyzes the user's emotional data to see if there has been any improvement. The server records the analysis of the user's emotional state and uses it as reference information for the next login. This information is also used for subsequent analyses.

[0325] Specific examples

[0326] Example 1: Importing and merging order data

[0327] The user registers new order data in the order management system.

[0328] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0329] The server compares the data with existing data and merges any duplicate order data.

[0330] Example 2: Generating and viewing a sales forecast

[0331] A user logs in to the dashboard and reviews the forecast for next month.

[0332] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0333] The server displays the generated sales forecast in a graphical format on a dashboard.

[0334] Example 3: Automatic report generation and distribution

[0335] The server automatically generates a sales report for the previous month on the 1st of each month.

[0336] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0337] The user views the received report and makes minor corrections as necessary.

[0338] Example 4: Transferring customer information

[0339] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0340] The server displays important information on a dashboard when a new person logs into the system.

[0341] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0342] Example 5: Using the Emotion Engine

[0343] A user logs into the system and the emotion engine analyzes the user's emotional state.

[0344] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[0345] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[0346] Example 2

[0347] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0348] Collecting, managing, and analyzing large amounts of data in business is generally done manually, requiring a great deal of effort and time. Furthermore, there is a demand for improved data consistency and accuracy, more accurate sales forecasts, automated report creation, and flexible responses based on emotional states. However, achieving all of these simultaneously has been difficult with conventional technology. This has led to issues such as a lack of improved business efficiency and the immediacy of information transmission.

[0349] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report according to a specified template based on the sales forecast, order status, etc., means for accumulating customer characteristic information and automatically providing it to a new sales representative, and means for analyzing user emotions using an emotion engine and adjusting system operation. This enables improved data consistency and accuracy, improved sales forecast accuracy, automated report creation, and flexible response based on emotional states.

[0350] A "data source" is a system or device that provides information, such as an email server, a case management system, or an ERP system.

[0351] A "unified format" is a standardized data format such as CSV or JSON that converts various data formats into a consistent format.

[0352] A "database" is a system for systematically storing and managing collected data.

[0353] "Duplicate data" refers to data that has been obtained from different sources but has identical content and needs to be combined during integration.

[0354] A "machine learning algorithm" is a computer program used to learn patterns from past data and predict future data.

[0355] "Sales forecasting" refers to predicting future sales based on past and current data.

[0356] A "specified template" is a predefined format used when generating a report.

[0357] A "report" is a document that compiles information such as sales forecasts and order status, and is automatically distributed to relevant parties.

[0358] "Customer characteristic information" refers to information about customers such as transaction history, response history, and business situation.

[0359] A "new contact" is an individual newly assigned to work with a particular customer within the system.

[0360] "Emotion engine" refers to technology or software for analyzing a user's emotional state.

[0361] "Analyzing user emotions" refers to the process of determining the user's emotional state from facial expressions, voice, input data, etc.

[0362] "Adjusting system operation" refers to changing the system's display and functions based on the results of emotion analysis to provide an operating environment that meets the user's needs.

[0363] The present invention is a system that collects data from various data sources, converts the data into a unified format, stores it, integrates and analyzes it as needed, and further analyzes user emotions to adjust the system's operation. Specific embodiments of the present invention are described below.

[0364] Data collection and conversion into a unified format

[0365] The server periodically connects to various data sources, such as email servers, case management systems, and ERP systems, to collect new data. For example, the server retrieves client emails from the email server and retrieves new case data from the case management system. The server converts the collected data into a unified format so that it can be processed consistently.

[0366] Data storage and integration

[0367] The server saves the unified data to the database, checking for consistency and integrity. After saving, the server consolidates the data in the database and detects and removes duplicate data. For example, it combines multiple orders from the same customer into a single record. The server also performs data cleaning to detect and correct incomplete or inaccurate data.

[0368] Generate sales forecasts

[0369] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[0370] Automated reporting

[0371] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[0372] Transfer of customer information

[0373] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[0374] Introducing the Emotion Engine

[0375] The server uses an emotion engine to recognize the user's emotions and adjust the system's behavior accordingly. For example, if the user is feeling stressed, the server can change the content and color of the report to provide a more relaxing environment. It can also customize the report content based on the user's emotions to provide more accurate information.

[0376] Specific examples

[0377] Example 1: Importing and merging order data

[0378] The user registers new order data in the order management system.

[0379] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0380] The server compares the data with existing data and merges any duplicate order data.

[0381] Example 2: Generating and viewing a sales forecast

[0382] A user logs in to the dashboard and reviews the forecast for next month.

[0383] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0384] The server displays the generated sales forecast in a graphical format on a dashboard.

[0385] Example 3: Automatic report generation and distribution

[0386] The server automatically generates a sales report for the previous month on the 1st of each month.

[0387] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0388] The user views the received report and makes minor corrections as necessary.

[0389] Example 4: Transferring customer information

[0390] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0391] The server displays important information on a dashboard when a new person logs into the system.

[0392] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0393] Example 5: Using the Emotion Engine

[0394] A user logs into the system and the emotion engine analyzes the user's emotional state.

[0395] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to calmer tones, providing a more relaxing environment.

[0396] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[0397] Prompt Sentence Examples

[0398] "Explain how you can generate a report based on next month's sales forecast and customize the content based on user sentiment."

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

[0400] Step 1: Data collection

[0401] The server connects to various data sources (email server, project management system, ERP system, etc.) in sequence based on a set schedule. Specifically, the server connects to the mail server using the SMTP protocol and retrieves emails from new business partners. The input is new emails from the mail server, and the output is the retrieved raw data.

[0402] Step 2: Analyze and convert data into a unified format

[0403] Analyzes data collected by the server and understands its structure and format. For example, it parses email data collected by the server and extracts important information such as client names and contact names. The input is the acquired raw data, and the output is parsed data in a unified format (JSON, CSV, etc.).

[0404] Step 3: Save your data

[0405] The server stores the data converted into a unified format in the database. During this process, it performs transaction processing to ensure consistency and integrity. Specifically, it inserts data into the database using an SQL query. The input is the unified format data, and the output is a confirmation message indicating success or failure.

[0406] Step 4: Merge duplicates

[0407] The server detects and consolidates duplicate data in the database. For example, if there are multiple orders from the same supplier, the server combines them into one. The server matches and merges the data. The input is all the data in the database, and the output is the consolidated data set.

[0408] Step 5: Cleaning the data

[0409] The server performs a data cleaning process to detect and correct incomplete or inaccurate data, for example by imputing missing values ​​appropriately or correcting malformed data. The input is the full dataset, and the output is the cleaned dataset.

[0410] Step 6: Generate a sales forecast

[0411] The server uses machine learning algorithms to generate sales forecasts based on past data and current conditions. Specifically, it uses libraries such as Scikit-learn to build a predictive model and calculate the forecast. The input is past sales data, order data, and inventory data, and the output is the sales forecast for the next month.

[0412] Step 7: Automatically generate reports

[0413] The server automatically generates reports based on sales forecasts and order status according to predefined templates. Specifically, it uses a template engine such as Jinja2 to generate reports in HTML format. The inputs are sales forecast values ​​and order data, and the output is the generated report (in HTML format).

[0414] Step 8: Distributing the report

[0415] The server converts the generated report into PDF or HTML format and sends it to the designated parties via email. The input is the generated report, and the output is a confirmation message of the sending result.

[0416] Step 9: Transfer of customer information

[0417] The server extracts information about the client to which the new person in charge has been assigned from the database and displays it on the dashboard. Specifically, it updates and displays the information in real time using Ajax. The input is the client information in the database, and the output is the information displayed on the dashboard.

[0418] Step 10: Use the Emotion Engine

[0419] The server uses an emotion engine to analyze the user's emotional state. Based on the analysis results, the dashboard's display content and colors are adjusted. For example, if the user is feeling stressed, the colors are changed to a gentler tone. The input is the user's facial expression data or voice data, and the output is a user interface customized based on the analysis results.

[0420] Step 11: Generate a customized report

[0421] The server customizes the report content according to the user's emotions, generates a report highlighting the necessary information, and distributes it to relevant parties. The input is the analyzed emotion data, sales forecasts, and order data, and the output is the customized report.

[0422] (Application example 2)

[0423] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0424] Conventional data management systems have issues with inefficient data collection and integration from various data sources, making it difficult to guarantee data consistency and accuracy. They also lack automation for sales forecasting and report creation, and have difficulty optimizing the work environment while taking user emotions into account. This reduces overall work efficiency and negatively impacts user productivity and satisfaction. Another issue is the inability to fully optimize specific tasks, inventory management, and production planning in work environments that include factory robots.

[0425] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0426] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating sales forecasts using a machine learning algorithm, means for automatically generating reports based on a specified template, means for accumulating customer characteristic information and automatically providing it to new staff members, an emotion recognition engine for recognizing user emotions, and means for adjusting the work environment based on the results of the emotion recognition engine. This enables automation of data collection and integration, accurate sales forecasts and report generation, and optimization of the work environment based on user emotions.

[0427] "Various data sources" is a general term for systems and devices that provide data in different formats and structures, such as mail servers, case management systems, and ERP systems.

[0428] "Means for converting collected data into a unified format" refers to technology or equipment that converts data of different formats or structures into a consistent format.

[0429] A "database" is a system designed to efficiently store, manage, and search large amounts of data.

[0430] "Data integration" is the process of compiling data collected from multiple data sources into a single, consistent format.

[0431] "Deleting duplicate data" is a process of consolidating and eliminating duplicate information when the same information exists multiple times.

[0432] A "machine learning algorithm" is a technology that allows computers to automatically learn patterns using large amounts of data and make predictions and classifications.

[0433] "Sales forecasting" is a method of predicting future sales based on past sales data, current inventory status, etc.

[0434] "Automatic report generation" is a function that automatically organizes and outputs the necessary information based on a predefined template.

[0435] "Means for accumulating customer characteristic information" refers to technology or equipment that centrally collects and stores information such as transaction history, response history, and business status.

[0436] The "means for automatically providing information to the new person in charge" is a technology or device that automatically presents the customer's characteristic information to the person in charge and supports a smooth handover of work.

[0437] An "emotion recognition engine that recognizes a user's emotions" is a technology or device that analyzes and recognizes emotions from a user's facial expressions and behavior.

[0438] A "means for adjusting the work environment" is a technology or device that changes work instructions and environmental settings based on the user's emotions, providing an optimal work environment.

[0439] The system of the present invention automates data collection, data integration, sales forecasting, report creation, and work environment adjustment based on emotion recognition in a factory environment, significantly improving business efficiency.

[0440] System Configuration

[0441] The system consists of the following main components:

[0442] 1. Data Collection Module

[0443] The server collects data in real time from various data sources within the factory (e.g., sensors, management systems), including mail servers, project management systems, and ERP systems. Programming languages ​​such as Python are used to collect the data, and REST APIs are used as needed.

[0444] 2. Data Conversion Module

[0445] The collected data is converted into a unified format on the server to maintain consistency even when the data has different formats or structures, and this conversion process is often performed using the Pandas library.

[0446] 3. Database Management Module

[0447] The converted data is stored in a database and managed centrally. MongoDB or MySQL is used for the database. During data integration, duplicate data is removed and data cleaning is also performed.

[0448] 4. Sales Forecasting Module

[0449] The server uses TensorFlow to train machine learning models based on historical data and current inventory status to generate sales forecasts, which are updated periodically and displayed in real time on a dashboard.

[0450] 5. Automatic report generation module

[0451] Daily, weekly, and monthly reports are automatically generated based on specified templates. Reports are generated in formats such as PDF and sent to relevant parties via email. Report generation uses libraries such as ReportLab.

[0452] 6. Customer information management module

[0453] The server collects and stores customer information and manages it in a centralized database. This information is automatically provided to the new employee, helping to ensure a smooth transition of work.

[0454] 7. Emotion Recognition Engine

[0455] The server analyzes the user's emotions using a facial recognition sensor and camera. This analysis uses an emotion recognition model that combines OpenCV and TensorFlow. The analysis results are reflected in the dashboard and reports.

[0456] 8. Work environment adjustment module

[0457] Based on the results of the emotion recognition engine, the server can adjust the user's working environment, for example by changing the content or colors of the dashboard.

[0458] Specific examples

[0459] 1. Data collection and integration

[0460] A user inputs new order data into the order management system. The server collects the data, converts it into a unified format, and stores it in a database. The stored data is checked for duplicates and backed up to cloud storage if necessary.

[0461] 2. Generate and view sales forecasts

[0462] A user logs in to the dashboard and checks the sales forecast for the next month. The server runs a machine learning algorithm based on past sales and inventory data to generate a forecast. The results are displayed in the dashboard in the form of a graph.

[0463] 3. Automatic report generation and distribution

[0464] The server automatically generates a sales report for the previous month on the first day of each month. The report is formatted based on a pre-defined template and sent to the relevant parties via email. The user can then view the received report and check its contents.

[0465] 4. Use of Emotion Recognition

[0466] When a user logs in to the system, an emotion recognition engine analyzes the user's emotions, and the server adjusts the color and layout of the dashboard based on the analysis, providing a comfortable working environment.

[0467] Prompt Sentence Examples

[0468] "Recognize workers' emotions in real time and optimize their working environment. Video data is normalized to 48x48 pixels."

[0469] In this way, the system of the present invention automates the entire process from data collection to integration, prediction, report generation, and emotion recognition, dramatically improving business efficiency.

[0470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0471] Step 1:

[0472] The server collects data from various data sources within the factory (e.g., sensors, management systems). Specifically, a Python program periodically calls the API to obtain the latest data. At this time, the obtained data is saved in raw data format. The input is data from various sensors and management systems, and the output is data saved in the raw data storage within the server.

[0473] Step 2:

[0474] The server converts the collected raw data into a unified format. Specifically, it uses the Pandas library to align various data formats and convert them into a consistent format. The input is the data stored in the raw data storage, and the output is the data converted into a unified format. This conversion process makes it possible to handle data from different data sources in a unified manner.

[0475] Step 3:

[0476] The server saves the data converted into a unified format in a database. Specifically, it uses MongoDB or MySQL to efficiently insert data into the database. The input is the data converted into a unified format, and the output is the data stored in the database. This saving process ensures the consistency and integrity of the data.

[0477] Step 4:

[0478] The server consolidates the data in the database and removes duplicates. Specifically, it uses algorithms to detect and remove duplicates. The input is the data in the database, and the output is a consistent, de-duplicated version. Any incomplete or inaccurate data is also detected and corrected.

[0479] Step 5:

[0480] The server generates sales forecasts using a machine learning algorithm. Specifically, it uses TensorFlow to train a model based on past data and predict future sales. The input is past sales data stored in a database, and the output is the sales forecast results. These forecast results are periodically updated and displayed on a dashboard.

[0481] Step 6:

[0482] The server automatically generates reports based on the specified template. Specifically, it uses the ReportLab library to generate daily, weekly, and monthly reports in PDF format. The input is the latest data in the database and the template, and the output is the generated PDF report. This is then sent to the relevant parties via email.

[0483] Step 7:

[0484] The server accumulates customer characteristic information and automatically provides it to the new representative. Specifically, the customer's transaction history and response history are stored in a database and managed centrally. The input is the customer characteristic information, and the output is an information dashboard for the new representative. This dashboard displays the necessary information in real time when the representative logs in.

[0485] Step 8:

[0486] The server analyzes the user's emotions using a facial recognition sensor or camera. Specifically, it uses an emotion recognition model that combines OpenCV and TensorFlow to recognize emotions from the user's facial expressions. The input is video data acquired from the sensor or camera, and the output is recognized emotion data. Subsequent processing is performed based on the emotion data.

[0487] Step 9:

[0488] The server adjusts the work environment based on the results of the emotion recognition engine. Specifically, it changes the color tone and layout of the dashboard to provide an environment that reduces the user's stress. The input is the result of the emotion recognition engine, and the output is the adjusted work environment. For example, a user who is feeling stressed can be provided with an interface with a calm color tone.

[0489] Through the above steps, the system of the present invention automates the entire process from data collection to integration, prediction, report generation, and emotion recognition, dramatically improving business efficiency.

[0490] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0491] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0492] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0493] [Second embodiment]

[0494] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0495] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0496] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0497] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0498] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0499] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0500] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0501] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0502] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0503] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0504] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0505] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0506] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. A specific embodiment of the system will be described below.

[0507] Data collection and conversion into a unified format

[0508] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[0509] Data storage and integration

[0510] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[0511] Generate sales forecasts

[0512] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[0513] Automated reporting

[0514] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[0515] Accumulation and utilization of customer information

[0516] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[0517] Specific examples

[0518] Example 1: Importing and merging order data

[0519] The user registers new order data in the order management system.

[0520] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0521] The server compares the data with existing data and merges any duplicate order data.

[0522] Example 2: Generating and viewing a sales forecast

[0523] A user logs in to the dashboard and reviews the forecast for next month.

[0524] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0525] The server displays the generated sales forecast in a graphical format on a dashboard.

[0526] Example 3: Automatic report generation and distribution

[0527] The server automatically generates a sales report for the previous month on the 1st of each month.

[0528] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0529] The user views the received report and makes minor corrections as necessary.

[0530] Example 4: Transferring customer information

[0531] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0532] The server displays important information on a dashboard when a new person logs into the system.

[0533] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0534] The system of the present invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving business efficiency.

[0535] The processing flow will be explained below.

[0536] Step 1:

[0537] The server connects to various data sources (email server, project management system, ERP system, etc.) at the specified time to collect new data. For example, it retrieves emails from business partners from the mail server and retrieves new project data from the project management system.

[0538] Step 2:

[0539] The server converts the collected data into a unified format, for example, converting date formats obtained from different data sources into a unified format (e.g., YYYY-MM-DD).

[0540] Step 3:

[0541] The server saves the data converted into the unified format in the database, while checking the consistency and integrity of the data.

[0542] Step 4:

[0543] The server consolidates data in the database and detects and removes duplicates, for example, merging the same order information from multiple data sources into a single record.

[0544] Step 5:

[0545] The server runs a data cleaning process to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs from other information.

[0546] Step 6:

[0547] The server uses machine learning algorithms to train a sales forecasting model based on past data, and the model is periodically updated to improve forecast accuracy.

[0548] Step 7:

[0549] The server applies the sales forecasting model to the new data as input to predict future sales, for example, calculating the sales forecast for the next month and saving it in a database.

[0550] Step 8:

[0551] The server automatically generates reports based on predefined report templates, such as a monthly report containing sales forecasts, actual results, inventory status, and order status.

[0552] Step 9:

[0553] The server automatically emails the generated report to the designated parties, with the report attached as a document file in PDF format or other format.

[0554] Step 10:

[0555] The server stores customer characteristics information and automatically provides it to new staff members. For example, when a new staff member logs in to the system after a change of staff member, relevant customer information is displayed on the dashboard.

[0556] Step 11:

[0557] Users can log in to the dashboard to check next month's sales forecast and the latest customer information, eliminating the need for additional inquiries or research and allowing them to get started quickly.

[0558] Example 1

[0559] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0560] With conventional data collection systems, it was difficult to efficiently collect and integrate data from various data sources. As a result, manual deduplication and correction of inaccurate data were required, reducing operational efficiency. Furthermore, operating machine learning algorithms for sales forecasting and report generation was time-consuming, and there was an issue of not being able to provide the latest forecast data or integrated information in real time. Furthermore, when personnel were changed, there was insufficient information handover to allow new personnel to quickly start work.

[0561] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0562] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and removing duplicate data, means for detecting and correcting incomplete or inaccurate data, means for generating sales forecasts using a machine learning algorithm, means for periodically training a model using past data, means for automatically generating reports based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new sales representative, means for displaying information in real time on a dashboard based on the collected data, and means for collecting email correspondence with business partners and storing it in a database. This allows for efficient collection and integration while maintaining data consistency, automatic generation of sales forecasts and reports, and smooth information transfer when sales representatives are changed.

[0563] "Various data sources" refers to different data providers such as mail servers, project management systems, order management systems, inventory management systems, and quotation management systems.

[0564] "Means of collecting data" refers to the methods and technologies that the server uses to connect to various data sources and obtain the required information.

[0565] A "unified format" refers to data obtained from different data sources converted into a common format or structure.

[0566] "Means of converting data into a unified format" refers to the methods and techniques used to convert collected data into a consistent format.

[0567] "Means of storing in a database" refers to the methods and techniques used to store the converted data in an organized manner and make it easily accessible.

[0568] "Means for integrating data and removing duplicate data" refers to methods and technologies for integrating data obtained from multiple data sources and deleting duplicate data when it exists multiple times, thereby consolidating it into one.

[0569] "Means for detecting and correcting incomplete or inaccurate data" refers to methods and techniques for detecting missing values ​​or erroneous information in data and correcting them to make them accurate.

[0570] A "machine learning algorithm" refers to an algorithm that trains a model based on past data and predicts future sales, etc.

[0571] "Means for generating sales forecasts" means methods or techniques for forecasting future sales using machine learning algorithms.

[0572] "Model training methods" refers to methods and techniques for using historical data to improve the performance of machine learning algorithms.

[0573] "Means for automated report generation" means methods or technologies for automatically generating periodic reports based on sales forecasts or consolidated data.

[0574] "Customer characteristic information" refers to important information related to commercial transactions, such as transaction history, response history, and business status.

[0575] "Means for automatically providing to a new person in charge" refers to a method or technology for automatically providing the necessary customer information to a new person in charge when the person in charge is changed.

[0576] "Means for displaying information on a dashboard in real time" refers to methods and technologies for instantly displaying collected data and forecast results on a user interface.

[0577] "Means of collecting email correspondence with business partners and storing it in a database" refers to methods and technologies for obtaining communication content with business partners from a mail server and storing it in a database.

[0578] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report generation, and customer information handover. Specific embodiments of the system are described below.

[0579] Data collection and conversion into a unified format

[0580] The server periodically connects to various data sources (e.g., mail server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. A Python script is used to collect the data, and its periodic execution is managed by a Cron job. After collection, the server uses libraries such as Pandas and NumPy to convert the data obtained from each data source into a unified format.

[0581] Data storage

[0582] The server saves the converted data in a database such as PostgreSQL or MySQL. At this time, it connects to the database using SQLAlchemy and inserts the data into a table. During the data saving process, it performs transaction management and performs a rollback if an error occurs.

[0583] Data integration and cleaning

[0584] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and merge identical order information into a single record. It also detects incomplete or inaccurate data and corrects it by applying appropriate defaults or imputed data using OpenRefine and Pandas.

[0585] Generate sales forecasts

[0586] The server runs machine learning algorithms using Scikit-learn and TensorFlow to generate sales forecasts for the next month. Past sales data, current inventory data, and the latest order information are used to train the model. Hyperopt and GridSearchCV are also used to improve the accuracy of the forecast model.

[0587] Automated reporting

[0588] The server automatically generates daily, weekly, and monthly reports in Excel and PDF formats based on predefined report templates using openpyxl and xlsxwriter for Excel generation and ReportLab for PDF generation, and sends the generated reports via email to designated parties using an SMTP server.

[0589] Accumulation and utilization of customer information

[0590] The server continuously accumulates and centrally manages customer-specific information. This includes, for example, transaction history, response history, and business status. When a customer changes contact person, the server displays relevant information in real time on the dashboard when the new contact person logs in to the system, supporting a smooth transition. The dashboard was developed using Django and Flask on the backend and React and Vue.js on the frontend.

[0591] Specific examples

[0592] Example 1: Importing and merging order data

[0593] The user registers new order data in the order management system.

[0594] The server periodically collects new order data from the order management system, converts it into a unified format using Pandas, and stores it in the database.

[0595] The server compares the data with existing data and merges any duplicate order data.

[0596] Example 2: Generating and viewing a sales forecast

[0597] A user logs in to the dashboard and reviews the forecast for next month.

[0598] The server uses Scikit-learn to run a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0599] The server displays the generated sales forecast in a graphical format on a dashboard.

[0600] Example 3: Automatic report generation and distribution

[0601] The server automatically generates the previous month's sales report using openpyxl on the 1st of each month.

[0602] The server formats the report content based on a pre-configured template and sends it to the relevant parties via email using an SMTP server.

[0603] The user views the received report and makes minor corrections as necessary.

[0604] Example 4: Transferring customer information

[0605] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0606] When a new person logs into the system, the server displays important information on a dashboard using React.

[0607] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0608] Prompt Sentence Examples

[0609] Below are some example prompts to be input to the generative AI model:

[0610] This system implements programs that automate data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. For example, new data is collected from an order management system, converted into a unified format, and stored in a database. Sales forecasts are then generated and can be viewed on a dashboard. This system uses software such as Scikit-learn, Pandas, Django, and React. Could you please tell me the detailed process flow?

[0611]

[0612] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0613] Step 1: Data collection

[0614] The server periodically connects to various data sources to collect new data. For example, it uses Python scripts and Cron jobs to collect emails from clients from the mail server and retrieves new case information from the case management system. In this process, it retrieves email data using the IMAP protocol and case data via the REST API.

[0615] The input is new data from various data sources and the output is the raw data captured on the server.

[0616] Specific behavior:

[0617] The server periodically connects to the mail server to retrieve new mail.

[0618] The server sends an HTTP request to the project management system's API to retrieve new project data.

[0619] Step 2: Convert the data format

[0620] The server converts the collected data into a unified format, using the Python Pandas library to convert CSV and JSON-formatted data into a DataFrame with consistent column names and data types.

[0621] The input is raw data and the output is data converted into a unified format.

[0622] Specific behavior:

[0623] The email data obtained by the server is read into a Pandas DataFrame and the column names are unified.

[0624] The server converts the job data from JSON format to a DataFrame and extracts the necessary information.

[0625] Step 3: Save your data

[0626] The server saves the converted data in a database (PostgreSQL or MySQL). It connects to the database using SQLAlchemy and inserts the data into a table. Transaction management allows for rollback if an error occurs.

[0627] The input is data converted into a unified format, and the output is data stored in a database.

[0628] Specific behavior:

[0629] The server uses the SQLAlchemy engine to connect to the database and saves the data according to the table structure.

[0630] The server begins a transaction and commits it if successful, or rolls it back if an error occurs.

[0631] Step 4: Integrate and clean the data

[0632] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and fix problematic data.

[0633] The input is the data stored in the database, and the output is the cleaned and consolidated data.

[0634] Specific behavior:

[0635] The server retrieves data from the database and uses Pandas to detect duplicate records.

[0636] The server detects incomplete data and fills in appropriate defaults.

[0637] Step 5: Generate a sales forecast

[0638] The server generates sales forecasts using machine learning algorithms, such as Scikit-learn and TensorFlow, to generate a predictive model based on past sales data, current inventory data, and the latest order information.

[0639] The input is the cleaned integrated data and the output is the predicted sales data.

[0640] Specific behavior:

[0641] The server generates features based on past sales data and current data.

[0642] The server trains the machine learning model and generates sales forecasts.

[0643] Step 6: Reporting

[0644] The server automatically generates reports containing sales forecast results and other business insights. Openpyxl and ReportLab are used to create reports in Excel and PDF formats.

[0645] The inputs are the forecasted sales data and the consolidated data, and the output is the generated report.

[0646] Specific behavior:

[0647] The server generates the sales forecast results as an Excel file and inserts the necessary graphs and tables.

[0648] The server creates a report in PDF format and formats the content according to the specified format.

[0649] Step 7: Distributing the report

[0650] The server sends the generated report to the designated parties via email using an SMTP server.

[0651] The input is the report generated and the output is the report sent to the interested party.

[0652] Specific behavior:

[0653] The server connects to the SMTP server and creates a message containing the email body and any attachments.

[0654] The server sends the email and records the sending log.

[0655] Step 8: Accumulating and utilizing customer information

[0656] The server stores customer characteristics information and automatically provides it to new staff members. When a user logs in to the system, relevant information is displayed in real time on a dashboard.

[0657] The input is customer information and login information, and the output is the information displayed on the dashboard.

[0658] Specific behavior:

[0659] The server extracts customer information from a database and filters the information relevant to the logged-in user.

[0660] The server uses React to display information on a dashboard in real time.

[0661] (Application example 1)

[0662] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0663] In today's business environment, automating data collection, management, analysis, and report generation is a key challenge. Especially in fields that handle large volumes of data, such as online shopping sites, there is a need to check data consistency, forecast sales, generate reports, and consolidate customer information. However, performing these processes manually is extremely time-consuming and inefficient. Furthermore, when duplicate data or inaccuracies occur, the process of detecting and correcting them is complex. Furthermore, the lack of a way to check sales forecasts and report generation in real time makes it difficult to make quick decisions. Therefore, to solve these challenges, a system that automatically collects, consolidates, analyzes, forecasts, and generates reports is needed.

[0664] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0665] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new person in charge, means for displaying the sales forecast in real time via a dashboard on a smartphone or tablet, and means for sending the report by email to relevant parties. This enables automatic collection, integration, analysis, prediction, and report generation of data.

[0666] "Various data sources" refers to different data sources such as a mail server, a case management system, an order management system, an inventory management system, and an estimate management system.

[0667] "Means of collecting data" refers to the function for periodically obtaining new data from various data sources.

[0668] "Means for converting into a unified format" refers to the ability to convert data of different formats or structures into a consistent format.

[0669] "Means for saving in a database" means a function for saving the converted data in a database for centralized management.

[0670] "Means for integrating data and removing duplicate data" means a function that combines identical data obtained from multiple data sources into a single record and eliminates duplication.

[0671] "Machine learning algorithm" refers to a computational model for making sales forecasts based on data.

[0672] "Means for generating sales forecasts" refers to the function of predicting sales based on past sales data, current order information, inventory data, etc.

[0673] "Means for automatically generating a report based on a specified template" means a function for automatically generating a report in accordance with a pre-set format.

[0674] "A means of accumulating customer-specific information and automatically providing it to new staff" refers to a function that continuously manages transaction history, response history, business status, etc., and makes it easy for new staff to access.

[0675] "A means of displaying sales forecasts in real time through a dashboard on a smartphone or tablet" means the ability to view sales forecasts through a dashboard on a mobile device.

[0676] "Means for sending reports to relevant parties by email" refers to a function that automatically sends generated reports to designated recipients by email.

[0677] The system for carrying out the present invention can efficiently collect data, automatically forecast sales, generate reports, and manage customer information on an online shopping site. A specific embodiment of the system will be described below.

[0678] Data collection and conversion into a unified format

[0679] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[0680] Data storage and integration

[0681] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[0682] Generate sales forecasts

[0683] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information. To do this, it uses Python and the Scikit-learn library. The server also periodically trains the model to improve the accuracy of its predictions.

[0684] Automated reporting

[0685] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual sales, inventory status, and order status. The generated reports are then emailed to designated parties. For this purpose, the Smtplib library is used.

[0686] Accumulation and utilization of customer information

[0687] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new customer when the customer is replaced, and is displayed on the dashboard to support a smooth transition.

[0688] View sales forecasts on the dashboard and send reports

[0689] The application installed on a smartphone or tablet displays sales forecasts from the server in real time when the user logs in to the dashboard. The generated reports are automatically sent to the relevant parties via email. For example, the application displays the sales forecast for the next month and sends a monthly report via email.

[0690] Specific examples

[0691] For example, a user may log in to a dashboard on a smartphone app to check the sales forecast for the next month. The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate the sales forecast for the next month and displays it in graph form. The server also automatically generates a sales report for the previous month on the first day of each month, formats it based on a specified template, and sends it to relevant parties by email.

[0692] Prompt Sentence Examples

[0693] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[0694] This system enables automatic data collection, integration, analysis, prediction, and report generation, dramatically improving operational efficiency.

[0695] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0696] Step 1:

[0697] The server periodically connects to various data sources (e.g., mail server, case management system, order management system, inventory management system, quotation management system, etc.) to collect new data. In this case, the server retrieves data obtained from each system (e.g., new order information from the order management system and email correspondence with business partners from the mail server), even if the data is in different formats and forms. The input is the raw data collected from different data sources, and the output is all the raw data collected.

[0698] Step 2:

[0699] The server converts the data collected from each data source into a unified format. During this process, the server converts data of different formats into a consistent format to maintain data integrity. For example, it converts data in XML format into JSON format and aligns the structure. This conversion process allows data from different data sources to be treated as consistent data. The input is raw data collected from various data sources, and the output is data converted into a unified format.

[0700] Step 3:

[0701] The server saves the data converted into a unified format in a database. In this step, the organized data is saved in a centrally managed database, allowing for efficient data access in subsequent processing. The input is the data converted into a unified format, and the output is the data saved in the database.

[0702] Step 4:

[0703] The server consolidates data in the database and removes duplicates. This process involves merging identical order information from multiple data sources into a single record. It also performs data cleaning processes to detect and correct incomplete or inaccurate data. For example, it detects and completes data with incomplete address information. The input is the data stored in the database, and the output is the consolidated data after duplicates have been removed.

[0704] Step 5:

[0705] The server runs a machine learning algorithm based on past data and current conditions to generate sales forecasts. This algorithm is implemented using Python and the Scikit-learn library, and calculates next month's sales forecasts using sales data from the past few years, current inventory status, and the latest order information. In addition, the server periodically performs model training to improve the accuracy of the forecasts. The inputs are past sales data, inventory information, and order information, and the output is next month's sales forecast data.

[0706] Step 6:

[0707] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The reports are sent by email to designated parties. This is implemented using the Smtplib library. The input is the sales forecast data and a report template, and the output is the generated report.

[0708] Step 7:

[0709] The server continuously accumulates and centrally manages customer characteristic information. This information includes, for example, transaction history, response history, and business status. When a person in charge is changed, this information is automatically provided to the new person in charge and displayed on a dashboard to support a smooth handover. The input is customer characteristic information, and the output is centrally managed customer information.

[0710] Step 8:

[0711] Users can log in to the application dashboard using a smartphone or tablet and check sales forecasts in real time from the server. The generated reports are automatically sent to relevant parties by email. The input is the user's login information and sales forecast data obtained from the server, and the output is sales forecast data displayed in real time.

[0712] Prompt Sentence Examples

[0713] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[0714] In this way, automated data collection, integration, analysis, prediction, and report generation are facilitated, improving operational efficiency.

[0715] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0716] The system of the present invention aims to significantly improve business efficiency by automating data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover, and by combining it with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[0717] Data collection and conversion into a unified format

[0718] The server periodically connects to various data sources (email server, case management system, ERP system, etc.) to collect new data. For example, it retrieves client emails from the mail server and retrieves new case data from the case management system. After collecting the data, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[0719] Data storage and integration

[0720] The server saves the unified data to the database, checking for consistency and integrity before inserting it. After saving, the server consolidates the data in the database and detects and removes duplicate data. For example, if the same order information comes from multiple data sources, it will be merged into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[0721] Generate sales forecasts

[0722] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[0723] Automated reporting

[0724] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[0725] Accumulation and utilization of customer information

[0726] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[0727] Introducing the Emotion Engine

[0728] The server uses an emotion engine to recognize the user's emotions and adjust the system's behavior accordingly. For example, if the user is feeling stressed, the server will change the content and color of the report to provide a more relaxing environment. It will also customize the report content based on the user's emotions to provide more accurate information.

[0729] Specific examples

[0730] Example 1: Importing and merging order data

[0731] The user registers new order data in the order management system.

[0732] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0733] The server compares the data with existing data and merges any duplicate order data.

[0734] Example 2: Generating and viewing a sales forecast

[0735] A user logs in to the dashboard and reviews the forecast for next month.

[0736] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0737] The server displays the generated sales forecast in a graphical format on a dashboard.

[0738] Example 3: Automatic report generation and distribution

[0739] The server automatically generates a sales report for the previous month on the 1st of each month.

[0740] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0741] The user views the received report and makes minor corrections as necessary.

[0742] Example 4: Transferring customer information

[0743] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0744] The server displays important information on a dashboard when a new person logs into the system.

[0745] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0746] Example 5: Using the Emotion Engine

[0747] A user logs into the system and the emotion engine analyzes the user's emotional state.

[0748] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[0749] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[0750] The system of this invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving work efficiency. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotional state, providing a more effective work environment.

[0751] The processing flow will be explained below.

[0752] Step 1:

[0753] The server connects to various data sources (e.g., email servers, case management systems, ERP systems, etc.) to collect new data. This process is scheduled periodically, for example, every day at 3:00 AM, and executes API calls and database queries to each data source to extract new data.

[0754] Step 2:

[0755] The server converts the collected data into a unified format, for example, converting date formats (such as YYYY / MM / DD or MM-DD-YYYY) obtained from different data sources into a unified format (e.g., YYYY-MM-DD), ensuring consistency in subsequent processing.

[0756] Step 3:

[0757] The server saves the data converted into a unified format into the database, while checking the consistency and integrity of the data during insertion. For example, it checks for duplicate records, and if any are found, it updates the existing data or ignores them.

[0758] Step 4:

[0759] The server consolidates data in the database, detects and removes duplicates (for example, if the same order information comes from multiple data sources, it consolidates them into a single record), and performs checks to ensure data consistency.

[0760] Step 5:

[0761] The server runs data cleaning processes to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs or incomplete address information with other information to improve consistency.

[0762] Step 6:

[0763] The server uses a machine learning algorithm to train a sales forecasting model based on past data. This model is periodically updated to improve forecast accuracy. For example, at the beginning of each month, the model is retrained using sales data from the past year.

[0764] Step 7:

[0765] The server applies the sales forecasting model to new data as input to predict future sales. For example, it calculates the sales forecast for the next month and saves the results in a database, allowing access to the latest forecast data.

[0766] Step 8:

[0767] The server automatically generates reports based on predefined report templates. For example, a monthly report might include sales forecasts, actual results, inventory status, and order status. The generated reports are saved in formats such as PDF.

[0768] Step 9:

[0769] The server automatically emails the generated report to designated parties based on a pre-defined schedule, with the report being sent at the specified time.

[0770] Step 10:

[0771] The server stores customer characteristics and automatically provides them to new staff members. For example, when a staff member logs in to the system, relevant customer information is displayed on the dashboard. This information includes transaction history and correspondence history.

[0772] Step 11:

[0773] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the user's input patterns and voice data to recognize emotions. Based on the analysis results, it determines the user's emotional state.

[0774] Step 12:

[0775] The server adjusts the system's behavior based on the analyzed emotional data. For example, if the user is feeling stressed, the content and color of the dashboard display will be changed to provide a more relaxing environment. This content adjustment is done in real time.

[0776] Step 13:

[0777] The server customizes the report content based on the user's emotions. For example, if the user is feeling stressed, the server will highlight important information in the report to make it easier to understand. It also omits unnecessary information to reduce the user's burden.

[0778] Step 14:

[0779] Before the login session ends, the server re-analyzes the user's emotional data to see if there has been any improvement. The server records the analysis of the user's emotional state and uses it as reference information for the next login. This information is also used for subsequent analyses.

[0780] Specific examples

[0781] Example 1: Importing and merging order data

[0782] The user registers new order data in the order management system.

[0783] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0784] The server compares the data with existing data and merges any duplicate order data.

[0785] Example 2: Generating and viewing a sales forecast

[0786] A user logs in to the dashboard and reviews the forecast for next month.

[0787] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0788] The server displays the generated sales forecast in a graphical format on a dashboard.

[0789] Example 3: Automatic report generation and distribution

[0790] The server automatically generates a sales report for the previous month on the 1st of each month.

[0791] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0792] The user views the received report and makes minor corrections as necessary.

[0793] Example 4: Transferring customer information

[0794] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0795] The server displays important information on a dashboard when a new person logs into the system.

[0796] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0797] Example 5: Using the Emotion Engine

[0798] A user logs into the system and the emotion engine analyzes the user's emotional state.

[0799] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[0800] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[0801] Example 2

[0802] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0803] Collecting, managing, and analyzing large amounts of data in business is generally done manually, requiring a great deal of effort and time. Furthermore, there is a demand for improved data consistency and accuracy, more accurate sales forecasts, automated report creation, and flexible responses based on emotional states. However, achieving all of these simultaneously has been difficult with conventional technology. This has led to issues such as a lack of improved business efficiency and the immediacy of information transmission.

[0804] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report according to a specified template based on the sales forecast, order status, etc., means for accumulating customer characteristic information and automatically providing it to a new sales representative, and means for analyzing user emotions using an emotion engine and adjusting system operation. This enables improved data consistency and accuracy, improved sales forecast accuracy, automated report creation, and flexible response based on emotional states.

[0805] A "data source" is a system or device that provides information, such as an email server, a case management system, or an ERP system.

[0806] A "unified format" is a standardized data format such as CSV or JSON that converts various data formats into a consistent format.

[0807] A "database" is a system for systematically storing and managing collected data.

[0808] "Duplicate data" refers to data that has been obtained from different sources but has identical content and needs to be combined during integration.

[0809] A "machine learning algorithm" is a computer program used to learn patterns from past data and predict future data.

[0810] "Sales forecasting" refers to predicting future sales based on past and current data.

[0811] A "specified template" is a predefined format used when generating a report.

[0812] A "report" is a document that compiles information such as sales forecasts and order status, and is automatically distributed to relevant parties.

[0813] "Customer characteristic information" refers to information about customers such as transaction history, response history, and business situation.

[0814] A "new contact" is an individual newly assigned to work with a particular customer within the system.

[0815] "Emotion engine" refers to technology or software for analyzing a user's emotional state.

[0816] "Analyzing user emotions" refers to the process of determining the user's emotional state from facial expressions, voice, input data, etc.

[0817] "Adjusting system operation" refers to changing the system's display and functions based on the results of emotion analysis to provide an operating environment that meets the user's needs.

[0818] The present invention is a system that collects data from various data sources, converts the data into a unified format, stores it, integrates and analyzes it as needed, and further analyzes user emotions to adjust the system's operation. Specific embodiments of the present invention are described below.

[0819] Data collection and conversion into a unified format

[0820] The server periodically connects to various data sources, such as email servers, case management systems, and ERP systems, to collect new data. For example, the server retrieves client emails from the email server and retrieves new case data from the case management system. The server converts the collected data into a unified format so that it can be processed consistently.

[0821] Data storage and integration

[0822] The server saves the unified data to the database, checking for consistency and integrity. After saving, the server consolidates the data in the database and detects and removes duplicate data. For example, it combines multiple orders from the same customer into a single record. The server also performs data cleaning to detect and correct incomplete or inaccurate data.

[0823] Generate sales forecasts

[0824] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[0825] Automated reporting

[0826] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[0827] Transfer of customer information

[0828] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[0829] Introducing the Emotion Engine

[0830] The server uses an emotion engine to recognize the user's emotions and adjust the system's behavior accordingly. For example, if the user is feeling stressed, the server can change the content and color of the report to provide a more relaxing environment. It can also customize the report content based on the user's emotions to provide more accurate information.

[0831] Specific examples

[0832] Example 1: Importing and merging order data

[0833] The user registers new order data in the order management system.

[0834] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0835] The server compares the data with existing data and merges any duplicate order data.

[0836] Example 2: Generating and viewing a sales forecast

[0837] A user logs in to the dashboard and reviews the forecast for next month.

[0838] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0839] The server displays the generated sales forecast in a graphical format on a dashboard.

[0840] Example 3: Automatic report generation and distribution

[0841] The server automatically generates a sales report for the previous month on the 1st of each month.

[0842] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0843] The user views the received report and makes minor corrections as necessary.

[0844] Example 4: Transferring customer information

[0845] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0846] The server displays important information on a dashboard when a new person logs into the system.

[0847] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0848] Example 5: Using the Emotion Engine

[0849] A user logs into the system and the emotion engine analyzes the user's emotional state.

[0850] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to calmer tones, providing a more relaxing environment.

[0851] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[0852] Prompt Sentence Examples

[0853] "Explain how you can generate a report based on next month's sales forecast and customize the content based on user sentiment."

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

[0855] Step 1: Data collection

[0856] The server connects to various data sources (email server, project management system, ERP system, etc.) in sequence based on a set schedule. Specifically, the server connects to the mail server using the SMTP protocol and retrieves emails from new business partners. The input is new emails from the mail server, and the output is the retrieved raw data.

[0857] Step 2: Analyze and convert data into a unified format

[0858] Analyzes data collected by the server and understands its structure and format. For example, it parses email data collected by the server and extracts important information such as client names and contact names. The input is the acquired raw data, and the output is parsed data in a unified format (JSON, CSV, etc.).

[0859] Step 3: Save your data

[0860] The server stores the data converted into a unified format in the database. During this process, it performs transaction processing to ensure consistency and integrity. Specifically, it inserts data into the database using an SQL query. The input is the unified format data, and the output is a confirmation message indicating success or failure.

[0861] Step 4: Merge duplicates

[0862] The server detects and consolidates duplicate data in the database. For example, if there are multiple orders from the same supplier, the server combines them into one. The server matches and merges the data. The input is all the data in the database, and the output is the consolidated data set.

[0863] Step 5: Cleaning the data

[0864] The server performs a data cleaning process to detect and correct incomplete or inaccurate data, for example by imputing missing values ​​appropriately or correcting malformed data. The input is the full dataset, and the output is the cleaned dataset.

[0865] Step 6: Generate a sales forecast

[0866] The server uses machine learning algorithms to generate sales forecasts based on past data and current conditions. Specifically, it uses libraries such as Scikit-learn to build a predictive model and calculate the forecast. The input is past sales data, order data, and inventory data, and the output is the sales forecast for the next month.

[0867] Step 7: Automatically generate reports

[0868] The server automatically generates reports based on sales forecasts and order status according to predefined templates. Specifically, it uses a template engine such as Jinja2 to generate reports in HTML format. The inputs are sales forecast values ​​and order data, and the output is the generated report (in HTML format).

[0869] Step 8: Distributing the report

[0870] The server converts the generated report into PDF or HTML format and sends it to the designated parties via email. The input is the generated report, and the output is a confirmation message of the sending result.

[0871] Step 9: Transfer of customer information

[0872] The server extracts information about the client to which the new person in charge has been assigned from the database and displays it on the dashboard. Specifically, it updates and displays the information in real time using Ajax. The input is the client information in the database, and the output is the information displayed on the dashboard.

[0873] Step 10: Use the Emotion Engine

[0874] The server uses an emotion engine to analyze the user's emotional state. Based on the analysis results, the dashboard's display content and colors are adjusted. For example, if the user is feeling stressed, the colors are changed to a gentler tone. The input is the user's facial expression data or voice data, and the output is a user interface customized based on the analysis results.

[0875] Step 11: Generate a customized report

[0876] The server customizes the report content according to the user's emotions, generates a report highlighting the necessary information, and distributes it to relevant parties. The input is the analyzed emotion data, sales forecasts, and order data, and the output is the customized report.

[0877] (Application example 2)

[0878] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0879] Conventional data management systems have issues with inefficient data collection and integration from various data sources, making it difficult to guarantee data consistency and accuracy. They also lack automation for sales forecasting and report creation, and have difficulty optimizing the work environment while taking user emotions into account. This reduces overall work efficiency and negatively impacts user productivity and satisfaction. Another issue is the inability to fully optimize specific tasks, inventory management, and production planning in work environments that include factory robots.

[0880] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0881] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating sales forecasts using a machine learning algorithm, means for automatically generating reports based on a specified template, means for accumulating customer characteristic information and automatically providing it to new staff members, an emotion recognition engine for recognizing user emotions, and means for adjusting the work environment based on the results of the emotion recognition engine. This enables automation of data collection and integration, accurate sales forecasts and report generation, and optimization of the work environment based on user emotions.

[0882] "Various data sources" is a general term for systems and devices that provide data in different formats and structures, such as mail servers, case management systems, and ERP systems.

[0883] "Means for converting collected data into a unified format" refers to technology or equipment that converts data of different formats or structures into a consistent format.

[0884] A "database" is a system designed to efficiently store, manage, and search large amounts of data.

[0885] "Data integration" is the process of compiling data collected from multiple data sources into a single, consistent format.

[0886] "Deleting duplicate data" is a process of consolidating and eliminating duplicate information when the same information exists multiple times.

[0887] A "machine learning algorithm" is a technology that allows computers to automatically learn patterns using large amounts of data and make predictions and classifications.

[0888] "Sales forecasting" is a method of predicting future sales based on past sales data, current inventory status, etc.

[0889] "Automatic report generation" is a function that automatically organizes and outputs the necessary information based on a predefined template.

[0890] "Means for accumulating customer characteristic information" refers to technology or equipment that centrally collects and stores information such as transaction history, response history, and business status.

[0891] The "means for automatically providing information to the new person in charge" is a technology or device that automatically presents the customer's characteristic information to the person in charge and supports a smooth handover of work.

[0892] An "emotion recognition engine that recognizes a user's emotions" is a technology or device that analyzes and recognizes emotions from a user's facial expressions and behavior.

[0893] A "means for adjusting the work environment" is a technology or device that changes work instructions and environmental settings based on the user's emotions, providing an optimal work environment.

[0894] The system of the present invention automates data collection, data integration, sales forecasting, report creation, and work environment adjustment based on emotion recognition in a factory environment, significantly improving business efficiency.

[0895] System Configuration

[0896] The system consists of the following main components:

[0897] 1. Data Collection Module

[0898] The server collects data in real time from various data sources within the factory (e.g., sensors, management systems), including mail servers, project management systems, and ERP systems. Programming languages ​​such as Python are used to collect the data, and REST APIs are used as needed.

[0899] 2. Data Conversion Module

[0900] The collected data is converted into a unified format on the server to maintain consistency even when the data has different formats or structures, and this conversion process is often performed using the Pandas library.

[0901] 3. Database Management Module

[0902] The converted data is stored in a database and managed centrally. MongoDB or MySQL is used for the database. During data integration, duplicate data is removed and data cleaning is also performed.

[0903] 4. Sales Forecasting Module

[0904] The server uses TensorFlow to train machine learning models based on historical data and current inventory status to generate sales forecasts, which are updated periodically and displayed in real time on a dashboard.

[0905] 5. Automatic report generation module

[0906] Daily, weekly, and monthly reports are automatically generated based on specified templates. Reports are generated in formats such as PDF and sent to relevant parties via email. Report generation uses libraries such as ReportLab.

[0907] 6. Customer information management module

[0908] The server collects and stores customer information and manages it in a centralized database. This information is automatically provided to the new employee, helping to ensure a smooth transition of work.

[0909] 7. Emotion Recognition Engine

[0910] The server analyzes the user's emotions using a facial recognition sensor and camera. This analysis uses an emotion recognition model that combines OpenCV and TensorFlow. The analysis results are reflected in the dashboard and reports.

[0911] 8. Work environment adjustment module

[0912] Based on the results of the emotion recognition engine, the server can adjust the user's working environment, for example by changing the content or colors of the dashboard.

[0913] Specific examples

[0914] 1. Data collection and integration

[0915] A user inputs new order data into the order management system. The server collects the data, converts it into a unified format, and stores it in a database. The stored data is checked for duplicates and backed up to cloud storage if necessary.

[0916] 2. Generate and view sales forecasts

[0917] A user logs in to the dashboard and checks the sales forecast for the next month. The server runs a machine learning algorithm based on past sales and inventory data to generate a forecast. The results are displayed in the dashboard in the form of a graph.

[0918] 3. Automatic report generation and distribution

[0919] The server automatically generates a sales report for the previous month on the first day of each month. The report is formatted based on a pre-defined template and sent to the relevant parties via email. The user can then view the received report and check its contents.

[0920] 4. Use of Emotion Recognition

[0921] When a user logs in to the system, an emotion recognition engine analyzes the user's emotions, and the server adjusts the color and layout of the dashboard based on the analysis, providing a comfortable working environment.

[0922] Prompt Sentence Examples

[0923] "Recognize workers' emotions in real time and optimize their working environment. Video data is normalized to 48x48 pixels."

[0924] In this way, the system of the present invention automates the entire process from data collection to integration, prediction, report generation, and emotion recognition, dramatically improving business efficiency.

[0925] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0926] Step 1:

[0927] The server collects data from various data sources within the factory (e.g., sensors, management systems). Specifically, a Python program periodically calls the API to obtain the latest data. At this time, the obtained data is saved in raw data format. The input is data from various sensors and management systems, and the output is data saved in the raw data storage within the server.

[0928] Step 2:

[0929] The server converts the collected raw data into a unified format. Specifically, it uses the Pandas library to align various data formats and convert them into a consistent format. The input is the data stored in the raw data storage, and the output is the data converted into a unified format. This conversion process makes it possible to handle data from different data sources in a unified manner.

[0930] Step 3:

[0931] The server saves the data converted into a unified format in a database. Specifically, it uses MongoDB or MySQL to efficiently insert data into the database. The input is the data converted into a unified format, and the output is the data stored in the database. This saving process ensures the consistency and integrity of the data.

[0932] Step 4:

[0933] The server consolidates the data in the database and removes duplicates. Specifically, it uses algorithms to detect and remove duplicates. The input is the data in the database, and the output is a consistent, de-duplicated version. Any incomplete or inaccurate data is also detected and corrected.

[0934] Step 5:

[0935] The server generates sales forecasts using a machine learning algorithm. Specifically, it uses TensorFlow to train a model based on past data and predict future sales. The input is past sales data stored in a database, and the output is the sales forecast results. These forecast results are periodically updated and displayed on a dashboard.

[0936] Step 6:

[0937] The server automatically generates reports based on the specified template. Specifically, it uses the ReportLab library to generate daily, weekly, and monthly reports in PDF format. The input is the latest data in the database and the template, and the output is the generated PDF report. This is then sent to the relevant parties via email.

[0938] Step 7:

[0939] The server accumulates customer characteristic information and automatically provides it to the new representative. Specifically, the customer's transaction history and response history are stored in a database and managed centrally. The input is the customer characteristic information, and the output is an information dashboard for the new representative. This dashboard displays the necessary information in real time when the representative logs in.

[0940] Step 8:

[0941] The server analyzes the user's emotions using a facial recognition sensor or camera. Specifically, it uses an emotion recognition model that combines OpenCV and TensorFlow to recognize emotions from the user's facial expressions. The input is video data acquired from the sensor or camera, and the output is recognized emotion data. Subsequent processing is performed based on the emotion data.

[0942] Step 9:

[0943] The server adjusts the work environment based on the results of the emotion recognition engine. Specifically, it changes the color tone and layout of the dashboard to provide an environment that reduces the user's stress. The input is the result of the emotion recognition engine, and the output is the adjusted work environment. For example, a user who is feeling stressed can be provided with an interface with a calm color tone.

[0944] Through the above steps, the system of the present invention automates the entire process from data collection to integration, prediction, report generation, and emotion recognition, dramatically improving business efficiency.

[0945] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0946] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0947] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0948] [Third embodiment]

[0949] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0950] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0951] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0952] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0953] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0954] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0955] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0956] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0957] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0958] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0959] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0960] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0961] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. A specific embodiment of the system will be described below.

[0962] Data collection and conversion into a unified format

[0963] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[0964] Data storage and integration

[0965] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[0966] Generate sales forecasts

[0967] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[0968] Automated reporting

[0969] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[0970] Accumulation and utilization of customer information

[0971] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[0972] Specific examples

[0973] Example 1: Importing and merging order data

[0974] The user registers new order data in the order management system.

[0975] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[0976] The server compares the data with existing data and merges any duplicate order data.

[0977] Example 2: Generating and viewing a sales forecast

[0978] A user logs in to the dashboard and reviews the forecast for next month.

[0979] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[0980] The server displays the generated sales forecast in a graphical format on a dashboard.

[0981] Example 3: Automatic report generation and distribution

[0982] The server automatically generates a sales report for the previous month on the 1st of each month.

[0983] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[0984] The user views the received report and makes minor corrections as necessary.

[0985] Example 4: Transferring customer information

[0986] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[0987] The server displays important information on a dashboard when a new person logs into the system.

[0988] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[0989] The system of the present invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving business efficiency.

[0990] The processing flow will be explained below.

[0991] Step 1:

[0992] The server connects to various data sources (email server, project management system, ERP system, etc.) at the specified time to collect new data. For example, it retrieves emails from business partners from the mail server and retrieves new project data from the project management system.

[0993] Step 2:

[0994] The server converts the collected data into a unified format, for example, converting date formats obtained from different data sources into a unified format (e.g., YYYY-MM-DD).

[0995] Step 3:

[0996] The server saves the data converted into the unified format in the database, while checking the consistency and integrity of the data.

[0997] Step 4:

[0998] The server consolidates data in the database and detects and removes duplicates, for example, merging the same order information from multiple data sources into a single record.

[0999] Step 5:

[1000] The server runs a data cleaning process to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs from other information.

[1001] Step 6:

[1002] The server uses machine learning algorithms to train a sales forecasting model based on past data, and the model is periodically updated to improve forecast accuracy.

[1003] Step 7:

[1004] The server applies the sales forecasting model to the new data as input to predict future sales, for example, calculating the sales forecast for the next month and saving it in a database.

[1005] Step 8:

[1006] The server automatically generates reports based on predefined report templates, such as a monthly report containing sales forecasts, actual results, inventory status, and order status.

[1007] Step 9:

[1008] The server automatically emails the generated report to the designated parties, with the report attached as a document file in PDF format or other format.

[1009] Step 10:

[1010] The server stores customer characteristics information and automatically provides it to new staff members. For example, when a new staff member logs in to the system after a change of staff member, relevant customer information is displayed on the dashboard.

[1011] Step 11:

[1012] Users can log in to the dashboard to check next month's sales forecast and the latest customer information, eliminating the need for additional inquiries or research and allowing them to get started quickly.

[1013] Example 1

[1014] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1015] With conventional data collection systems, it was difficult to efficiently collect and integrate data from various data sources. As a result, manual deduplication and correction of inaccurate data were required, reducing operational efficiency. Furthermore, operating machine learning algorithms for sales forecasting and report generation was time-consuming, and there was an issue of not being able to provide the latest forecast data or integrated information in real time. Furthermore, when personnel were changed, there was insufficient information handover to allow new personnel to quickly start work.

[1016] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1017] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and removing duplicate data, means for detecting and correcting incomplete or inaccurate data, means for generating sales forecasts using a machine learning algorithm, means for periodically training a model using past data, means for automatically generating reports based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new sales representative, means for displaying information in real time on a dashboard based on the collected data, and means for collecting email correspondence with business partners and storing it in a database. This allows for efficient collection and integration while maintaining data consistency, automatic generation of sales forecasts and reports, and smooth information transfer when sales representatives are changed.

[1018] "Various data sources" refers to different data providers such as mail servers, project management systems, order management systems, inventory management systems, and quotation management systems.

[1019] "Means of collecting data" refers to the methods and technologies that the server uses to connect to various data sources and obtain the required information.

[1020] A "unified format" refers to data obtained from different data sources converted into a common format or structure.

[1021] "Means of converting data into a unified format" refers to the methods and techniques used to convert collected data into a consistent format.

[1022] "Means of storing in a database" refers to the methods and techniques used to store the converted data in an organized manner and make it easily accessible.

[1023] "Means for integrating data and removing duplicate data" refers to methods and technologies for integrating data obtained from multiple data sources and deleting duplicate data when it exists multiple times, thereby consolidating it into one.

[1024] "Means for detecting and correcting incomplete or inaccurate data" refers to methods and techniques for detecting missing values ​​or erroneous information in data and correcting them to make them accurate.

[1025] A "machine learning algorithm" refers to an algorithm that trains a model based on past data and predicts future sales, etc.

[1026] "Means for generating sales forecasts" means methods or techniques for forecasting future sales using machine learning algorithms.

[1027] "Model training methods" refers to methods and techniques for using historical data to improve the performance of machine learning algorithms.

[1028] "Means for automated report generation" means methods or technologies for automatically generating periodic reports based on sales forecasts or consolidated data.

[1029] "Customer characteristic information" refers to important information related to commercial transactions, such as transaction history, response history, and business status.

[1030] "Means for automatically providing to a new person in charge" refers to a method or technology for automatically providing the necessary customer information to a new person in charge when the person in charge is changed.

[1031] "Means for displaying information on a dashboard in real time" refers to methods and technologies for instantly displaying collected data and forecast results on a user interface.

[1032] "Means of collecting email correspondence with business partners and storing it in a database" refers to methods and technologies for obtaining communication content with business partners from a mail server and storing it in a database.

[1033] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report generation, and customer information handover. Specific embodiments of the system are described below.

[1034] Data collection and conversion into a unified format

[1035] The server periodically connects to various data sources (e.g., mail server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. A Python script is used to collect the data, and its periodic execution is managed by a Cron job. After collection, the server uses libraries such as Pandas and NumPy to convert the data obtained from each data source into a unified format.

[1036] Data storage

[1037] The server saves the converted data in a database such as PostgreSQL or MySQL. At this time, it connects to the database using SQLAlchemy and inserts the data into a table. During the data saving process, it performs transaction management and performs a rollback if an error occurs.

[1038] Data integration and cleaning

[1039] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and merge identical order information into a single record. It also detects incomplete or inaccurate data and corrects it by applying appropriate defaults or imputed data using OpenRefine and Pandas.

[1040] Generate sales forecasts

[1041] The server runs machine learning algorithms using Scikit-learn and TensorFlow to generate sales forecasts for the next month. Past sales data, current inventory data, and the latest order information are used to train the model. Hyperopt and GridSearchCV are also used to improve the accuracy of the forecast model.

[1042] Automated reporting

[1043] The server automatically generates daily, weekly, and monthly reports in Excel and PDF formats based on predefined report templates using openpyxl and xlsxwriter for Excel generation and ReportLab for PDF generation, and sends the generated reports via email to designated parties using an SMTP server.

[1044] Accumulation and utilization of customer information

[1045] The server continuously accumulates and centrally manages customer-specific information. This includes, for example, transaction history, response history, and business status. When a customer changes contact person, the server displays relevant information in real time on the dashboard when the new contact person logs in to the system, supporting a smooth transition. The dashboard was developed using Django and Flask on the backend and React and Vue.js on the frontend.

[1046] Specific examples

[1047] Example 1: Importing and merging order data

[1048] The user registers new order data in the order management system.

[1049] The server periodically collects new order data from the order management system, converts it into a unified format using Pandas, and stores it in the database.

[1050] The server compares the data with existing data and merges any duplicate order data.

[1051] Example 2: Generating and viewing a sales forecast

[1052] A user logs in to the dashboard and reviews the forecast for next month.

[1053] The server uses Scikit-learn to run a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1054] The server displays the generated sales forecast in a graphical format on a dashboard.

[1055] Example 3: Automatic report generation and distribution

[1056] The server automatically generates the previous month's sales report using openpyxl on the 1st of each month.

[1057] The server formats the report content based on a pre-configured template and sends it to the relevant parties via email using an SMTP server.

[1058] The user views the received report and makes minor corrections as necessary.

[1059] Example 4: Transferring customer information

[1060] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1061] When a new person logs into the system, the server displays important information on a dashboard using React.

[1062] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1063] Prompt Sentence Examples

[1064] Below are some example prompts to be input to the generative AI model:

[1065] This system implements programs that automate data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. For example, new data is collected from an order management system, converted into a unified format, and stored in a database. Sales forecasts are then generated and can be viewed on a dashboard. This system uses software such as Scikit-learn, Pandas, Django, and React. Could you please tell me the detailed process flow?

[1066]

[1067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1068] Step 1: Data collection

[1069] The server periodically connects to various data sources to collect new data. For example, it uses Python scripts and Cron jobs to collect emails from clients from the mail server and retrieves new case information from the case management system. In this process, it retrieves email data using the IMAP protocol and case data via the REST API.

[1070] The input is new data from various data sources and the output is the raw data captured on the server.

[1071] Specific behavior:

[1072] The server periodically connects to the mail server to retrieve new mail.

[1073] The server sends an HTTP request to the project management system's API to retrieve new project data.

[1074] Step 2: Convert the data format

[1075] The server converts the collected data into a unified format, using the Python Pandas library to convert CSV and JSON-formatted data into a DataFrame with consistent column names and data types.

[1076] The input is raw data and the output is data converted into a unified format.

[1077] Specific behavior:

[1078] The email data obtained by the server is read into a Pandas DataFrame and the column names are unified.

[1079] The server converts the job data from JSON format to a DataFrame and extracts the necessary information.

[1080] Step 3: Save your data

[1081] The server saves the converted data in a database (PostgreSQL or MySQL). It connects to the database using SQLAlchemy and inserts the data into a table. Transaction management allows for rollback if an error occurs.

[1082] The input is data converted into a unified format, and the output is data stored in a database.

[1083] Specific behavior:

[1084] The server uses the SQLAlchemy engine to connect to the database and saves the data according to the table structure.

[1085] The server begins a transaction and commits it if successful, or rolls it back if an error occurs.

[1086] Step 4: Integrate and clean the data

[1087] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and fix problematic data.

[1088] The input is the data stored in the database, and the output is the cleaned and consolidated data.

[1089] Specific behavior:

[1090] The server retrieves data from the database and uses Pandas to detect duplicate records.

[1091] The server detects incomplete data and fills in appropriate defaults.

[1092] Step 5: Generate a sales forecast

[1093] The server generates sales forecasts using machine learning algorithms, such as Scikit-learn and TensorFlow, to generate a predictive model based on past sales data, current inventory data, and the latest order information.

[1094] The input is the cleaned integrated data and the output is the predicted sales data.

[1095] Specific behavior:

[1096] The server generates features based on past sales data and current data.

[1097] The server trains the machine learning model and generates sales forecasts.

[1098] Step 6: Reporting

[1099] The server automatically generates reports containing sales forecast results and other business insights. Openpyxl and ReportLab are used to create reports in Excel and PDF formats.

[1100] The inputs are the forecasted sales data and the consolidated data, and the output is the generated report.

[1101] Specific behavior:

[1102] The server generates the sales forecast results as an Excel file and inserts the necessary graphs and tables.

[1103] The server creates a report in PDF format and formats the content according to the specified format.

[1104] Step 7: Distributing the report

[1105] The server sends the generated report to the designated parties via email using an SMTP server.

[1106] The input is the report generated and the output is the report sent to the interested party.

[1107] Specific behavior:

[1108] The server connects to the SMTP server and creates a message containing the email body and any attachments.

[1109] The server sends the email and records the sending log.

[1110] Step 8: Accumulating and utilizing customer information

[1111] The server stores customer characteristics information and automatically provides it to new staff members. When a user logs in to the system, relevant information is displayed in real time on a dashboard.

[1112] The input is customer information and login information, and the output is the information displayed on the dashboard.

[1113] Specific behavior:

[1114] The server extracts customer information from a database and filters the information relevant to the logged-in user.

[1115] The server uses React to display information on a dashboard in real time.

[1116] (Application example 1)

[1117] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1118] In today's business environment, automating data collection, management, analysis, and report generation is a key challenge. Especially in fields that handle large volumes of data, such as online shopping sites, there is a need to check data consistency, forecast sales, generate reports, and consolidate customer information. However, performing these processes manually is extremely time-consuming and inefficient. Furthermore, when duplicate data or inaccuracies occur, the process of detecting and correcting them is complex. Furthermore, the lack of a way to check sales forecasts and report generation in real time makes it difficult to make quick decisions. Therefore, to solve these challenges, a system that automatically collects, consolidates, analyzes, forecasts, and generates reports is needed.

[1119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1120] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new person in charge, means for displaying the sales forecast in real time via a dashboard on a smartphone or tablet, and means for sending the report by email to relevant parties. This enables automatic collection, integration, analysis, prediction, and report generation of data.

[1121] "Various data sources" refers to different data sources such as a mail server, a case management system, an order management system, an inventory management system, and an estimate management system.

[1122] "Means of collecting data" refers to the function for periodically obtaining new data from various data sources.

[1123] "Means for converting into a unified format" refers to the ability to convert data of different formats or structures into a consistent format.

[1124] "Means for saving in a database" means a function for saving the converted data in a database for centralized management.

[1125] "Means for integrating data and removing duplicate data" means a function that combines identical data obtained from multiple data sources into a single record and eliminates duplication.

[1126] "Machine learning algorithm" refers to a computational model for making sales forecasts based on data.

[1127] "Means for generating sales forecasts" refers to the function of predicting sales based on past sales data, current order information, inventory data, etc.

[1128] "Means for automatically generating a report based on a specified template" means a function for automatically generating a report in accordance with a pre-set format.

[1129] "A means of accumulating customer-specific information and automatically providing it to new staff" refers to a function that continuously manages transaction history, response history, business status, etc., and makes it easy for new staff to access.

[1130] "A means of displaying sales forecasts in real time through a dashboard on a smartphone or tablet" means the ability to view sales forecasts through a dashboard on a mobile device.

[1131] "Means for sending reports to relevant parties by email" refers to a function that automatically sends generated reports to designated recipients by email.

[1132] The system for carrying out the present invention can efficiently collect data, automatically forecast sales, generate reports, and manage customer information on an online shopping site. A specific embodiment of the system will be described below.

[1133] Data collection and conversion into a unified format

[1134] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[1135] Data storage and integration

[1136] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[1137] Generate sales forecasts

[1138] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information. To do this, it uses Python and the Scikit-learn library. The server also periodically trains the model to improve the accuracy of its predictions.

[1139] Automated reporting

[1140] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual sales, inventory status, and order status. The generated reports are then emailed to designated parties. For this purpose, the Smtplib library is used.

[1141] Accumulation and utilization of customer information

[1142] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new customer when the customer is replaced, and is displayed on the dashboard to support a smooth transition.

[1143] View sales forecasts on the dashboard and send reports

[1144] The application installed on a smartphone or tablet displays sales forecasts from the server in real time when the user logs in to the dashboard. The generated reports are automatically sent to the relevant parties via email. For example, the application displays the sales forecast for the next month and sends a monthly report via email.

[1145] Specific examples

[1146] For example, a user may log in to a dashboard on a smartphone app to check the sales forecast for the next month. The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate the sales forecast for the next month and displays it in graph form. The server also automatically generates a sales report for the previous month on the first day of each month, formats it based on a specified template, and sends it to relevant parties by email.

[1147] Prompt Sentence Examples

[1148] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[1149] This system enables automatic data collection, integration, analysis, prediction, and report generation, dramatically improving operational efficiency.

[1150] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1151] Step 1:

[1152] The server periodically connects to various data sources (e.g., mail server, case management system, order management system, inventory management system, quotation management system, etc.) to collect new data. In this case, the server retrieves data obtained from each system (e.g., new order information from the order management system and email correspondence with business partners from the mail server), even if the data is in different formats and forms. The input is the raw data collected from different data sources, and the output is all the raw data collected.

[1153] Step 2:

[1154] The server converts the data collected from each data source into a unified format. During this process, the server converts data of different formats into a consistent format to maintain data integrity. For example, it converts data in XML format into JSON format and aligns the structure. This conversion process allows data from different data sources to be treated as consistent data. The input is raw data collected from various data sources, and the output is data converted into a unified format.

[1155] Step 3:

[1156] The server saves the data converted into a unified format in a database. In this step, the organized data is saved in a centrally managed database, allowing for efficient data access in subsequent processing. The input is the data converted into a unified format, and the output is the data saved in the database.

[1157] Step 4:

[1158] The server consolidates data in the database and removes duplicates. This process involves merging identical order information from multiple data sources into a single record. It also performs data cleaning processes to detect and correct incomplete or inaccurate data. For example, it detects and completes data with incomplete address information. The input is the data stored in the database, and the output is the consolidated data after duplicates have been removed.

[1159] Step 5:

[1160] The server runs a machine learning algorithm based on past data and current conditions to generate sales forecasts. This algorithm is implemented using Python and the Scikit-learn library, and calculates next month's sales forecasts using sales data from the past few years, current inventory status, and the latest order information. In addition, the server periodically performs model training to improve the accuracy of the forecasts. The inputs are past sales data, inventory information, and order information, and the output is next month's sales forecast data.

[1161] Step 6:

[1162] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The reports are sent by email to designated parties. This is implemented using the Smtplib library. The input is the sales forecast data and a report template, and the output is the generated report.

[1163] Step 7:

[1164] The server continuously accumulates and centrally manages customer characteristic information. This information includes, for example, transaction history, response history, and business status. When a person in charge is changed, this information is automatically provided to the new person in charge and displayed on a dashboard to support a smooth handover. The input is customer characteristic information, and the output is centrally managed customer information.

[1165] Step 8:

[1166] Users can log in to the application dashboard using a smartphone or tablet and check sales forecasts in real time from the server. The generated reports are automatically sent to relevant parties by email. The input is the user's login information and sales forecast data obtained from the server, and the output is sales forecast data displayed in real time.

[1167] Prompt Sentence Examples

[1168] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[1169] In this way, automated data collection, integration, analysis, prediction, and report generation are facilitated, improving operational efficiency.

[1170] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1171] The system of the present invention aims to significantly improve business efficiency by automating data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover, and by combining it with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[1172] Data collection and conversion into a unified format

[1173] The server periodically connects to various data sources (email server, case management system, ERP system, etc.) to collect new data. For example, it retrieves client emails from the mail server and retrieves new case data from the case management system. After collecting the data, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[1174] Data storage and integration

[1175] The server saves the unified data to the database, checking for consistency and integrity before inserting it. After saving, the server consolidates the data in the database and detects and removes duplicate data. For example, if the same order information comes from multiple data sources, it will be merged into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[1176] Generate sales forecasts

[1177] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[1178] Automated reporting

[1179] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[1180] Accumulation and utilization of customer information

[1181] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[1182] Introducing the Emotion Engine

[1183] The server uses an emotion engine to recognize the user's emotions and adjust the system's behavior accordingly. For example, if the user is feeling stressed, the server will change the content and color of the report to provide a more relaxing environment. It will also customize the report content based on the user's emotions to provide more accurate information.

[1184] Specific examples

[1185] Example 1: Importing and merging order data

[1186] The user registers new order data in the order management system.

[1187] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[1188] The server compares the data with existing data and merges any duplicate order data.

[1189] Example 2: Generating and viewing a sales forecast

[1190] A user logs in to the dashboard and reviews the forecast for next month.

[1191] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1192] The server displays the generated sales forecast in a graphical format on a dashboard.

[1193] Example 3: Automatic report generation and distribution

[1194] The server automatically generates a sales report for the previous month on the 1st of each month.

[1195] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[1196] The user views the received report and makes minor corrections as necessary.

[1197] Example 4: Transferring customer information

[1198] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1199] The server displays important information on a dashboard when a new person logs into the system.

[1200] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1201] Example 5: Using the Emotion Engine

[1202] A user logs into the system and the emotion engine analyzes the user's emotional state.

[1203] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[1204] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[1205] The system of this invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving work efficiency. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotional state, providing a more effective work environment.

[1206] The processing flow will be explained below.

[1207] Step 1:

[1208] The server connects to various data sources (e.g., email servers, case management systems, ERP systems, etc.) to collect new data. This process is scheduled periodically, for example, every day at 3:00 AM, and executes API calls and database queries to each data source to extract new data.

[1209] Step 2:

[1210] The server converts the collected data into a unified format, for example, converting date formats (such as YYYY / MM / DD or MM-DD-YYYY) obtained from different data sources into a unified format (e.g., YYYY-MM-DD), ensuring consistency in subsequent processing.

[1211] Step 3:

[1212] The server saves the data converted into a unified format into the database, while checking the consistency and integrity of the data during insertion. For example, it checks for duplicate records, and if any are found, it updates the existing data or ignores them.

[1213] Step 4:

[1214] The server consolidates data in the database, detects and removes duplicates (for example, if the same order information comes from multiple data sources, it consolidates them into a single record), and performs checks to ensure data consistency.

[1215] Step 5:

[1216] The server runs data cleaning processes to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs or incomplete address information with other information to improve consistency.

[1217] Step 6:

[1218] The server uses a machine learning algorithm to train a sales forecasting model based on past data. This model is periodically updated to improve forecast accuracy. For example, at the beginning of each month, the model is retrained using sales data from the past year.

[1219] Step 7:

[1220] The server applies the sales forecasting model to new data as input to predict future sales. For example, it calculates the sales forecast for the next month and saves the results in a database, allowing access to the latest forecast data.

[1221] Step 8:

[1222] The server automatically generates reports based on predefined report templates. For example, a monthly report might include sales forecasts, actual results, inventory status, and order status. The generated reports are saved in formats such as PDF.

[1223] Step 9:

[1224] The server automatically emails the generated report to designated parties based on a pre-defined schedule, with the report being sent at the specified time.

[1225] Step 10:

[1226] The server stores customer characteristics and automatically provides them to new staff members. For example, when a staff member logs in to the system, relevant customer information is displayed on the dashboard. This information includes transaction history and correspondence history.

[1227] Step 11:

[1228] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the user's input patterns and voice data to recognize emotions. Based on the analysis results, it determines the user's emotional state.

[1229] Step 12:

[1230] The server adjusts the system's behavior based on the analyzed emotional data. For example, if the user is feeling stressed, the content and color of the dashboard display will be changed to provide a more relaxing environment. This content adjustment is done in real time.

[1231] Step 13:

[1232] The server customizes the report content based on the user's emotions. For example, if the user is feeling stressed, the server will highlight important information in the report to make it easier to understand. It also omits unnecessary information to reduce the user's burden.

[1233] Step 14:

[1234] Before the login session ends, the server re-analyzes the user's emotional data to see if there has been any improvement. The server records the analysis of the user's emotional state and uses it as reference information for the next login. This information is also used for subsequent analyses.

[1235] Specific examples

[1236] Example 1: Importing and merging order data

[1237] The user registers new order data in the order management system.

[1238] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[1239] The server compares the data with existing data and merges any duplicate order data.

[1240] Example 2: Generating and viewing a sales forecast

[1241] A user logs in to the dashboard and reviews the forecast for next month.

[1242] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1243] The server displays the generated sales forecast in a graphical format on a dashboard.

[1244] Example 3: Automatic report generation and distribution

[1245] The server automatically generates a sales report for the previous month on the 1st of each month.

[1246] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[1247] The user views the received report and makes minor corrections as necessary.

[1248] Example 4: Transferring customer information

[1249] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1250] The server displays important information on a dashboard when a new person logs into the system.

[1251] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1252] Example 5: Using the Emotion Engine

[1253] A user logs into the system and the emotion engine analyzes the user's emotional state.

[1254] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[1255] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[1256] Example 2

[1257] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1258] Collecting, managing, and analyzing large amounts of data in business is generally done manually, requiring a great deal of effort and time. Furthermore, there is a demand for improved data consistency and accuracy, more accurate sales forecasts, automated report creation, and flexible responses based on emotional states. However, achieving all of these simultaneously has been difficult with conventional technology. This has led to issues such as a lack of improved business efficiency and the immediacy of information transmission.

[1259] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report according to a specified template based on the sales forecast, order status, etc., means for accumulating customer characteristic information and automatically providing it to a new sales representative, and means for analyzing user emotions using an emotion engine and adjusting system operation. This enables improved data consistency and accuracy, improved sales forecast accuracy, automated report creation, and flexible response based on emotional states.

[1260] A "data source" is a system or device that provides information, such as an email server, a case management system, or an ERP system.

[1261] A "unified format" is a standardized data format such as CSV or JSON that converts various data formats into a consistent format.

[1262] A "database" is a system for systematically storing and managing collected data.

[1263] "Duplicate data" refers to data that has been obtained from different sources but has identical content and needs to be combined during integration.

[1264] A "machine learning algorithm" is a computer program used to learn patterns from past data and predict future data.

[1265] "Sales forecasting" refers to predicting future sales based on past and current data.

[1266] A "specified template" is a predefined format used when generating a report.

[1267] A "report" is a document that compiles information such as sales forecasts and order status, and is automatically distributed to relevant parties.

[1268] "Customer characteristic information" refers to information about customers such as transaction history, response history, and business situation.

[1269] A "new contact" is an individual newly assigned to work with a particular customer within the system.

[1270] "Emotion engine" refers to technology or software for analyzing a user's emotional state.

[1271] "Analyzing user emotions" refers to the process of determining the user's emotional state from facial expressions, voice, input data, etc.

[1272] "Adjusting system operation" refers to changing the system's display and functions based on the results of emotion analysis to provide an operating environment that meets the user's needs.

[1273] The present invention is a system that collects data from various data sources, converts the data into a unified format, stores it, integrates and analyzes it as needed, and further analyzes user emotions to adjust the system's operation. Specific embodiments of the present invention are described below.

[1274] Data collection and conversion into a unified format

[1275] The server periodically connects to various data sources, such as email servers, case management systems, and ERP systems, to collect new data. For example, the server retrieves client emails from the email server and retrieves new case data from the case management system. The server converts the collected data into a unified format so that it can be processed consistently.

[1276] Data storage and integration

[1277] The server saves the unified data to the database, checking for consistency and integrity. After saving, the server consolidates the data in the database and detects and removes duplicate data. For example, it combines multiple orders from the same customer into a single record. The server also performs data cleaning to detect and correct incomplete or inaccurate data.

[1278] Generate sales forecasts

[1279] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[1280] Automated reporting

[1281] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[1282] Transfer of customer information

[1283] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[1284] Introducing the Emotion Engine

[1285] The server uses an emotion engine to recognize the user's emotions and adjust the system's behavior accordingly. For example, if the user is feeling stressed, the server can change the content and color of the report to provide a more relaxing environment. It can also customize the report content based on the user's emotions to provide more accurate information.

[1286] Specific examples

[1287] Example 1: Importing and merging order data

[1288] The user registers new order data in the order management system.

[1289] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[1290] The server compares the data with existing data and merges any duplicate order data.

[1291] Example 2: Generating and viewing a sales forecast

[1292] A user logs in to the dashboard and reviews the forecast for next month.

[1293] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1294] The server displays the generated sales forecast in a graphical format on a dashboard.

[1295] Example 3: Automatic report generation and distribution

[1296] The server automatically generates a sales report for the previous month on the 1st of each month.

[1297] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[1298] The user views the received report and makes minor corrections as necessary.

[1299] Example 4: Transferring customer information

[1300] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1301] The server displays important information on a dashboard when a new person logs into the system.

[1302] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1303] Example 5: Using the Emotion Engine

[1304] A user logs into the system and the emotion engine analyzes the user's emotional state.

[1305] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to calmer tones, providing a more relaxing environment.

[1306] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[1307] Prompt Sentence Examples

[1308] "Explain how you can generate a report based on next month's sales forecast and customize the content based on user sentiment."

[1309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1310] Step 1: Data collection

[1311] The server connects to various data sources (email server, project management system, ERP system, etc.) in sequence based on a set schedule. Specifically, the server connects to the mail server using the SMTP protocol and retrieves emails from new business partners. The input is new emails from the mail server, and the output is the retrieved raw data.

[1312] Step 2: Analyze and convert data into a unified format

[1313] Analyzes data collected by the server and understands its structure and format. For example, it parses email data collected by the server and extracts important information such as client names and contact names. The input is the acquired raw data, and the output is parsed data in a unified format (JSON, CSV, etc.).

[1314] Step 3: Save your data

[1315] The server stores the data converted into a unified format in the database. During this process, it performs transaction processing to ensure consistency and integrity. Specifically, it inserts data into the database using an SQL query. The input is the unified format data, and the output is a confirmation message indicating success or failure.

[1316] Step 4: Merge duplicates

[1317] The server detects and consolidates duplicate data in the database. For example, if there are multiple orders from the same supplier, the server combines them into one. The server matches and merges the data. The input is all the data in the database, and the output is the consolidated data set.

[1318] Step 5: Cleaning the data

[1319] The server performs a data cleaning process to detect and correct incomplete or inaccurate data, for example by imputing missing values ​​appropriately or correcting malformed data. The input is the full dataset, and the output is the cleaned dataset.

[1320] Step 6: Generate a sales forecast

[1321] The server uses machine learning algorithms to generate sales forecasts based on past data and current conditions. Specifically, it uses libraries such as Scikit-learn to build a predictive model and calculate the forecast. The input is past sales data, order data, and inventory data, and the output is the sales forecast for the next month.

[1322] Step 7: Automatically generate reports

[1323] The server automatically generates reports based on sales forecasts and order status according to predefined templates. Specifically, it uses a template engine such as Jinja2 to generate reports in HTML format. The inputs are sales forecast values ​​and order data, and the output is the generated report (in HTML format).

[1324] Step 8: Distributing the report

[1325] The server converts the generated report into PDF or HTML format and sends it to the designated parties via email. The input is the generated report, and the output is a confirmation message of the sending result.

[1326] Step 9: Transfer of customer information

[1327] The server extracts information about the client to which the new person in charge has been assigned from the database and displays it on the dashboard. Specifically, it updates and displays the information in real time using Ajax. The input is the client information in the database, and the output is the information displayed on the dashboard.

[1328] Step 10: Use the Emotion Engine

[1329] The server uses an emotion engine to analyze the user's emotional state. Based on the analysis results, the dashboard's display content and colors are adjusted. For example, if the user is feeling stressed, the colors are changed to a gentler tone. The input is the user's facial expression data or voice data, and the output is a user interface customized based on the analysis results.

[1330] Step 11: Generate a customized report

[1331] The server customizes the report content according to the user's emotions, generates a report highlighting the necessary information, and distributes it to relevant parties. The input is the analyzed emotion data, sales forecasts, and order data, and the output is the customized report.

[1332] (Application example 2)

[1333] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1334] Conventional data management systems have issues with inefficient data collection and integration from various data sources, making it difficult to guarantee data consistency and accuracy. They also lack automation for sales forecasting and report creation, and have difficulty optimizing the work environment while taking user emotions into account. This reduces overall work efficiency and negatively impacts user productivity and satisfaction. Another issue is the inability to fully optimize specific tasks, inventory management, and production planning in work environments that include factory robots.

[1335] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1336] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating sales forecasts using a machine learning algorithm, means for automatically generating reports based on a specified template, means for accumulating customer characteristic information and automatically providing it to new staff members, an emotion recognition engine for recognizing user emotions, and means for adjusting the work environment based on the results of the emotion recognition engine. This enables automation of data collection and integration, accurate sales forecasts and report generation, and optimization of the work environment based on user emotions.

[1337] "Various data sources" is a general term for systems and devices that provide data in different formats and structures, such as mail servers, case management systems, and ERP systems.

[1338] "Means for converting collected data into a unified format" refers to technology or equipment that converts data of different formats or structures into a consistent format.

[1339] A "database" is a system designed to efficiently store, manage, and search large amounts of data.

[1340] "Data integration" is the process of compiling data collected from multiple data sources into a single, consistent format.

[1341] "Deleting duplicate data" is a process of consolidating and eliminating duplicate information when the same information exists multiple times.

[1342] A "machine learning algorithm" is a technology that allows computers to automatically learn patterns using large amounts of data and make predictions and classifications.

[1343] "Sales forecasting" is a method of predicting future sales based on past sales data, current inventory status, etc.

[1344] "Automatic report generation" is a function that automatically organizes and outputs the necessary information based on a predefined template.

[1345] "Means for accumulating customer characteristic information" refers to technology or equipment that centrally collects and stores information such as transaction history, response history, and business status.

[1346] The "means for automatically providing information to the new person in charge" is a technology or device that automatically presents the customer's characteristic information to the person in charge and supports a smooth handover of work.

[1347] An "emotion recognition engine that recognizes a user's emotions" is a technology or device that analyzes and recognizes emotions from a user's facial expressions and behavior.

[1348] A "means for adjusting the work environment" is a technology or device that changes work instructions and environmental settings based on the user's emotions, providing an optimal work environment.

[1349] The system of the present invention automates data collection, data integration, sales forecasting, report creation, and work environment adjustment based on emotion recognition in a factory environment, significantly improving business efficiency.

[1350] System Configuration

[1351] The system consists of the following main components:

[1352] 1. Data Collection Module

[1353] The server collects data in real time from various data sources within the factory (e.g., sensors, management systems), including mail servers, project management systems, and ERP systems. Programming languages ​​such as Python are used to collect the data, and REST APIs are used as needed.

[1354] 2. Data Conversion Module

[1355] The collected data is converted into a unified format on the server to maintain consistency even when the data has different formats or structures, and this conversion process is often performed using the Pandas library.

[1356] 3. Database Management Module

[1357] The converted data is stored in a database and managed centrally. MongoDB or MySQL is used for the database. During data integration, duplicate data is removed and data cleaning is also performed.

[1358] 4. Sales Forecasting Module

[1359] The server uses TensorFlow to train machine learning models based on historical data and current inventory status to generate sales forecasts, which are updated periodically and displayed in real time on a dashboard.

[1360] 5. Automatic report generation module

[1361] Daily, weekly, and monthly reports are automatically generated based on specified templates. Reports are generated in formats such as PDF and sent to relevant parties via email. Report generation uses libraries such as ReportLab.

[1362] 6. Customer information management module

[1363] The server collects and stores customer information and manages it in a centralized database. This information is automatically provided to the new employee, helping to ensure a smooth transition of work.

[1364] 7. Emotion Recognition Engine

[1365] The server analyzes the user's emotions using a facial recognition sensor and camera. This analysis uses an emotion recognition model that combines OpenCV and TensorFlow. The analysis results are reflected in the dashboard and reports.

[1366] 8. Work environment adjustment module

[1367] Based on the results of the emotion recognition engine, the server can adjust the user's working environment, for example by changing the content or colors of the dashboard.

[1368] Specific examples

[1369] 1. Data collection and integration

[1370] A user inputs new order data into the order management system. The server collects the data, converts it into a unified format, and stores it in a database. The stored data is checked for duplicates and backed up to cloud storage if necessary.

[1371] 2. Generate and view sales forecasts

[1372] A user logs in to the dashboard and checks the sales forecast for the next month. The server runs a machine learning algorithm based on past sales and inventory data to generate a forecast. The results are displayed in the dashboard in the form of a graph.

[1373] 3. Automatic report generation and distribution

[1374] The server automatically generates a sales report for the previous month on the first day of each month. The report is formatted based on a pre-defined template and sent to the relevant parties via email. The user can then view the received report and check its contents.

[1375] 4. Use of Emotion Recognition

[1376] When a user logs in to the system, an emotion recognition engine analyzes the user's emotions, and the server adjusts the color and layout of the dashboard based on the analysis, providing a comfortable working environment.

[1377] Prompt Sentence Examples

[1378] "Recognize workers' emotions in real time and optimize their working environment. Video data is normalized to 48x48 pixels."

[1379] In this way, the system of the present invention automates the entire process from data collection to integration, prediction, report generation, and emotion recognition, dramatically improving business efficiency.

[1380] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1381] Step 1:

[1382] The server collects data from various data sources within the factory (e.g., sensors, management systems). Specifically, a Python program periodically calls the API to obtain the latest data. At this time, the obtained data is saved in raw data format. The input is data from various sensors and management systems, and the output is data saved in the raw data storage within the server.

[1383] Step 2:

[1384] The server converts the collected raw data into a unified format. Specifically, it uses the Pandas library to align various data formats and convert them into a consistent format. The input is the data stored in the raw data storage, and the output is the data converted into a unified format. This conversion process makes it possible to handle data from different data sources in a unified manner.

[1385] Step 3:

[1386] The server saves the data converted into a unified format in a database. Specifically, it uses MongoDB or MySQL to efficiently insert data into the database. The input is the data converted into a unified format, and the output is the data stored in the database. This saving process ensures the consistency and integrity of the data.

[1387] Step 4:

[1388] The server consolidates the data in the database and removes duplicates. Specifically, it uses algorithms to detect and remove duplicates. The input is the data in the database, and the output is a consistent, de-duplicated version. Any incomplete or inaccurate data is also detected and corrected.

[1389] Step 5:

[1390] The server generates sales forecasts using a machine learning algorithm. Specifically, it uses TensorFlow to train a model based on past data and predict future sales. The input is past sales data stored in a database, and the output is the sales forecast results. These forecast results are periodically updated and displayed on a dashboard.

[1391] Step 6:

[1392] The server automatically generates reports based on the specified template. Specifically, it uses the ReportLab library to generate daily, weekly, and monthly reports in PDF format. The input is the latest data in the database and the template, and the output is the generated PDF report. This is then sent to the relevant parties via email.

[1393] Step 7:

[1394] The server accumulates customer characteristic information and automatically provides it to the new representative. Specifically, the customer's transaction history and response history are stored in a database and managed centrally. The input is the customer characteristic information, and the output is an information dashboard for the new representative. This dashboard displays the necessary information in real time when the representative logs in.

[1395] Step 8:

[1396] The server analyzes the user's emotions using a facial recognition sensor or camera. Specifically, it uses an emotion recognition model that combines OpenCV and TensorFlow to recognize emotions from the user's facial expressions. The input is video data acquired from the sensor or camera, and the output is recognized emotion data. Subsequent processing is performed based on the emotion data.

[1397] Step 9:

[1398] The server adjusts the work environment based on the results of the emotion recognition engine. Specifically, it changes the color tone and layout of the dashboard to provide an environment that reduces the user's stress. The input is the result of the emotion recognition engine, and the output is the adjusted work environment. For example, a user who is feeling stressed can be provided with an interface with a calm color tone.

[1399] Through the above steps, the system of the present invention automates the entire process from data collection to integration, prediction, report generation, and emotion recognition, dramatically improving business efficiency.

[1400] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1401] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1402] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1403] [Fourth embodiment]

[1404] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1405] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1406] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1407] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1408] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1409] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1410] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1411] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1412] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1413] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1414] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1415] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1416] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1417] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. A specific embodiment of the system will be described below.

[1418] Data collection and conversion into a unified format

[1419] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[1420] Data storage and integration

[1421] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[1422] Generate sales forecasts

[1423] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[1424] Automated reporting

[1425] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[1426] Accumulation and utilization of customer information

[1427] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[1428] Specific examples

[1429] Example 1: Importing and merging order data

[1430] The user registers new order data in the order management system.

[1431] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[1432] The server compares the data with existing data and merges any duplicate order data.

[1433] Example 2: Generating and viewing a sales forecast

[1434] A user logs in to the dashboard and reviews the forecast for next month.

[1435] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1436] The server displays the generated sales forecast in a graphical format on a dashboard.

[1437] Example 3: Automatic report generation and distribution

[1438] The server automatically generates a sales report for the previous month on the 1st of each month.

[1439] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[1440] The user views the received report and makes minor corrections as necessary.

[1441] Example 4: Transferring customer information

[1442] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1443] The server displays important information on a dashboard when a new person logs into the system.

[1444] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1445] The system of the present invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving business efficiency.

[1446] The processing flow will be explained below.

[1447] Step 1:

[1448] The server connects to various data sources (email server, project management system, ERP system, etc.) at the specified time to collect new data. For example, it retrieves emails from business partners from the mail server and retrieves new project data from the project management system.

[1449] Step 2:

[1450] The server converts the collected data into a unified format, for example, converting date formats obtained from different data sources into a unified format (e.g., YYYY-MM-DD).

[1451] Step 3:

[1452] The server saves the data converted into the unified format in the database, while checking the consistency and integrity of the data.

[1453] Step 4:

[1454] The server consolidates data in the database and detects and removes duplicates, for example, merging the same order information from multiple data sources into a single record.

[1455] Step 5:

[1456] The server runs a data cleaning process to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs from other information.

[1457] Step 6:

[1458] The server uses machine learning algorithms to train a sales forecasting model based on past data, and the model is periodically updated to improve forecast accuracy.

[1459] Step 7:

[1460] The server applies the sales forecasting model to the new data as input to predict future sales, for example, calculating the sales forecast for the next month and saving it in a database.

[1461] Step 8:

[1462] The server automatically generates reports based on predefined report templates, such as a monthly report containing sales forecasts, actual results, inventory status, and order status.

[1463] Step 9:

[1464] The server automatically emails the generated report to the designated parties, with the report attached as a document file in PDF format or other format.

[1465] Step 10:

[1466] The server stores customer characteristics information and automatically provides it to new staff members. For example, when a new staff member logs in to the system after a change of staff member, relevant customer information is displayed on the dashboard.

[1467] Step 11:

[1468] Users can log in to the dashboard to check next month's sales forecast and the latest customer information, eliminating the need for additional inquiries or research and allowing them to get started quickly.

[1469] Example 1

[1470] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1471] With conventional data collection systems, it was difficult to efficiently collect and integrate data from various data sources. As a result, manual deduplication and correction of inaccurate data were required, reducing operational efficiency. Furthermore, operating machine learning algorithms for sales forecasting and report generation was time-consuming, and there was an issue of not being able to provide the latest forecast data or integrated information in real time. Furthermore, when personnel were changed, there was insufficient information handover to allow new personnel to quickly start work.

[1472] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1473] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and removing duplicate data, means for detecting and correcting incomplete or inaccurate data, means for generating sales forecasts using a machine learning algorithm, means for periodically training a model using past data, means for automatically generating reports based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new sales representative, means for displaying information in real time on a dashboard based on the collected data, and means for collecting email correspondence with business partners and storing it in a database. This allows for efficient collection and integration while maintaining data consistency, automatic generation of sales forecasts and reports, and smooth information transfer when sales representatives are changed.

[1474] "Various data sources" refers to different data providers such as mail servers, project management systems, order management systems, inventory management systems, and quotation management systems.

[1475] "Means of collecting data" refers to the methods and technologies that the server uses to connect to various data sources and obtain the required information.

[1476] A "unified format" refers to data obtained from different data sources converted into a common format or structure.

[1477] "Means of converting data into a unified format" refers to the methods and techniques used to convert collected data into a consistent format.

[1478] "Means of storing in a database" refers to the methods and techniques used to store the converted data in an organized manner and make it easily accessible.

[1479] "Means for integrating data and removing duplicate data" refers to methods and technologies for integrating data obtained from multiple data sources and deleting duplicate data when it exists multiple times, thereby consolidating it into one.

[1480] "Means for detecting and correcting incomplete or inaccurate data" refers to methods and techniques for detecting missing values ​​or erroneous information in data and correcting them to make them accurate.

[1481] A "machine learning algorithm" refers to an algorithm that trains a model based on past data and predicts future sales, etc.

[1482] "Means for generating sales forecasts" means methods or techniques for forecasting future sales using machine learning algorithms.

[1483] "Model training methods" refers to methods and techniques for using historical data to improve the performance of machine learning algorithms.

[1484] "Means for automated report generation" means methods or technologies for automatically generating periodic reports based on sales forecasts or consolidated data.

[1485] "Customer characteristic information" refers to important information related to commercial transactions, such as transaction history, response history, and business status.

[1486] "Means for automatically providing to a new person in charge" refers to a method or technology for automatically providing the necessary customer information to a new person in charge when the person in charge is changed.

[1487] "Means for displaying information on a dashboard in real time" refers to methods and technologies for instantly displaying collected data and forecast results on a user interface.

[1488] "Means of collecting email correspondence with business partners and storing it in a database" refers to methods and technologies for obtaining communication content with business partners from a mail server and storing it in a database.

[1489] The system of the present invention automates data collection, conversion, storage, integration, sales forecasting, report generation, and customer information handover. Specific embodiments of the system are described below.

[1490] Data collection and conversion into a unified format

[1491] The server periodically connects to various data sources (e.g., mail server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. A Python script is used to collect the data, and its periodic execution is managed by a Cron job. After collection, the server uses libraries such as Pandas and NumPy to convert the data obtained from each data source into a unified format.

[1492] Data storage

[1493] The server saves the converted data in a database such as PostgreSQL or MySQL. At this time, it connects to the database using SQLAlchemy and inserts the data into a table. During the data saving process, it performs transaction management and performs a rollback if an error occurs.

[1494] Data integration and cleaning

[1495] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and merge identical order information into a single record. It also detects incomplete or inaccurate data and corrects it by applying appropriate defaults or imputed data using OpenRefine and Pandas.

[1496] Generate sales forecasts

[1497] The server runs machine learning algorithms using Scikit-learn and TensorFlow to generate sales forecasts for the next month. Past sales data, current inventory data, and the latest order information are used to train the model. Hyperopt and GridSearchCV are also used to improve the accuracy of the forecast model.

[1498] Automated reporting

[1499] The server automatically generates daily, weekly, and monthly reports in Excel and PDF formats based on predefined report templates using openpyxl and xlsxwriter for Excel generation and ReportLab for PDF generation, and sends the generated reports via email to designated parties using an SMTP server.

[1500] Accumulation and utilization of customer information

[1501] The server continuously accumulates and centrally manages customer-specific information. This includes, for example, transaction history, response history, and business status. When a customer changes contact person, the server displays relevant information in real time on the dashboard when the new contact person logs in to the system, supporting a smooth transition. The dashboard was developed using Django and Flask on the backend and React and Vue.js on the frontend.

[1502] Specific examples

[1503] Example 1: Importing and merging order data

[1504] The user registers new order data in the order management system.

[1505] The server periodically collects new order data from the order management system, converts it into a unified format using Pandas, and stores it in the database.

[1506] The server compares the data with existing data and merges any duplicate order data.

[1507] Example 2: Generating and viewing a sales forecast

[1508] A user logs in to the dashboard and reviews the forecast for next month.

[1509] The server uses Scikit-learn to run a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1510] The server displays the generated sales forecast in a graphical format on a dashboard.

[1511] Example 3: Automatic report generation and distribution

[1512] The server automatically generates the previous month's sales report using openpyxl on the 1st of each month.

[1513] The server formats the report content based on a pre-configured template and sends it to the relevant parties via email using an SMTP server.

[1514] The user views the received report and makes minor corrections as necessary.

[1515] Example 4: Transferring customer information

[1516] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1517] When a new person logs into the system, the server displays important information on a dashboard using React.

[1518] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1519] Prompt Sentence Examples

[1520] Below are some example prompts to be input to the generative AI model:

[1521] This system implements programs that automate data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover. For example, new data is collected from an order management system, converted into a unified format, and stored in a database. Sales forecasts are then generated and can be viewed on a dashboard. This system uses software such as Scikit-learn, Pandas, Django, and React. Could you please tell me the detailed process flow?

[1522]

[1523] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1524] Step 1: Data collection

[1525] The server periodically connects to various data sources to collect new data. For example, it uses Python scripts and Cron jobs to collect emails from clients from the mail server and retrieves new case information from the case management system. In this process, it retrieves email data using the IMAP protocol and case data via the REST API.

[1526] The input is new data from various data sources and the output is the raw data captured on the server.

[1527] Specific behavior:

[1528] The server periodically connects to the mail server to retrieve new mail.

[1529] The server sends an HTTP request to the project management system's API to retrieve new project data.

[1530] Step 2: Convert the data format

[1531] The server converts the collected data into a unified format, using the Python Pandas library to convert CSV and JSON-formatted data into a DataFrame with consistent column names and data types.

[1532] The input is raw data and the output is data converted into a unified format.

[1533] Specific behavior:

[1534] The email data obtained by the server is read into a Pandas DataFrame and the column names are unified.

[1535] The server converts the job data from JSON format to a DataFrame and extracts the necessary information.

[1536] Step 3: Save your data

[1537] The server saves the converted data in a database (PostgreSQL or MySQL). It connects to the database using SQLAlchemy and inserts the data into a table. Transaction management allows for rollback if an error occurs.

[1538] The input is data converted into a unified format, and the output is data stored in a database.

[1539] Specific behavior:

[1540] The server uses the SQLAlchemy engine to connect to the database and saves the data according to the table structure.

[1541] The server begins a transaction and commits it if successful, or rolls it back if an error occurs.

[1542] Step 4: Integrate and clean the data

[1543] The server consolidates the stored data and removes duplicates. It uses Pandas to detect duplicates and fix problematic data.

[1544] The input is the data stored in the database, and the output is the cleaned and consolidated data.

[1545] Specific behavior:

[1546] The server retrieves data from the database and uses Pandas to detect duplicate records.

[1547] The server detects incomplete data and fills in appropriate defaults.

[1548] Step 5: Generate a sales forecast

[1549] The server generates sales forecasts using machine learning algorithms, such as Scikit-learn and TensorFlow, to generate a predictive model based on past sales data, current inventory data, and the latest order information.

[1550] The input is the cleaned integrated data and the output is the predicted sales data.

[1551] Specific behavior:

[1552] The server generates features based on past sales data and current data.

[1553] The server trains the machine learning model and generates sales forecasts.

[1554] Step 6: Reporting

[1555] The server automatically generates reports containing sales forecast results and other business insights. Openpyxl and ReportLab are used to create reports in Excel and PDF formats.

[1556] The inputs are the forecasted sales data and the consolidated data, and the output is the generated report.

[1557] Specific behavior:

[1558] The server generates the sales forecast results as an Excel file and inserts the necessary graphs and tables.

[1559] The server creates a report in PDF format and formats the content according to the specified format.

[1560] Step 7: Distributing the report

[1561] The server sends the generated report to the designated parties via email using an SMTP server.

[1562] The input is the report generated and the output is the report sent to the interested party.

[1563] Specific behavior:

[1564] The server connects to the SMTP server and creates a message containing the email body and any attachments.

[1565] The server sends the email and records the sending log.

[1566] Step 8: Accumulating and utilizing customer information

[1567] The server stores customer characteristics information and automatically provides it to new staff members. When a user logs in to the system, relevant information is displayed in real time on a dashboard.

[1568] The input is customer information and login information, and the output is the information displayed on the dashboard.

[1569] Specific behavior:

[1570] The server extracts customer information from a database and filters the information relevant to the logged-in user.

[1571] The server uses React to display information on a dashboard in real time.

[1572] (Application example 1)

[1573] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1574] In today's business environment, automating data collection, management, analysis, and report generation is a key challenge. Especially in fields that handle large volumes of data, such as online shopping sites, there is a need to check data consistency, forecast sales, generate reports, and consolidate customer information. However, performing these processes manually is extremely time-consuming and inefficient. Furthermore, when duplicate data or inaccuracies occur, the process of detecting and correcting them is complex. Furthermore, the lack of a way to check sales forecasts and report generation in real time makes it difficult to make quick decisions. Therefore, to solve these challenges, a system that automatically collects, consolidates, analyzes, forecasts, and generates reports is needed.

[1575] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1576] In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report based on a specified template, means for accumulating customer characteristic information and automatically providing it to a new person in charge, means for displaying the sales forecast in real time via a dashboard on a smartphone or tablet, and means for sending the report by email to relevant parties. This enables automatic collection, integration, analysis, prediction, and report generation of data.

[1577] "Various data sources" refers to different data sources such as a mail server, a case management system, an order management system, an inventory management system, and an estimate management system.

[1578] "Means of collecting data" refers to the function for periodically obtaining new data from various data sources.

[1579] "Means for converting into a unified format" refers to the ability to convert data of different formats or structures into a consistent format.

[1580] "Means for saving in a database" means a function for saving the converted data in a database for centralized management.

[1581] "Means for integrating data and removing duplicate data" means a function that combines identical data obtained from multiple data sources into a single record and eliminates duplication.

[1582] "Machine learning algorithm" refers to a computational model for making sales forecasts based on data.

[1583] "Means for generating sales forecasts" refers to the function of predicting sales based on past sales data, current order information, inventory data, etc.

[1584] "Means for automatically generating a report based on a specified template" means a function for automatically generating a report in accordance with a pre-set format.

[1585] "A means of accumulating customer-specific information and automatically providing it to new staff" refers to a function that continuously manages transaction history, response history, business status, etc., and makes it easy for new staff to access.

[1586] "A means of displaying sales forecasts in real time through a dashboard on a smartphone or tablet" means the ability to view sales forecasts through a dashboard on a mobile device.

[1587] "Means for sending reports to relevant parties by email" refers to a function that automatically sends generated reports to designated recipients by email.

[1588] The system for carrying out the present invention can efficiently collect data, automatically forecast sales, generate reports, and manage customer information on an online shopping site. A specific embodiment of the system will be described below.

[1589] Data collection and conversion into a unified format

[1590] The server periodically connects to various data sources (email server, project management system, order management system, inventory management system, quotation management system, etc.) to collect new data. For example, it retrieves new order information from the order management system and obtains email correspondence with business partners from the mail server. After collection, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[1591] Data storage and integration

[1592] The server stores the unified data in a database. After storing it, the server consolidates the data in the database and removes duplicates. For example, if the same order information comes from multiple sources, it merges them into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[1593] Generate sales forecasts

[1594] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information. To do this, it uses Python and the Scikit-learn library. The server also periodically trains the model to improve the accuracy of its predictions.

[1595] Automated reporting

[1596] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual sales, inventory status, and order status. The generated reports are then emailed to designated parties. For this purpose, the Smtplib library is used.

[1597] Accumulation and utilization of customer information

[1598] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new customer when the customer is replaced, and is displayed on the dashboard to support a smooth transition.

[1599] View sales forecasts on the dashboard and send reports

[1600] The application installed on a smartphone or tablet displays sales forecasts from the server in real time when the user logs in to the dashboard. The generated reports are automatically sent to the relevant parties via email. For example, the application displays the sales forecast for the next month and sends a monthly report via email.

[1601] Specific examples

[1602] For example, a user may log in to a dashboard on a smartphone app to check the sales forecast for the next month. The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate the sales forecast for the next month and displays it in graph form. The server also automatically generates a sales report for the previous month on the first day of each month, formats it based on a specified template, and sends it to relevant parties by email.

[1603] Prompt Sentence Examples

[1604] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[1605] This system enables automatic data collection, integration, analysis, prediction, and report generation, dramatically improving operational efficiency.

[1606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1607] Step 1:

[1608] The server periodically connects to various data sources (e.g., mail server, case management system, order management system, inventory management system, quotation management system, etc.) to collect new data. In this case, the server retrieves data obtained from each system (e.g., new order information from the order management system and email correspondence with business partners from the mail server), even if the data is in different formats and forms. The input is the raw data collected from different data sources, and the output is all the raw data collected.

[1609] Step 2:

[1610] The server converts the data collected from each data source into a unified format. During this process, the server converts data of different formats into a consistent format to maintain data integrity. For example, it converts data in XML format into JSON format and aligns the structure. This conversion process allows data from different data sources to be treated as consistent data. The input is raw data collected from various data sources, and the output is data converted into a unified format.

[1611] Step 3:

[1612] The server saves the data converted into a unified format in a database. In this step, the organized data is saved in a centrally managed database, allowing for efficient data access in subsequent processing. The input is the data converted into a unified format, and the output is the data saved in the database.

[1613] Step 4:

[1614] The server consolidates data in the database and removes duplicates. This process involves merging identical order information from multiple data sources into a single record. It also performs data cleaning processes to detect and correct incomplete or inaccurate data. For example, it detects and completes data with incomplete address information. The input is the data stored in the database, and the output is the consolidated data after duplicates have been removed.

[1615] Step 5:

[1616] The server runs a machine learning algorithm based on past data and current conditions to generate sales forecasts. This algorithm is implemented using Python and the Scikit-learn library, and calculates next month's sales forecasts using sales data from the past few years, current inventory status, and the latest order information. In addition, the server periodically performs model training to improve the accuracy of the forecasts. The inputs are past sales data, inventory information, and order information, and the output is next month's sales forecast data.

[1617] Step 6:

[1618] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The reports are sent by email to designated parties. This is implemented using the Smtplib library. The input is the sales forecast data and a report template, and the output is the generated report.

[1619] Step 7:

[1620] The server continuously accumulates and centrally manages customer characteristic information. This information includes, for example, transaction history, response history, and business status. When a person in charge is changed, this information is automatically provided to the new person in charge and displayed on a dashboard to support a smooth handover. The input is customer characteristic information, and the output is centrally managed customer information.

[1621] Step 8:

[1622] Users can log in to the application dashboard using a smartphone or tablet and check sales forecasts in real time from the server. The generated reports are automatically sent to relevant parties by email. The input is the user's login information and sales forecast data obtained from the server, and the output is sales forecast data displayed in real time.

[1623] Prompt Sentence Examples

[1624] "Please generate a sales forecast for next month. Please generate a forecast based on past sales data, current inventory status, and order information, and report the results to us."

[1625] In this way, automated data collection, integration, analysis, prediction, and report generation are facilitated, improving operational efficiency.

[1626] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1627] The system of the present invention aims to significantly improve business efficiency by automating data collection, conversion, storage, integration, sales forecasting, report creation, and customer information handover, and by combining it with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[1628] Data collection and conversion into a unified format

[1629] The server periodically connects to various data sources (email server, case management system, ERP system, etc.) to collect new data. For example, it retrieves client emails from the mail server and retrieves new case data from the case management system. After collecting the data, the server converts the data retrieved from each data source into a unified format. This allows data of different formats and structures to be processed consistently.

[1630] Data storage and integration

[1631] The server saves the unified data to the database, checking for consistency and integrity before inserting it. After saving, the server consolidates the data in the database and detects and removes duplicate data. For example, if the same order information comes from multiple data sources, it will be merged into a single record. The server also performs data cleaning processes to detect and correct incomplete or inaccurate data.

[1632] Generate sales forecasts

[1633] The server runs machine learning algorithms based on past data and current conditions to generate sales forecasts. The server periodically trains the model to improve the accuracy of the forecasts. For example, it calculates next month's sales forecast using sales data from the past few years, current inventory status, and the latest order information.

[1634] Automated reporting

[1635] The server automatically generates daily, weekly, and monthly reports based on predefined report templates. For example, a monthly report might include the current month's sales forecast, actual results, inventory status, and order status. The generated reports are then emailed to designated parties.

[1636] Accumulation and utilization of customer information

[1637] The server continuously accumulates and centrally manages customer-specific information, including transaction history, response history, and business status. This information is automatically provided to the new person in charge when the person in charge is changed. When a user logs into the system, the server displays relevant information in real time on the dashboard, supporting a smooth handover.

[1638] Introducing the Emotion Engine

[1639] The server uses an emotion engine to recognize the user's emotions and adjust the system's behavior accordingly. For example, if the user is feeling stressed, the server will change the content and color of the report to provide a more relaxing environment. It will also customize the report content based on the user's emotions to provide more accurate information.

[1640] Specific examples

[1641] Example 1: Importing and merging order data

[1642] The user registers new order data in the order management system.

[1643] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[1644] The server compares the data with existing data and merges any duplicate order data.

[1645] Example 2: Generating and viewing a sales forecast

[1646] A user logs in to the dashboard and reviews the forecast for next month.

[1647] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1648] The server displays the generated sales forecast in a graphical format on a dashboard.

[1649] Example 3: Automatic report generation and distribution

[1650] The server automatically generates a sales report for the previous month on the 1st of each month.

[1651] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[1652] The user views the received report and makes minor corrections as necessary.

[1653] Example 4: Transferring customer information

[1654] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1655] The server displays important information on a dashboard when a new person logs into the system.

[1656] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1657] Example 5: Using the Emotion Engine

[1658] A user logs into the system and the emotion engine analyzes the user's emotional state.

[1659] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[1660] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[1661] The system of this invention completely automates the previously difficult processes of data collection, integration, sales forecasting, report creation, and customer information handover, dramatically improving work efficiency. Furthermore, the introduction of an emotion engine enables flexible responses based on the user's emotional state, providing a more effective work environment.

[1662] The processing flow will be explained below.

[1663] Step 1:

[1664] The server connects to various data sources (e.g., email servers, case management systems, ERP systems, etc.) to collect new data. This process is scheduled periodically, for example, every day at 3:00 AM, and executes API calls and database queries to each data source to extract new data.

[1665] Step 2:

[1666] The server converts the collected data into a unified format, for example, converting date formats (such as YYYY / MM / DD or MM-DD-YYYY) obtained from different data sources into a unified format (e.g., YYYY-MM-DD), ensuring consistency in subsequent processing.

[1667] Step 3:

[1668] The server saves the data converted into a unified format into the database, while checking the consistency and integrity of the data during insertion. For example, it checks for duplicate records, and if any are found, it updates the existing data or ignores them.

[1669] Step 4:

[1670] The server consolidates data in the database, detects and removes duplicates (for example, if the same order information comes from multiple data sources, it consolidates them into a single record), and performs checks to ensure data consistency.

[1671] Step 5:

[1672] The server runs data cleaning processes to detect and correct incomplete or inaccurate data, for example by filling in missing customer IDs or incomplete address information with other information to improve consistency.

[1673] Step 6:

[1674] The server uses a machine learning algorithm to train a sales forecasting model based on past data. This model is periodically updated to improve forecast accuracy. For example, at the beginning of each month, the model is retrained using sales data from the past year.

[1675] Step 7:

[1676] The server applies the sales forecasting model to new data as input to predict future sales. For example, it calculates the sales forecast for the next month and saves the results in a database, allowing access to the latest forecast data.

[1677] Step 8:

[1678] The server automatically generates reports based on predefined report templates. For example, a monthly report might include sales forecasts, actual results, inventory status, and order status. The generated reports are saved in formats such as PDF.

[1679] Step 9:

[1680] The server automatically emails the generated report to designated parties based on a pre-defined schedule, with the report being sent at the specified time.

[1681] Step 10:

[1682] The server stores customer characteristics and automatically provides them to new staff members. For example, when a staff member logs in to the system, relevant customer information is displayed on the dashboard. This information includes transaction history and correspondence history.

[1683] Step 11:

[1684] The server uses an emotion engine to recognize the user's emotions. For example, it analyzes the user's input patterns and voice data to recognize emotions. Based on the analysis results, it determines the user's emotional state.

[1685] Step 12:

[1686] The server adjusts the system's behavior based on the analyzed emotional data. For example, if the user is feeling stressed, the content and color of the dashboard display will be changed to provide a more relaxing environment. This content adjustment is done in real time.

[1687] Step 13:

[1688] The server customizes the report content based on the user's emotions. For example, if the user is feeling stressed, the server will highlight important information in the report to make it easier to understand. It also omits unnecessary information to reduce the user's burden.

[1689] Step 14:

[1690] Before the login session ends, the server re-analyzes the user's emotional data to see if there has been any improvement. The server records the analysis of the user's emotional state and uses it as reference information for the next login. This information is also used for subsequent analyses.

[1691] Specific examples

[1692] Example 1: Importing and merging order data

[1693] The user registers new order data in the order management system.

[1694] The server periodically collects new order data from the order management system, converts it into a unified format, and stores it in a database.

[1695] The server compares the data with existing data and merges any duplicate order data.

[1696] Example 2: Generating and viewing a sales forecast

[1697] A user logs in to the dashboard and reviews the forecast for next month.

[1698] The server runs a machine learning algorithm based on past sales data and current order and inventory data to generate a sales forecast for the next month.

[1699] The server displays the generated sales forecast in a graphical format on a dashboard.

[1700] Example 3: Automatic report generation and distribution

[1701] The server automatically generates a sales report for the previous month on the 1st of each month.

[1702] The server formats the report content based on a pre-defined template and sends it to the relevant parties via email.

[1703] The user views the received report and makes minor corrections as necessary.

[1704] Example 4: Transferring customer information

[1705] The server extracts information about the client to whom the new contact person has been assigned from the centralized database.

[1706] The server displays important information on a dashboard when a new person logs into the system.

[1707] Users can check the information displayed on the dashboard and get to work quickly, eliminating the need for additional inquiries or research.

[1708] Example 5: Using the Emotion Engine

[1709] A user logs into the system and the emotion engine analyzes the user's emotional state.

[1710] The server adjusts the dashboard display content and colors based on the analysis results. For example, if a user feels stressed, the colors will be changed to a more calming tone, providing a more relaxing environment.

[1711] The server automatically generates a customized report according to the user's emotions and distributes it to the relevant parties.

[1712] Example 2

[1713] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1714] Collecting, managing, and analyzing large amounts of data in business is generally done manually, requiring a great deal of effort and time. Furthermore, there is a demand for improved data consistency and accuracy, more accurate sales forecasts, automated report creation, and flexible responses based on emotional states. However, achieving all of these simultaneously has been difficult with conventional technology. This has led to issues such as a lack of improved business efficiency and the immediacy of information transmission.

[1715] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from various data sources, means for converting the collected data into a unified format, means for storing the data converted into the unified format in a database, means for integrating data in the database and deleting duplicate data, means for generating a sales forecast using a machine learning algorithm, means for automatically generating a report according to a specified template based on the sales forecast, order status, etc., means for accumulating customer characteristic information and automatically providing it to a new sales representative, and means for analyzing user emotions using an emotion engine and adjusting system operation. This enables improved data consistency and accuracy, improved sales forecast accuracy, automated report creation, and flexible response based on emotional states.

[1716] A "data source" is...

Claims

1. a means of collecting data from various data sources; A means of converting the collected data into a unified format; a means for storing the data converted into the unified format in a database; A means of consolidating data in the database and removing duplicate data; a means for generating a sales forecast using a machine learning algorithm; A means to automatically generate reports based on specified templates; A means to accumulate customer characteristic information and automatically provide it to new staff members, A system including:

2. 2. The system of claim 1, wherein the means for removing duplicate data includes means for detecting and correcting incomplete or inaccurate data.

3. 2. The system of claim 1, wherein the means for generating a sales forecast using a machine learning algorithm includes means for periodically training the model using previously collected data.

Images