System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving input of a target company and a period from a user; means for collecting data related to the target company and the period from a database; means for preprocessing the collected data; means for analyzing the preprocessed data; means for visualizing data based on an analysis result; means for automatically generating a business negotiation material using the visualized data; and means for providing the automatically generated business negotiation material to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] Sales departments and management teams face the problem of requiring a great deal of time and effort when creating sales documents. This is particularly true because a series of manual tasks, including data collection, preprocessing, analysis, visualization, and report creation, is inefficient and makes it difficult to maintain the accuracy and consistency of information. Furthermore, if sales documents are not provided in a timely manner, this can lead to delayed decision-making and lost business opportunities. It is necessary to resolve this situation and improve the efficiency and quality of sales document creation. [Means for solving the problem]

[0005] The present invention provides a system including a means for accepting input of target companies and time periods from a user, a means for collecting data related to the target companies and time periods from a database, a means for preprocessing the collected data, a means for analyzing the preprocessed data, a means for visualizing the data based on the analysis results, a means for automatically generating sales negotiation materials using the visualized data, and a means for providing the automatically generated sales negotiation materials to a user. This automates the entire sales negotiation material creation process, enabling efficient and accurate sales negotiation materials to be quickly created and provided. The collected data includes data from a customer management system, a sales management system, and an enterprise resource planning system. Preprocessing involves data cleansing, missing value imputation, and data normalization, resulting in high-quality analysis results.

[0006] A "user" is a person in charge within a company who operates the system to request the creation of business negotiation materials.

[0007] "Target company" refers to a specific company that is the subject of analysis when preparing business documents.

[0008] The "period" refers to the range of time to be analyzed when creating business documents.

[0009] "Database" refers to a system that continuously accumulates and manages information, such as a customer management system, sales management system, and enterprise resource planning system.

[0010] "Means for collection" refers to a component that has the function of automatically extracting and collecting the necessary information from a database.

[0011] "Preprocessing means" refers to a component that has the functions of data cleansing, missing value completion, and data normalization to prepare collected data in a format suitable for analysis.

[0012] "Means of analysis" refers to a component that has the function of performing statistical analysis and trend analysis based on preprocessed data to calculate the results and trends of sales negotiations.

[0013] "Visualization means" refers to a component that has the function of converting and displaying analysis results in a visual format such as a graph or chart.

[0014] "Means for automatic generation" refers to a component that has the function of automatically creating sales documents in a specified format (e.g., PowerPoint, PDF) based on visualized data and analysis results.

[0015] "Means of providing" refers to a component that has the function of distributing and transmitting the generated business documents so that users can easily access and obtain them.

[0016] A "customer management system" refers to a software system for managing customer information and sales activity information.

[0017] A "sales management system" refers to a software system for managing and analyzing sales processes and sales negotiation information.

[0018] An "enterprise resource planning system" refers to a software system for efficiently planning and managing resources within a company.

[0019] "Data cleansing" refers to the process of removing inconsistencies and duplication from data and improving its accuracy.

[0020] "Missing value imputation" refers to the process of filling in missing data using statistical methods or other methods to complete a dataset.

[0021] "Data normalization" refers to the process of converting data into a unified format and making it suitable for analysis. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The present invention relates to a system for automatically generating business negotiation materials, and a specific implementation method thereof will be described in detail.

[0044] The system consists of a terminal operated by the user, a server that executes the processing, and a database required to create business negotiation materials.

[0045] First, a user logs in to the system using a terminal and specifies the target companies and target period for which business negotiation materials are to be created. The terminal then transmits this specified information to the server.

[0046] The server collects the necessary data from databases based on the received information on the target company and target period. The databases include customer relationship management (CRM), sales management systems, and enterprise resource planning (ERP) systems. This allows the collection of past sales negotiation data, sales data, customer information, product information, and more.

[0047] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0048] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[0049] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[0050] The server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualized data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. This makes the documents consistent and easier to understand.

[0051] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[0052] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system. It will then perform data cleansing and fill in missing values, calculate the success rate of sales negotiations and average order amount, and graph past sales negotiation trends. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[0053] In this way, the present invention realizes improved efficiency and quality in creating business negotiation materials.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The user logs in to the system using a terminal and requests the creation of business negotiation materials. The user inputs the name of the target company and the target period.

[0057] Step 2:

[0058] The terminal transmits the input information on the target company and target period to the server.

[0059] Step 3:

[0060] The server analyzes the received request and identifies the required data.

[0061] Step 4:

[0062] The server collects data related to the target company and the target period from databases such as a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP).

[0063] Step 5:

[0064] The server performs data cleansing on the collected data, which includes removing inconsistent and duplicate data.

[0065] Step 6:

[0066] The server imputes missing data values. Missing values ​​are imputed using averages or predicted values.

[0067] Step 7:

[0068] The server performs data normalization, so that the data is in a uniform format.

[0069] Step 8:

[0070] The server calculates KPIs such as the success rate of sales negotiations and the average order amount based on the pre-processed data.

[0071] Step 9:

[0072] The server performs time series analysis based on past sales negotiation data and extracts trends.

[0073] Step 10:

[0074] The server then creates visualizations of the data based on the analysis results, which may include generating line graphs, bar graphs, pie charts, etc.

[0075] Step 11:

[0076] The server automatically generates a draft of the sales documents based on the visualized data, and the report is created in PowerPoint or PDF format.

[0077] Step 12:

[0078] The server provides the generated sales negotiation materials as a link that the user can download.

[0079] Step 13:

[0080] The user accesses the provided link through the terminal and downloads or checks the business documents.

[0081] Through the above processing flow, negotiation materials are automatically generated efficiently and quickly provided to the user.

[0082] Example 1

[0083] 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."

[0084] Creating sales documents requires a great deal of time and effort, and because the data collection, preprocessing, analysis, and visualization processes are particularly complex, a system that can perform this work quickly and accurately is needed. Furthermore, there is the problem of integrating data collected from different data sources and resolving inconsistencies, which requires a lot of time and effort.

[0085] 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.

[0086] In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for cleansing the collected data, correcting inconsistent data, and filling in missing data values, means for calculating negotiation success rates, average order amounts, customer behavior patterns, etc. using the preprocessed data, means for generating line graphs, bar graphs, pie charts, heat maps, etc. based on the calculation results and visualizing the data, means for automatically generating negotiation materials using the visualized data and exporting them in a specified format, and means for providing the automatically generated negotiation materials to the user. This enables the rapid and accurate creation of negotiation materials.

[0087] A "user" is an individual or group that operates the system and instructs the creation of business negotiation materials.

[0088] "Target company" refers to the company for which business negotiation materials are to be created.

[0089] The "target period" is a specific time range related to the creation of the sales negotiation materials.

[0090] A "database" is an information management system that systematically stores information and makes it accessible as needed.

[0091] "Cleansing" is the process of de-duplication of data, correcting inconsistent data, and filling in missing values.

[0092] The "success rate of business negotiations" is an indicator that indicates the percentage of successful business negotiations within a certain period of time.

[0093] "Average order amount" is the average order amount in business negotiations.

[0094] "Customer behavior patterns" are behavioral data such as purchases and inquiries that a customer exhibits within a specific time range.

[0095] A "line graph" is a graph in which data points are connected by straight lines, and is used to visually represent changes and trends over time.

[0096] A "bar graph" is a graph in which different categories of data are represented by the length of the bars.

[0097] A "pie chart" is a graph in which segments of a circle represent proportions of a whole.

[0098] A "heat map" is a visual representation of data values ​​using shades or hues of color.

[0099] "Business negotiation materials" are documents that record the progress and results of business negotiations and include analysis results and graphs.

[0100] "Export" is the act of outputting a generated document in a particular format.

[0101] This invention relates to a system that is comprised of a terminal operated by a user, a server that executes processing, and a database required for creating negotiation materials, and also to a method for automatically generating negotiation materials. A specific implementation method will now be described in detail.

[0102] First, the user logs in to the system using a terminal and specifies the target company and target period for creating business negotiation materials. The terminal then sends this specified information to the server. For example, if the user specifies "Company XYZ" and the period "Q1 2023," the terminal sends this as an HTTP request to the server.

[0103] Based on the received information on the target company and target period, the server collects the necessary data from databases, including customer relationship management (CRM), sales management, and enterprise resource planning (ERP) systems. The server uses a database connection pool to issue queries to these systems and collect past sales data, sales data, customer information, product information, and other information related to the target company.

[0104] The server then preprocesses the collected data, using a data cleansing tool (e.g., OpenRefine) to remove duplicates and correct inconsistent data, as well as to impute missing values ​​and normalize the data to prepare it for analysis.

[0105] Once preprocessing is complete, the server performs data analysis. Specifically, it uses data analysis libraries (e.g., Pandas and NumPy) to calculate KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns. It also performs trend analysis based on past sales negotiation data to analyze trends in success rates and seasonal fluctuations in sales.

[0106] Based on the analysis results, the server visualizes the data using visualization libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc., which facilitates visual understanding of the data.

[0107] Next, the server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. It uses Python libraries (e.g., ReportLab and pptx) to assemble the sales documents and generate documents containing the necessary information and comments.

[0108] Finally, the server provides the automatically generated business documents to the user. The server uploads the generated documents to cloud storage and generates a download link. The server sends this link to the user's device or automatically sends the documents to a specified email address as needed. The user can view, download, or print the documents through the provided link.

[0109] As a concrete example, consider the case where the user specifies the target company "XYZ Company" and the period "Q1 2023." The server collects data related to "XYZ Company" from the CRM system and ERP system, performs data cleansing, and fills in missing values. It calculates the success rate of sales negotiations and average order amount, and creates graphs of past sales negotiation trends. Finally, it automatically generates sales negotiation materials in PDF format containing these analysis results and graphs, and provides them to the user.

[0110] An example of a prompt to enter is:

[0111] "When specifying the target company and period, please collect data from CRM and ERP and automatically generate sales negotiation materials. As a specific example, let's say the target company is "XYZ Company" and the period is "Q1 2023." Please cleanse the obtained data, calculate the success rate of sales negotiations and average order amount, and generate line graphs and bar graphs. Output the final sales negotiation materials in PDF format and provide them to the user."

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1:

[0114] The user logs into the system using a terminal. The user then enters the target company "XYZ Corporation" and the target period "Q1 2023" and presses the submit button. The terminal sends this information to the server as an HTTP request. The input includes the target company and period information, and the output passes this information to the server.

[0115] Specific operation: The user enters "XYZ Company" and "Q1 2023" into the form on the terminal and clicks the "Submit" button. The terminal sends this as an HTTP request in JSON format to the server.

[0116] Step 2:

[0117] The server accesses the database and collects the necessary data based on the target company and target period information received from the user. The input is the target company and period information, and the output is the data retrieved from the database. The server issues queries to the CRM system and ERP system to collect the corresponding data.

[0118] What happens: The server uses the database connection pool to access the CRM and ERP API endpoints, and queries to retrieve data related to "Company XYZ" and "Q1 2023."

[0119] Step 3:

[0120] The server preprocesses the collected data. The collected data may contain duplicates and inconsistencies, so cleansing is necessary. The input is raw data, and the output is cleansed data. Specifically, a data cleansing tool (e.g., OpenRefine) is used to remove duplicates, correct inconsistencies, and complete missing values.

[0121] What it does: The server uses OpenRefine to detect and remove duplicate data, correct inconsistent data, and impute missing values ​​with the mean or median.

[0122] Step 4:

[0123] The server performs data analysis using the preprocessed data. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses a data analysis library (e.g., Pandas or NumPy) to calculate the success rate of sales negotiations, average order amount, and customer behavior patterns.

[0124] What it does: Uses Pandas and NumPy to calculate aggregates, averages, and summary statistics for a dataset. Calculates win rates, average order value, and customer behavior patterns.

[0125] Step 5:

[0126] The server visualizes the analysis results. The input is the analysis results, and the output is visualized data (graphs, charts). This is done using libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc.

[0127] Specific operations: Using Matplotlib and Seaborn, the progress of sales success rates is visualized as a line graph, seasonal fluctuations in sales as a bar graph, and customer behavior patterns as pie charts and heat maps.

[0128] Step 6:

[0129] The server automatically generates sales documents based on the visualized data. The input is the visualized data and a prompt from the AI ​​model, and the output is sales documents in the specified format (e.g., PowerPoint, PDF). The documents are generated using Python libraries (e.g., ReportLab or pptx).

[0130] What it does: The server uses the ReportLab and pptx libraries to automatically generate a sales presentation, which includes analysis results, graphs, and automatically generated comments.

[0131] Step 7:

[0132] The server generates a download link for the automatically generated business documents and sends it to the user's device. The input is the generated business documents, and the output is a download link or email. The user receives this and downloads or prints the documents.

[0133] Specific operation: The server uploads the generated sales documents to cloud storage and generates a download link. The link is sent to the user via email. The user clicks the link to download the documents.

[0134] (Application example 1)

[0135] 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."

[0136] Logistics centers handle many types of data and are required to quickly organize and analyze it and provide appropriate reports to relevant parties. However, performing the entire process of data collection, preprocessing, analysis, visualization, and report creation manually is time-consuming and prone to errors. It is also important to report the analysis results in a visually easy-to-understand format, but this is also time-consuming. As such, there is a need to solve the issues of efficient and accurate data processing and report creation.

[0137] 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.

[0138] In this invention, the server includes: means for accepting input of a target company and a period from a user; means for collecting data related to the target company and the period from a database; means for preprocessing the collected data; means for analyzing the preprocessed data; means for visualizing data based on the analysis results; means for automatically generating business reports using the visualized data; means for providing the automatically generated business reports to a user; means for generating a link for displaying the generated reports and sending it to a user terminal; means for sending the reports by email as needed; and means for the reports to include inventory turnover, delivery time, and pick rate. This automates data processing and report generation at a logistics center, enabling efficient and accurate business operations.

[0139] "User terminal" means a device used by a user to view and manipulate commercial reporting materials, including a smartphone, tablet, smart glasses, etc.

[0140] "Target company" refers to the company that is the subject of data analysis and report creation for the invention.

[0141] "Time period" refers to a specific time range for data collection, analysis, and reporting.

[0142] A "database" is a system for storing data, which is composed of a customer management system, a transportation management system, an enterprise resource planning system, and the like.

[0143] "Preprocessing" refers to the process of removing duplicates, filling in missing values, and normalizing the collected data.

[0144] "Analysis" refers to the process of calculating specific indicators (KPIs) based on preprocessed data and interpreting the data based on them.

[0145] "Visualization" refers to the process of converting analytical results into a visually understandable format such as a line graph, bar graph, pie chart, or heat map.

[0146] "Commercial reporting materials" are reports containing data analysis results for the target company and period, and are provided in formats such as PDF or PowerPoint.

[0147] "Displayable link" refers to a link sent to a user's device that the user can access to view and download the report materials.

[0148] "Inventory turnover rate" refers to an indicator that shows the speed at which inventory is replaced at a logistics center.

[0149] "Delivery time" refers to an indicator that measures the time from when an order is received to when the product is delivered.

[0150] "Pick rate" refers to an indicator that indicates the frequency with which products are accurately picked up at a logistics center.

[0151] This invention relates to a system for automating data processing and report creation in a logistics center. The system is composed of a user terminal, a server that executes processing, and a database.

[0152] First, the user logs into the system using a terminal and specifies the target company and target period. The specified information is sent from the terminal to the server. Based on this information, the server collects the necessary data from the database. The database includes a customer relationship management system (CRM), a transportation management system (TMS), and an enterprise resource planning system (ERP). This allows the collection of past logistics data, delivery data, customer information, inventory information, and more.

[0153] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0154] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as inventory turnover, average delivery time, and pick rate, and performs trend analysis based on past logistics data. This allows the operational status of the logistics center and areas for improvement to be identified.

[0155] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data. Using this visualized data, a draft of the business report is created. Based on the visualized data, the server automatically generates the business report in the specified format (e.g., PowerPoint, PDF).

[0156] The automatically generated commercial report is generated as a displayable link and sent to the user's device. The user can view, download, or print the commercial report via the provided link. The system also has a function to automatically send the report to a specified email address, if necessary.

[0157] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past logistics and delivery data related to "XYZ Company" from the CRM system, TMS, and ERP system. It will then perform data cleansing and fill in missing values, calculate inventory turnover and average delivery time, and graph past logistics trends. Finally, it will automatically generate a business report containing these analysis results and graphs and provide it to the user.

[0158] Example prompt sentence:

[0159] Target company: “XYZ Company”

[0160] Target period: "Q1 2023"

[0161] Collected data: CRM data, TMS data, ERP data

[0162] Essential KPIs: Inventory turnover, delivery time, pick rate

[0163] Report format: PDF

[0164] In this way, the present invention improves the efficiency and quality of data processing and report generation in a logistics center.

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The system accepts input of target companies and periods from the user. The user logs into the system using a terminal and inputs the target company (e.g., "XYZ Company") and target period (e.g., "Q1 2023"). The terminal sends this specified information to the server. The input is received as manual data from the user, and the output is the specified information for the target company and period.

[0168] Step 2:

[0169] Data related to the target company and period is collected from the database. Based on the received information on the target company and period, the server collects the necessary data from the CRM system, TMS, and ERP system. This includes past logistics data, delivery data, customer information, inventory information, etc. The input is the specified information on the target company and period, and the output is the collected data from each system.

[0170] Step 3:

[0171] The collected data is preprocessed. The server cleanses the data, removes duplicates and inconsistencies, and imputes missing values. It also normalizes the data and prepares it in a format suitable for analysis. The input is the collected data, and the output is the cleansed and normalized data.

[0172] Step 4:

[0173] The preprocessed data is analyzed. The server calculates KPIs such as inventory turnover, delivery time, and pick rate based on the cleansed and normalized data. It also performs trend analysis based on past logistics data. The input is the preprocessed data, and the output is the results of various KPIs and trend analysis.

[0174] Step 5:

[0175] The server visualizes the data based on the analysis results. The server visually represents the analysis results in the form of line graphs, bar graphs, pie charts, heat maps, etc. This makes it easier to understand the data. The input is the analysis results, and the output is the generated graphs and charts.

[0176] Step 6:

[0177] The visualized data is used to automatically generate business reports. The server generates business reports in a specified format (e.g., PDF, PowerPoint) based on the visualized data. The input is the visualized data, and the output is the business report.

[0178] Step 7:

[0179] Automatically generated commercial report materials are provided to users. The server sends the generated report materials to the user's terminal as a displayable link. The user can check the report materials via this link and download or print them. In addition, a function is provided to automatically send the materials to a specified email address, if necessary. The input is the generated report materials, and the output is a link that can be viewed on the user's terminal or an automatically sent email.

[0180] 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.

[0181] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[0182] The system consists of a terminal operated by the user, a server that processes various data, and a database. An emotion engine is also built into the terminal and server.

[0183] First, the user logs into the system using a terminal and requests the creation of business documents. The user inputs the name of the target company and the target period. At this time, the emotion engine recognizes the user's emotions in real time. The emotion engine can grasp the user's emotional state by analyzing the user's facial expressions, tone of voice, and the content of the input text.

[0184] The terminal sends the user's emotional information along with the input information to the server. The server then collects the necessary data from a database based on the received information on the target company and target period. The database includes a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP), which collects past sales negotiation data, sales data, customer information, product information, and other data.

[0185] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0186] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[0187] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[0188] The server automatically generates sales documents in the specified format (e.g., PowerPoint or PDF) based on the visualization data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. The emotion engine dynamically adjusts the content and design of the documents according to the user's emotional state. For example, if the user is feeling stressed, the system will generate documents that are simpler and easier to read.

[0189] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[0190] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023" and the emotion engine detects the user's tension, the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system, perform data cleansing, and calculate the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it will generate simple, visually easy-to-understand materials that will reduce stress. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[0191] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[0192] The processing flow will be explained below.

[0193] Step 1:

[0194] The user logs into the system using a terminal and requests the creation of business documents. The user enters the name of the target company and the target period. At this time, the emotion engine analyzes the user's facial expressions, tone of voice, and text input in real time through the terminal's built-in camera, microphone, and keyboard input, and recognizes the user's emotions.

[0195] Step 2:

[0196] The terminal transmits the recognized emotion information of the user to the server together with the input information on the target company and target period.

[0197] Step 3:

[0198] The server analyzes the received request and identifies the required data relating to the target company and time period.

[0199] Step 4:

[0200] The server accesses each database (customer management system, sales management system, enterprise resource planning system) and collects data related to the specified target company and target period.

[0201] Step 5:

[0202] After collecting the data, the server performs data cleansing, which includes removing duplicate data and correcting inconsistent data.

[0203] Step 6:

[0204] The server completes the missing values ​​in the collected data by predicting and completing the missing values ​​using statistical methods and machine learning algorithms.

[0205] Step 7:

[0206] Once the data is cleaned, the server normalizes it, unifying data in different formats and making it suitable for analysis.

[0207] Step 8:

[0208] The server uses the pre-processed data to perform data analysis, specifically calculating important KPIs such as success rate, average order value, and customer behavior patterns.

[0209] Step 9:

[0210] The server performs time-series analysis based on past sales negotiation data to extract trends, allowing analysis of sales negotiation history with target companies and seasonal fluctuations in sales.

[0211] Step 10:

[0212] The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data.

[0213] Step 11:

[0214] The server automatically generates a draft of a sales document based on the visualized data. The content and format of the document are dynamically adjusted based on the user's emotional data collected by the emotion engine. For example, if the user is nervous, the structure of the document is simplified and visually intuitive elements are enhanced.

[0215] Step 12:

[0216] The server provides the user with automatically generated business documents in a specified format (e.g., PowerPoint, PDF) and sends them to the user's device as a trusted link.

[0217] Step 13:

[0218] Users can view the sales documents through the provided link and download, print, or email them. By viewing the documents generated by the emotion engine, users can reduce stress and tension, increasing the success rate of sales negotiations.

[0219] Through the above processing flow, business negotiation materials are automatically generated efficiently and are provided in a form that takes into consideration the user's feelings.

[0220] Example 2

[0221] 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."

[0222] Conventional sales document creation systems require users to input data on target companies and time periods, and then automatically generate documents based on that data. However, they were unable to consider the user's emotional state. This meant that they lacked the flexibility to adjust the content and format of the documents depending on the user's emotional state. Furthermore, there was a problem with the design of sales documents being inappropriate when the user was emotionally stressed.

[0223] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for preprocessing the collected data, means for analyzing the preprocessed data, means for visualizing data based on the analysis results, means for automatically generating negotiation materials using the visualized data, means for recognizing the user's emotions, means for dynamically adjusting the content and format of the negotiation materials based on the user's emotional information, and means for providing the automatically generated negotiation materials to the user. This enables flexible and efficient creation of negotiation materials that take the user's emotional state into consideration.

[0224] "User" refers to a person who accesses and operates the system.

[0225] "Terminal" refers to a device such as a computer or smartphone that is operated by a user.

[0226] A "server" refers to a computer system that processes requests from multiple terminals and performs data collection, analysis, document generation, etc.

[0227] The term "target company" refers to a specific company that the user designates in order to create business negotiation materials.

[0228] "Period" refers to a specific time range for extracting data necessary for creating sales documents.

[0229] A "database" is a system for storing information, and includes customer management systems, sales management systems, enterprise resource planning systems, and the like.

[0230] An "emotion engine" refers to a system that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, and input text.

[0231] "Data cleansing" refers to the process of removing duplicates and inconsistencies in data and filling in missing values.

[0232] "Data normalization" refers to the process of organizing data based on certain rules and making it consistent.

[0233] "KPI" stands for Key Performance Indicator and refers to key indicators such as success rate of sales negotiations, average order amount, and customer behavior patterns.

[0234] "Visualization" refers to converting the results of data analysis into a visually easy-to-understand format (e.g., graphs, charts).

[0235] "Business negotiation materials" refers to materials that are automatically generated based on collected and analyzed data and are used in business negotiations.

[0236] A "prompt sentence" refers to an instruction sentence input to a generative AI model.

[0237] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[0238] System Configuration

[0239] Terminal: A device operated by a user, such as a computer or smartphone.

[0240] Server: A computer system that processes, analyzes, and generates various data.

[0241] Database: Data storage consisting of customer relationship management (CRM), sales management, enterprise resource planning (ERP), etc.

[0242] Emotion engine: Software that analyzes a user's facial expressions, tone of voice, and input text to recognize emotions.

[0243] Program processing flow

[0244] 1. A user operates a terminal and logs in to the system:

[0245] A user accesses the system at a terminal and authenticates by entering a username and password.

[0246] If authentication is successful, the user can access the main screen of the system.

[0247] 2. User enters target information:

[0248] The user fills in the required data in a form to input the name of the target company and the period.

[0249] 3. Emotion Recognition with Emotion Engine:

[0250] The device's built-in emotion engine analyzes the user's facial expressions, tone of voice, and input text to grasp their emotional state in real time.

[0251] The analysis results are output as a probability-based emotional state (tension, joy, stress, etc.).

[0252] 4. Data transmission:

[0253] The terminal generates a data packet containing the target company name, period, and emotion information and transmits it to the server.

[0254] 5. Data Collection:

[0255] Based on the received company name and period information, the server collects relevant data from databases such as customer relationship management (CRM), sales management systems, and enterprise resource planning systems (ERP).

[0256] 6. Data Preprocessing:

[0257] The server cleanses the collected data, removing duplicates and inconsistencies and filling in missing data.

[0258] Normalize the data into a format suitable for analysis.

[0259] 7. Data Analysis:

[0260] Based on the pre-processed data, the server calculates key performance indicators (KPIs) such as success rate, average order amount, and customer behavior patterns.

[0261] Conduct trend analysis to understand seasonal fluctuations and sales history.

[0262] 8. Data Visualization:

[0263] The server visualizes the analysis results in a visually easy-to-understand format (line graphs, bar graphs, pie charts, heat maps, etc.).

[0264] 9. Automatic generation of sales documents:

[0265] The server generates business documents in a specified format (e.g., PowerPoint, PDF) based on the visualized data.

[0266] The content and design of materials are dynamically adjusted based on information from the emotion engine. For example, if a user is feeling stressed, simple, visually easy-to-understand materials are provided.

[0267] 10. Provision of business materials:

[0268] The server generates a downloadable link for the generated business negotiation materials and transmits the link to the user's terminal.

[0269] If necessary, the system also has the function to automatically send documents to a specified email address.

[0270] Specific examples

[0271] When a user specifies the target company "Company A" and the period "Q1 2023" and the emotion engine detects the user's tension, the server collects past sales negotiation data and sales data related to "Company A" from the CRM system and ERP system, cleans the data, and calculates the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it generates simple, visually easy-to-understand materials that reduce stress. Finally, it automatically generates sales negotiation materials including these analysis results and graphs and provides them to the user.

[0272] Prompt Sentence Examples

[0273] "Please create a sales document for Company A for the period Q1 2023. Because users are feeling nervous, please create a simple and visually easy-to-understand format."

[0274] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[0275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0276] Step 1: User login and input of target information

[0277] Specific operation: The user accesses the system login screen using a terminal and enters the username and password. After successful authentication, the system's main screen is displayed.

[0278] Input: Username, Password

[0279] Output: Main screen if login is successful, authentication error message if unsuccessful

[0280] Step 2: Enter the target company and period

[0281] Specific operation: The user enters the name of the target company and the period, then submits the input form. The entered information is temporarily saved on the device.

[0282] Input: Target company name, period

[0283] Output: A data packet containing the target company name and time period

[0284] Step 3: Emotion Recognition

[0285] How it works: The emotion engine analyzes the user's facial expressions, tone of voice, and input text in real time, and outputs a probability-based emotional state. The analysis results are stored on the device.

[0286] Input: User facial expressions, tone of voice, input text

[0287] Output: Emotional state (e.g., nervous, happy, stressed, etc.)

[0288] Step 4: Send data

[0289] Specific operation: The device generates a data packet containing the target company name, period, and emotion information and sends it to the server.

[0290] Input: Target company name, period, sentiment information

[0291] Output: Data packet sent to the server

[0292] Step 5: Data collection

[0293] Specific operation: The server receives the data packet and extracts the necessary data from the database (CRM, sales management system, ERP, etc.) based on the target company name and period.

[0294] Input: Target company name, period

[0295] Output: Collected sales opportunity data, sales data, and customer information

[0296] Step 6: Data Preprocessing

[0297] What it does: It cleanses the data collected by the server, removing duplicates and inconsistencies, filling in missing data, and normalizing the data into a format suitable for analysis.

[0298] Input: Collected data

[0299] Output: Cleansed and normalized data

[0300] Step 7: Data analysis

[0301] Specific operation: The server uses the preprocessed data to calculate KPIs such as success rate, average order amount, and customer behavior patterns, and performs trend analysis.

[0302] Input: Normalized data

[0303] Output: Analysis results (sales success rate, average order amount, trend data, etc.)

[0304] Step 8: Data Visualization

[0305] Specific operation: The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, etc.

[0306] Input: Analysis results

[0307] Output: Visualized data (graphs and charts)

[0308] Step 9: Auto-generate sales documents

[0309] Specific operation: The server generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. The design and content of the documents are dynamically adjusted based on the information from the emotion engine.

[0310] Input: Visualization data, emotion information

[0311] Output: Auto-generated sales documents

[0312] Step 10: Provide sales materials

[0313] Specific operation: The server generates a downloadable link for the generated sales documents and sends this link to the user's device. If necessary, the server also sends the documents to the email address specified by the user.

[0314] Input: Auto-generated sales document

[0315] Output: Download link, email to be sent

[0316] (Application example 2)

[0317] 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."

[0318] Creating reports on equipment operation and maintenance in factories takes time and effort, and there is also the problem that the quality and efficiency of the reports are affected by the emotional state of the person in charge. Furthermore, when a person in charge is feeling stressed or tired, there is a demand for reports that are visually easy to understand and concise. To solve these issues, there is a need for a dynamic report generation system that responds to the user's emotions.

[0319] 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.

[0320] In this invention, the server includes means for receiving input of target equipment and period from the user, means for collecting data related to the target equipment and period from the database, and means for pre-processing the collected data, thereby enabling dynamic report generation according to the emotional state of the user.

[0321] "Covered Equipment" refers to specific machinery and equipment used within a factory.

[0322] "Time period" refers to the specific time range for collecting and analyzing data for the subject equipment.

[0323] A "means" refers to a method, device, or part of a system used to achieve a specific purpose.

[0324] A "database" refers to a digital system for systematically storing and managing various information.

[0325] "Collection" refers to the operation of gathering necessary information from a database.

[0326] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze.

[0327] "Analysis" refers to the calculation and evaluation of specific indicators and trends based on pre-processed data.

[0328] "Visualization" refers to displaying the results of data analysis in a visually easy-to-understand form (for example, graphs or charts).

[0329] "Automatic generation" refers to the system automatically creating materials in a specified format.

[0330] "Emotional state" refers to the user's psychological and emotional state, which is analyzed from the user's facial expressions, tone of voice, input text, etc.

[0331] "Dynamic adjustment" refers to changing the content or format of materials in real time according to specific conditions or circumstances.

[0332] "Providing" refers to the operation of handing over the generated materials to the user.

[0333] This invention is a system that automatically generates reports on the maintenance and operation of machinery and equipment used in factories. The system accepts input from users about the equipment and period of time in question, collects related data from a database, and preprocesses, analyzes, and visualizes that data. Furthermore, the system can analyze the user's emotional state and dynamically adjust the report content and format based on the user's emotion.

[0334] Hardware and Software Use

[0335] The following hardware and software are used to implement the present invention.

[0336] 1. Device:

[0337] A device used by a user to input information (e.g., smartphone, tablet, dedicated touch panel terminal).

[0338] 2. Server:

[0339] A central server for performing data collection, pre-processing, analysis, visualization, and report generation.

[0340] 3. Database:

[0341] A database for storing various information about equipment in a factory (e.g., customer management system, sales management system, enterprise resource planning system).

[0342] 4. Emotion Engine:

[0343] A software module (e.g., EmotionEngine) for analyzing a user's emotional state from facial expressions, tone of voice, and input text.

[0344] Data processing and calculation

[0345] 1. Data Collection:

[0346] The server receives information about the equipment and period entered by the user from the terminal, and collects data such as related maintenance logs, operating hours, and failure history from the database.

[0347] 2. Pretreatment:

[0348] Cleanse the data, impute missing values, normalize, and prepare it in a format suitable for analysis.

[0349] 3. Data Analysis:

[0350] Key indicators such as repair frequency, availability rate, and failure trends are calculated, and heat maps and line graphs are generated as needed.

[0351] 4. Emotion analysis:

[0352] The emotion engine analyzes the user's emotional state in real time to determine how stressed or tired they are.

[0353] 5. Report Generation:

[0354] Based on the analysis results, a report is automatically generated that reflects the user's emotional state. For example, if the user is nervous, the report will be presented in a simpler, more visually understandable format.

[0355] Specific examples

[0356] Suppose a user wants to create a maintenance report for a large machine tool in a factory. The user enters the ID of the target machine and a period (e.g., Q1 2023) on their device. If the emotion engine detects the user's state of tension, the server collects the necessary information from the database, preprocesses, and analyzes the data. It then generates a simple report that reflects the user's state of tension and provides it to the user. Through this process, the user can obtain the necessary report efficiently and without stress.

[0357] Prompt Sentence Examples

[0358] Enter the machine ID: "MXT-2001"

[0359] Enter the start date of the period (YYYY-MM-DD): "2023-01-01"

[0360] Enter the end date of the period (YYYY-MM-DD): "2023-03-31"

[0361] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0362] Step 1:

[0363] The terminal accepts the ID of the target device and the start and end dates of the period as input from the user. The input data is sent to the system and saved on the server. The input here is the ID of the target device and the period, and the necessary data is collected based on that.

[0364] Step 2:

[0365] The server collects data such as related maintenance logs, operating hours, and failure history from the database based on the ID and period information of the target equipment received from the terminal. The collected data is prepared as a preliminary step for data analysis. The input here is the ID and period of the target equipment, and the corresponding output is the collected raw data.

[0366] Step 3:

[0367] The server preprocesses the collected data. Preprocessing includes data cleansing, missing value imputation, and normalization. Cleansing removes unnecessary or inconsistent data, and missing value imputation maintains data integrity. Normalization standardizes the data format. The input here is raw data, and the output is preprocessed data.

[0368] Step 4:

[0369] The server analyzes the preprocessed data. Specifically, it calculates key indicators such as repair frequency, availability rate, and failure trends, and generates visualized data such as heat maps and line graphs. The input here is the preprocessed data, and the output is the analysis results and visualized data.

[0370] Step 5:

[0371] The emotion engine analyzes the user's facial expressions and tone of voice in real time from the device to determine their emotional state. The input here is raw data on the user's emotional state, and the output is information on the determined emotional state.

[0372] Step 6:

[0373] The server dynamically adjusts the content and format of the report based on the user's emotional state. For example, if the user is nervous, it generates a simpler, more visually understandable report. The inputs here are the analysis results and the user's emotional state, and the output is a dynamically adjusted draft report.

[0374] Step 7:

[0375] The server automatically generates a final report based on the adjusted draft report and saves it in the specified format (e.g. PDF). The input here is the draft report, and the output is the final report file.

[0376] Step 8:

[0377] The terminal provides the final report file to the user, who can then review the report on the terminal and download or print it. The input at this stage is the final report file, and the output is a download link or file provided to the user.

[0378] The above is the flow of processing in the system for realizing the application example.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] [Second embodiment]

[0383] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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).

[0389] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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."

[0395] The present invention relates to a system for automatically generating business negotiation materials, and a specific implementation method thereof will be described in detail.

[0396] The system consists of a terminal operated by the user, a server that executes the processing, and a database required to create business negotiation materials.

[0397] First, a user logs in to the system using a terminal and specifies the target companies and target period for which business negotiation materials are to be created. The terminal then transmits this specified information to the server.

[0398] The server collects the necessary data from databases based on the received information on the target company and target period. The databases include customer relationship management (CRM), sales management systems, and enterprise resource planning (ERP) systems. This allows the collection of past sales negotiation data, sales data, customer information, product information, and more.

[0399] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0400] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[0401] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[0402] The server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualized data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. This makes the documents consistent and easier to understand.

[0403] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[0404] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system. It will then perform data cleansing and fill in missing values, calculate the success rate of sales negotiations and average order amount, and graph past sales negotiation trends. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[0405] In this way, the present invention realizes improved efficiency and quality in creating business negotiation materials.

[0406] The processing flow will be explained below.

[0407] Step 1:

[0408] The user logs in to the system using a terminal and requests the creation of business negotiation materials. The user inputs the name of the target company and the target period.

[0409] Step 2:

[0410] The terminal transmits the input information on the target company and target period to the server.

[0411] Step 3:

[0412] The server analyzes the received request and identifies the required data.

[0413] Step 4:

[0414] The server collects data related to the target company and the target period from databases such as a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP).

[0415] Step 5:

[0416] The server performs data cleansing on the collected data, which includes removing inconsistent and duplicate data.

[0417] Step 6:

[0418] The server imputes missing data values. Missing values ​​are imputed using averages or predicted values.

[0419] Step 7:

[0420] The server performs data normalization, so that the data is in a uniform format.

[0421] Step 8:

[0422] The server calculates KPIs such as the success rate of sales negotiations and the average order amount based on the pre-processed data.

[0423] Step 9:

[0424] The server performs time series analysis based on past sales negotiation data and extracts trends.

[0425] Step 10:

[0426] The server then creates visualizations of the data based on the analysis results, which may include generating line graphs, bar graphs, pie charts, etc.

[0427] Step 11:

[0428] The server automatically generates a draft of the sales documents based on the visualized data, and the report is created in PowerPoint or PDF format.

[0429] Step 12:

[0430] The server provides the generated sales negotiation materials as a link that the user can download.

[0431] Step 13:

[0432] The user accesses the provided link through the terminal and downloads or checks the business documents.

[0433] Through the above processing flow, negotiation materials are automatically generated efficiently and quickly provided to the user.

[0434] Example 1

[0435] 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."

[0436] Creating sales documents requires a great deal of time and effort, and because the data collection, preprocessing, analysis, and visualization processes are particularly complex, a system that can perform this work quickly and accurately is needed. Furthermore, there is the problem of integrating data collected from different data sources and resolving inconsistencies, which requires a lot of time and effort.

[0437] 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.

[0438] In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for cleansing the collected data, correcting inconsistent data, and filling in missing data values, means for calculating negotiation success rates, average order amounts, customer behavior patterns, etc. using the preprocessed data, means for generating line graphs, bar graphs, pie charts, heat maps, etc. based on the calculation results and visualizing the data, means for automatically generating negotiation materials using the visualized data and exporting them in a specified format, and means for providing the automatically generated negotiation materials to the user. This enables the rapid and accurate creation of negotiation materials.

[0439] A "user" is an individual or group that operates the system and instructs the creation of business negotiation materials.

[0440] "Target company" refers to the company for which business negotiation materials are to be created.

[0441] The "target period" is a specific time range related to the creation of the sales negotiation materials.

[0442] A "database" is an information management system that systematically stores information and makes it accessible as needed.

[0443] "Cleansing" is the process of de-duplication of data, correcting inconsistent data, and filling in missing values.

[0444] The "success rate of business negotiations" is an indicator that indicates the percentage of successful business negotiations within a certain period of time.

[0445] "Average order amount" is the average order amount in business negotiations.

[0446] "Customer behavior patterns" are behavioral data such as purchases and inquiries that a customer exhibits within a specific time range.

[0447] A "line graph" is a graph in which data points are connected by straight lines, and is used to visually represent changes and trends over time.

[0448] A "bar graph" is a graph in which different categories of data are represented by the length of the bars.

[0449] A "pie chart" is a graph in which segments of a circle represent proportions of a whole.

[0450] A "heat map" is a visual representation of data values ​​using shades or hues of color.

[0451] "Business negotiation materials" are documents that record the progress and results of business negotiations and include analysis results and graphs.

[0452] "Export" is the act of outputting a generated document in a particular format.

[0453] This invention relates to a system that is comprised of a terminal operated by a user, a server that executes processing, and a database required for creating negotiation materials, and also to a method for automatically generating negotiation materials. A specific implementation method will now be described in detail.

[0454] First, the user logs in to the system using a terminal and specifies the target company and target period for creating business negotiation materials. The terminal then sends this specified information to the server. For example, if the user specifies "Company XYZ" and the period "Q1 2023," the terminal sends this as an HTTP request to the server.

[0455] Based on the received information on the target company and target period, the server collects the necessary data from databases, including customer relationship management (CRM), sales management, and enterprise resource planning (ERP) systems. The server uses a database connection pool to issue queries to these systems and collect past sales data, sales data, customer information, product information, and other information related to the target company.

[0456] The server then preprocesses the collected data, using a data cleansing tool (e.g., OpenRefine) to remove duplicates and correct inconsistent data, as well as to impute missing values ​​and normalize the data to prepare it for analysis.

[0457] Once preprocessing is complete, the server performs data analysis. Specifically, it uses data analysis libraries (e.g., Pandas and NumPy) to calculate KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns. It also performs trend analysis based on past sales negotiation data to analyze trends in success rates and seasonal fluctuations in sales.

[0458] Based on the analysis results, the server visualizes the data using visualization libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc., which facilitates visual understanding of the data.

[0459] Next, the server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. It uses Python libraries (e.g., ReportLab and pptx) to assemble the sales documents and generate documents containing the necessary information and comments.

[0460] Finally, the server provides the automatically generated business documents to the user. The server uploads the generated documents to cloud storage and generates a download link. The server sends this link to the user's device or automatically sends the documents to a specified email address as needed. The user can view, download, or print the documents through the provided link.

[0461] As a concrete example, consider the case where the user specifies the target company "XYZ Company" and the period "Q1 2023." The server collects data related to "XYZ Company" from the CRM system and ERP system, performs data cleansing, and fills in missing values. It calculates the success rate of sales negotiations and average order amount, and creates graphs of past sales negotiation trends. Finally, it automatically generates sales negotiation materials in PDF format containing these analysis results and graphs, and provides them to the user.

[0462] An example of a prompt to enter is:

[0463] "When specifying the target company and period, please collect data from CRM and ERP and automatically generate sales negotiation materials. As a specific example, let's say the target company is "XYZ Company" and the period is "Q1 2023." Please cleanse the obtained data, calculate the success rate of sales negotiations and average order amount, and generate line graphs and bar graphs. Output the final sales negotiation materials in PDF format and provide them to the user."

[0464] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0465] Step 1:

[0466] The user logs into the system using a terminal. The user then enters the target company "XYZ Corporation" and the target period "Q1 2023" and presses the submit button. The terminal sends this information to the server as an HTTP request. The input includes the target company and period information, and the output passes this information to the server.

[0467] Specific operation: The user enters "XYZ Company" and "Q1 2023" into the form on the terminal and clicks the "Submit" button. The terminal sends this as an HTTP request in JSON format to the server.

[0468] Step 2:

[0469] The server accesses the database and collects the necessary data based on the target company and target period information received from the user. The input is the target company and period information, and the output is the data retrieved from the database. The server issues queries to the CRM system and ERP system to collect the corresponding data.

[0470] What happens: The server uses the database connection pool to access the CRM and ERP API endpoints, and queries to retrieve data related to "Company XYZ" and "Q1 2023."

[0471] Step 3:

[0472] The server preprocesses the collected data. The collected data may contain duplicates and inconsistencies, so cleansing is necessary. The input is raw data, and the output is cleansed data. Specifically, a data cleansing tool (e.g., OpenRefine) is used to remove duplicates, correct inconsistencies, and complete missing values.

[0473] What it does: The server uses OpenRefine to detect and remove duplicate data, correct inconsistent data, and impute missing values ​​with the mean or median.

[0474] Step 4:

[0475] The server performs data analysis using the preprocessed data. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses a data analysis library (e.g., Pandas or NumPy) to calculate the success rate of sales negotiations, average order amount, and customer behavior patterns.

[0476] What it does: Uses Pandas and NumPy to calculate aggregates, averages, and summary statistics for a dataset. Calculates win rates, average order value, and customer behavior patterns.

[0477] Step 5:

[0478] The server visualizes the analysis results. The input is the analysis results, and the output is visualized data (graphs, charts). This is done using libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc.

[0479] Specific operations: Using Matplotlib and Seaborn, the progress of sales success rates is visualized as a line graph, seasonal fluctuations in sales as a bar graph, and customer behavior patterns as pie charts and heat maps.

[0480] Step 6:

[0481] The server automatically generates sales documents based on the visualized data. The input is the visualized data and a prompt from the AI ​​model, and the output is sales documents in the specified format (e.g., PowerPoint, PDF). The documents are generated using Python libraries (e.g., ReportLab or pptx).

[0482] What it does: The server uses the ReportLab and pptx libraries to automatically generate a sales presentation, which includes analysis results, graphs, and automatically generated comments.

[0483] Step 7:

[0484] The server generates a download link for the automatically generated business documents and sends it to the user's device. The input is the generated business documents, and the output is a download link or email. The user receives this and downloads or prints the documents.

[0485] Specific operation: The server uploads the generated sales documents to cloud storage and generates a download link. The link is sent to the user via email. The user clicks the link to download the documents.

[0486] (Application example 1)

[0487] 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."

[0488] Logistics centers handle many types of data and are required to quickly organize and analyze it and provide appropriate reports to relevant parties. However, performing the entire process of data collection, preprocessing, analysis, visualization, and report creation manually is time-consuming and prone to errors. It is also important to report the analysis results in a visually easy-to-understand format, but this is also time-consuming. As such, there is a need to solve the issues of efficient and accurate data processing and report creation.

[0489] 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.

[0490] In this invention, the server includes: means for accepting input of a target company and a period from a user; means for collecting data related to the target company and the period from a database; means for preprocessing the collected data; means for analyzing the preprocessed data; means for visualizing data based on the analysis results; means for automatically generating business reports using the visualized data; means for providing the automatically generated business reports to a user; means for generating a link for displaying the generated reports and sending it to a user terminal; means for sending the reports by email as needed; and means for the reports to include inventory turnover, delivery time, and pick rate. This automates data processing and report generation at a logistics center, enabling efficient and accurate business operations.

[0491] "User terminal" means a device used by a user to view and manipulate commercial reporting materials, including a smartphone, tablet, smart glasses, etc.

[0492] "Target company" refers to the company that is the subject of data analysis and report creation for the invention.

[0493] "Time period" refers to a specific time range for data collection, analysis, and reporting.

[0494] A "database" is a system for storing data, which is composed of a customer management system, a transportation management system, an enterprise resource planning system, and the like.

[0495] "Preprocessing" refers to the process of removing duplicates, filling in missing values, and normalizing the collected data.

[0496] "Analysis" refers to the process of calculating specific indicators (KPIs) based on preprocessed data and interpreting the data based on them.

[0497] "Visualization" refers to the process of converting analytical results into a visually understandable format such as a line graph, bar graph, pie chart, or heat map.

[0498] "Commercial reporting materials" are reports containing data analysis results for the target company and period, and are provided in formats such as PDF or PowerPoint.

[0499] "Displayable link" refers to a link sent to a user's device that the user can access to view and download the report materials.

[0500] "Inventory turnover rate" refers to an indicator that shows the speed at which inventory is replaced at a logistics center.

[0501] "Delivery time" refers to an indicator that measures the time from when an order is received to when the product is delivered.

[0502] "Pick rate" refers to an indicator that indicates the frequency with which products are accurately picked up at a logistics center.

[0503] This invention relates to a system for automating data processing and report creation in a logistics center. The system is composed of a user terminal, a server that executes processing, and a database.

[0504] First, the user logs into the system using a terminal and specifies the target company and target period. The specified information is sent from the terminal to the server. Based on this information, the server collects the necessary data from the database. The database includes a customer relationship management system (CRM), a transportation management system (TMS), and an enterprise resource planning system (ERP). This allows the collection of past logistics data, delivery data, customer information, inventory information, and more.

[0505] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0506] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as inventory turnover, average delivery time, and pick rate, and performs trend analysis based on past logistics data. This allows the operational status of the logistics center and areas for improvement to be identified.

[0507] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data. Using this visualized data, a draft of the business report is created. Based on the visualized data, the server automatically generates the business report in the specified format (e.g., PowerPoint, PDF).

[0508] The automatically generated commercial report is generated as a displayable link and sent to the user's device. The user can view, download, or print the commercial report via the provided link. The system also has a function to automatically send the report to a specified email address, if necessary.

[0509] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past logistics and delivery data related to "XYZ Company" from the CRM system, TMS, and ERP system. It will then perform data cleansing and fill in missing values, calculate inventory turnover and average delivery time, and graph past logistics trends. Finally, it will automatically generate a business report containing these analysis results and graphs and provide it to the user.

[0510] Example prompt sentence:

[0511] Target company: “XYZ Company”

[0512] Target period: "Q1 2023"

[0513] Collected data: CRM data, TMS data, ERP data

[0514] Essential KPIs: Inventory turnover, delivery time, pick rate

[0515] Report format: PDF

[0516] In this way, the present invention improves the efficiency and quality of data processing and report generation in a logistics center.

[0517] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0518] Step 1:

[0519] The system accepts input of target companies and periods from the user. The user logs into the system using a terminal and inputs the target company (e.g., "XYZ Company") and target period (e.g., "Q1 2023"). The terminal sends this specified information to the server. The input is received as manual data from the user, and the output is the specified information for the target company and period.

[0520] Step 2:

[0521] Data related to the target company and period is collected from the database. Based on the received information on the target company and period, the server collects the necessary data from the CRM system, TMS, and ERP system. This includes past logistics data, delivery data, customer information, inventory information, etc. The input is the specified information on the target company and period, and the output is the collected data from each system.

[0522] Step 3:

[0523] The collected data is preprocessed. The server cleanses the data, removes duplicates and inconsistencies, and imputes missing values. It also normalizes the data and prepares it in a format suitable for analysis. The input is the collected data, and the output is the cleansed and normalized data.

[0524] Step 4:

[0525] The preprocessed data is analyzed. The server calculates KPIs such as inventory turnover, delivery time, and pick rate based on the cleansed and normalized data. It also performs trend analysis based on past logistics data. The input is the preprocessed data, and the output is the results of various KPIs and trend analysis.

[0526] Step 5:

[0527] The server visualizes the data based on the analysis results. The server visually represents the analysis results in the form of line graphs, bar graphs, pie charts, heat maps, etc. This makes it easier to understand the data. The input is the analysis results, and the output is the generated graphs and charts.

[0528] Step 6:

[0529] The visualized data is used to automatically generate business reports. The server generates business reports in a specified format (e.g., PDF, PowerPoint) based on the visualized data. The input is the visualized data, and the output is the business report.

[0530] Step 7:

[0531] Automatically generated commercial report materials are provided to users. The server sends the generated report materials to the user's terminal as a displayable link. The user can check the report materials via this link and download or print them. In addition, a function is provided to automatically send the materials to a specified email address, if necessary. The input is the generated report materials, and the output is a link that can be viewed on the user's terminal or an automatically sent email.

[0532] 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.

[0533] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[0534] The system consists of a terminal operated by the user, a server that processes various data, and a database. An emotion engine is also built into the terminal and server.

[0535] First, the user logs into the system using a terminal and requests the creation of business documents. The user inputs the name of the target company and the target period. At this time, the emotion engine recognizes the user's emotions in real time. The emotion engine can grasp the user's emotional state by analyzing the user's facial expressions, tone of voice, and the content of the input text.

[0536] The terminal sends the user's emotional information along with the input information to the server. The server then collects the necessary data from a database based on the received information on the target company and target period. The database includes a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP), which collects past sales negotiation data, sales data, customer information, product information, and other data.

[0537] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0538] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[0539] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[0540] The server automatically generates sales documents in the specified format (e.g., PowerPoint or PDF) based on the visualization data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. The emotion engine dynamically adjusts the content and design of the documents according to the user's emotional state. For example, if the user is feeling stressed, the system will generate documents that are simpler and easier to read.

[0541] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[0542] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023" and the emotion engine detects the user's tension, the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system, perform data cleansing, and calculate the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it will generate simple, visually easy-to-understand materials that will reduce stress. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[0543] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[0544] The processing flow will be explained below.

[0545] Step 1:

[0546] The user logs into the system using a terminal and requests the creation of business documents. The user enters the name of the target company and the target period. At this time, the emotion engine analyzes the user's facial expressions, tone of voice, and text input in real time through the terminal's built-in camera, microphone, and keyboard input, and recognizes the user's emotions.

[0547] Step 2:

[0548] The terminal transmits the recognized emotion information of the user to the server together with the input information on the target company and target period.

[0549] Step 3:

[0550] The server analyzes the received request and identifies the required data relating to the target company and time period.

[0551] Step 4:

[0552] The server accesses each database (customer management system, sales management system, enterprise resource planning system) and collects data related to the specified target company and target period.

[0553] Step 5:

[0554] After collecting the data, the server performs data cleansing, which includes removing duplicate data and correcting inconsistent data.

[0555] Step 6:

[0556] The server completes the missing values ​​in the collected data by predicting and completing the missing values ​​using statistical methods and machine learning algorithms.

[0557] Step 7:

[0558] Once the data is cleaned, the server normalizes it, unifying data in different formats and making it suitable for analysis.

[0559] Step 8:

[0560] The server uses the pre-processed data to perform data analysis, specifically calculating important KPIs such as success rate, average order value, and customer behavior patterns.

[0561] Step 9:

[0562] The server performs time-series analysis based on past sales negotiation data to extract trends, allowing analysis of sales negotiation history with target companies and seasonal fluctuations in sales.

[0563] Step 10:

[0564] The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data.

[0565] Step 11:

[0566] The server automatically generates a draft of a sales document based on the visualized data. The content and format of the document are dynamically adjusted based on the user's emotional data collected by the emotion engine. For example, if the user is nervous, the structure of the document is simplified and visually intuitive elements are enhanced.

[0567] Step 12:

[0568] The server provides the user with automatically generated business documents in a specified format (e.g., PowerPoint, PDF) and sends them to the user's device as a trusted link.

[0569] Step 13:

[0570] Users can view the sales documents through the provided link and download, print, or email them. By viewing the documents generated by the emotion engine, users can reduce stress and tension, increasing the success rate of sales negotiations.

[0571] Through the above processing flow, business negotiation materials are automatically generated efficiently and are provided in a form that takes into consideration the user's feelings.

[0572] Example 2

[0573] 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."

[0574] Conventional sales document creation systems require users to input data on target companies and time periods, and then automatically generate documents based on that data. However, they were unable to consider the user's emotional state. This meant that they lacked the flexibility to adjust the content and format of the documents depending on the user's emotional state. Furthermore, there was a problem with the design of sales documents being inappropriate when the user was emotionally stressed.

[0575] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for preprocessing the collected data, means for analyzing the preprocessed data, means for visualizing data based on the analysis results, means for automatically generating negotiation materials using the visualized data, means for recognizing the user's emotions, means for dynamically adjusting the content and format of the negotiation materials based on the user's emotional information, and means for providing the automatically generated negotiation materials to the user. This enables flexible and efficient creation of negotiation materials that take the user's emotional state into consideration.

[0576] "User" refers to a person who accesses and operates the system.

[0577] "Terminal" refers to a device such as a computer or smartphone that is operated by a user.

[0578] A "server" refers to a computer system that processes requests from multiple terminals and performs data collection, analysis, document generation, etc.

[0579] The term "target company" refers to a specific company that the user designates in order to create business negotiation materials.

[0580] "Period" refers to a specific time range for extracting data necessary for creating sales documents.

[0581] A "database" is a system for storing information, and includes customer management systems, sales management systems, enterprise resource planning systems, and the like.

[0582] An "emotion engine" refers to a system that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, and input text.

[0583] "Data cleansing" refers to the process of removing duplicates and inconsistencies in data and filling in missing values.

[0584] "Data normalization" refers to the process of organizing data based on certain rules and making it consistent.

[0585] "KPI" stands for Key Performance Indicator and refers to key indicators such as success rate of sales negotiations, average order amount, and customer behavior patterns.

[0586] "Visualization" refers to converting the results of data analysis into a visually easy-to-understand format (e.g., graphs, charts).

[0587] "Business negotiation materials" refers to materials that are automatically generated based on collected and analyzed data and are used in business negotiations.

[0588] A "prompt sentence" refers to an instruction sentence input to a generative AI model.

[0589] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[0590] System Configuration

[0591] Terminal: A device operated by a user, such as a computer or smartphone.

[0592] Server: A computer system that processes, analyzes, and generates various data.

[0593] Database: Data storage consisting of customer relationship management (CRM), sales management, enterprise resource planning (ERP), etc.

[0594] Emotion engine: Software that analyzes a user's facial expressions, tone of voice, and input text to recognize emotions.

[0595] Program processing flow

[0596] 1. A user operates a terminal and logs in to the system:

[0597] A user accesses the system at a terminal and authenticates by entering a username and password.

[0598] If authentication is successful, the user can access the main screen of the system.

[0599] 2. User enters target information:

[0600] The user fills in the required data in a form to input the name of the target company and the period.

[0601] 3. Emotion Recognition with Emotion Engine:

[0602] The device's built-in emotion engine analyzes the user's facial expressions, tone of voice, and input text to grasp their emotional state in real time.

[0603] The analysis results are output as a probability-based emotional state (tension, joy, stress, etc.).

[0604] 4. Data transmission:

[0605] The terminal generates a data packet containing the target company name, period, and emotion information and transmits it to the server.

[0606] 5. Data Collection:

[0607] Based on the received company name and period information, the server collects relevant data from databases such as customer relationship management (CRM), sales management systems, and enterprise resource planning systems (ERP).

[0608] 6. Data Preprocessing:

[0609] The server cleanses the collected data, removing duplicates and inconsistencies and filling in missing data.

[0610] Normalize the data into a format suitable for analysis.

[0611] 7. Data Analysis:

[0612] Based on the pre-processed data, the server calculates key performance indicators (KPIs) such as success rate, average order amount, and customer behavior patterns.

[0613] Conduct trend analysis to understand seasonal fluctuations and sales history.

[0614] 8. Data Visualization:

[0615] The server visualizes the analysis results in a visually easy-to-understand format (line graphs, bar graphs, pie charts, heat maps, etc.).

[0616] 9. Automatic generation of sales documents:

[0617] The server generates business documents in a specified format (e.g., PowerPoint, PDF) based on the visualized data.

[0618] The content and design of materials are dynamically adjusted based on information from the emotion engine. For example, if a user is feeling stressed, simple, visually easy-to-understand materials are provided.

[0619] 10. Provision of business materials:

[0620] The server generates a downloadable link for the generated business negotiation materials and transmits the link to the user's terminal.

[0621] If necessary, the system also has the function to automatically send documents to a specified email address.

[0622] Specific examples

[0623] When a user specifies the target company "Company A" and the period "Q1 2023" and the emotion engine detects the user's tension, the server collects past sales negotiation data and sales data related to "Company A" from the CRM system and ERP system, cleans the data, and calculates the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it generates simple, visually easy-to-understand materials that reduce stress. Finally, it automatically generates sales negotiation materials including these analysis results and graphs and provides them to the user.

[0624] Prompt Sentence Examples

[0625] "Please create a sales document for Company A for the period Q1 2023. Because users are feeling nervous, please create a simple and visually easy-to-understand format."

[0626] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[0627] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0628] Step 1: User login and input of target information

[0629] Specific operation: The user accesses the system login screen using a terminal and enters the username and password. After successful authentication, the system's main screen is displayed.

[0630] Input: Username, Password

[0631] Output: Main screen if login is successful, authentication error message if unsuccessful

[0632] Step 2: Enter the target company and period

[0633] Specific operation: The user enters the name of the target company and the period, then submits the input form. The entered information is temporarily saved on the device.

[0634] Input: Target company name, period

[0635] Output: A data packet containing the target company name and time period

[0636] Step 3: Emotion Recognition

[0637] How it works: The emotion engine analyzes the user's facial expressions, tone of voice, and input text in real time, and outputs a probability-based emotional state. The analysis results are stored on the device.

[0638] Input: User facial expressions, tone of voice, input text

[0639] Output: Emotional state (e.g., nervous, happy, stressed, etc.)

[0640] Step 4: Send data

[0641] Specific operation: The device generates a data packet containing the target company name, period, and emotion information and sends it to the server.

[0642] Input: Target company name, period, sentiment information

[0643] Output: Data packet sent to the server

[0644] Step 5: Data collection

[0645] Specific operation: The server receives the data packet and extracts the necessary data from the database (CRM, sales management system, ERP, etc.) based on the target company name and period.

[0646] Input: Target company name, period

[0647] Output: Collected sales opportunity data, sales data, and customer information

[0648] Step 6: Data Preprocessing

[0649] What it does: It cleanses the data collected by the server, removing duplicates and inconsistencies, filling in missing data, and normalizing the data into a format suitable for analysis.

[0650] Input: Collected data

[0651] Output: Cleansed and normalized data

[0652] Step 7: Data analysis

[0653] Specific operation: The server uses the preprocessed data to calculate KPIs such as success rate, average order amount, and customer behavior patterns, and performs trend analysis.

[0654] Input: Normalized data

[0655] Output: Analysis results (sales success rate, average order amount, trend data, etc.)

[0656] Step 8: Data Visualization

[0657] Specific operation: The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, etc.

[0658] Input: Analysis results

[0659] Output: Visualized data (graphs and charts)

[0660] Step 9: Auto-generate sales documents

[0661] Specific operation: The server generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. The design and content of the documents are dynamically adjusted based on the information from the emotion engine.

[0662] Input: Visualization data, emotion information

[0663] Output: Auto-generated sales documents

[0664] Step 10: Provide sales materials

[0665] Specific operation: The server generates a downloadable link for the generated sales documents and sends this link to the user's device. If necessary, the server also sends the documents to the email address specified by the user.

[0666] Input: Auto-generated sales document

[0667] Output: Download link, email to be sent

[0668] (Application example 2)

[0669] 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."

[0670] Creating reports on equipment operation and maintenance in factories takes time and effort, and there is also the problem that the quality and efficiency of the reports are affected by the emotional state of the person in charge. Furthermore, when a person in charge is feeling stressed or tired, there is a demand for reports that are visually easy to understand and concise. To solve these issues, there is a need for a dynamic report generation system that responds to the user's emotions.

[0671] 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.

[0672] In this invention, the server includes means for receiving input of target equipment and period from the user, means for collecting data related to the target equipment and period from the database, and means for pre-processing the collected data, thereby enabling dynamic report generation according to the emotional state of the user.

[0673] "Covered Equipment" refers to specific machinery and equipment used within a factory.

[0674] "Time period" refers to the specific time range for collecting and analyzing data for the subject equipment.

[0675] A "means" refers to a method, device, or part of a system used to achieve a specific purpose.

[0676] A "database" refers to a digital system for systematically storing and managing various information.

[0677] "Collection" refers to the operation of gathering necessary information from a database.

[0678] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze.

[0679] "Analysis" refers to the calculation and evaluation of specific indicators and trends based on pre-processed data.

[0680] "Visualization" refers to displaying the results of data analysis in a visually easy-to-understand form (for example, graphs or charts).

[0681] "Automatic generation" refers to the system automatically creating materials in a specified format.

[0682] "Emotional state" refers to the user's psychological and emotional state, which is analyzed from the user's facial expressions, tone of voice, input text, etc.

[0683] "Dynamic adjustment" refers to changing the content or format of materials in real time according to specific conditions or circumstances.

[0684] "Providing" refers to the operation of handing over the generated materials to the user.

[0685] This invention is a system that automatically generates reports on the maintenance and operation of machinery and equipment used in factories. The system accepts input from users about the equipment and period of time in question, collects related data from a database, and preprocesses, analyzes, and visualizes that data. Furthermore, the system can analyze the user's emotional state and dynamically adjust the report content and format based on the user's emotion.

[0686] Hardware and Software Use

[0687] The following hardware and software are used to implement the present invention.

[0688] 1. Device:

[0689] A device used by a user to input information (e.g., smartphone, tablet, dedicated touch panel terminal).

[0690] 2. Server:

[0691] A central server for performing data collection, pre-processing, analysis, visualization, and report generation.

[0692] 3. Database:

[0693] A database for storing various information about equipment in a factory (e.g., customer management system, sales management system, enterprise resource planning system).

[0694] 4. Emotion Engine:

[0695] A software module (e.g., EmotionEngine) for analyzing a user's emotional state from facial expressions, tone of voice, and input text.

[0696] Data processing and calculation

[0697] 1. Data Collection:

[0698] The server receives information about the equipment and period entered by the user from the terminal, and collects data such as related maintenance logs, operating hours, and failure history from the database.

[0699] 2. Pretreatment:

[0700] Cleanse the data, impute missing values, normalize, and prepare it in a format suitable for analysis.

[0701] 3. Data Analysis:

[0702] Key indicators such as repair frequency, availability rate, and failure trends are calculated, and heat maps and line graphs are generated as needed.

[0703] 4. Emotion analysis:

[0704] The emotion engine analyzes the user's emotional state in real time to determine how stressed or tired they are.

[0705] 5. Report Generation:

[0706] Based on the analysis results, a report is automatically generated that reflects the user's emotional state. For example, if the user is nervous, the report will be presented in a simpler, more visually understandable format.

[0707] Specific examples

[0708] Suppose a user wants to create a maintenance report for a large machine tool in a factory. The user enters the ID of the target machine and a period (e.g., Q1 2023) on their device. If the emotion engine detects the user's state of tension, the server collects the necessary information from the database, preprocesses, and analyzes the data. It then generates a simple report that reflects the user's state of tension and provides it to the user. Through this process, the user can obtain the necessary report efficiently and without stress.

[0709] Prompt Sentence Examples

[0710] Enter the machine ID: "MXT-2001"

[0711] Enter the start date of the period (YYYY-MM-DD): "2023-01-01"

[0712] Enter the end date of the period (YYYY-MM-DD): "2023-03-31"

[0713] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0714] Step 1:

[0715] The terminal accepts the ID of the target device and the start and end dates of the period as input from the user. The input data is sent to the system and saved on the server. The input here is the ID of the target device and the period, and the necessary data is collected based on that.

[0716] Step 2:

[0717] The server collects data such as related maintenance logs, operating hours, and failure history from the database based on the ID and period information of the target equipment received from the terminal. The collected data is prepared as a preliminary step for data analysis. The input here is the ID and period of the target equipment, and the corresponding output is the collected raw data.

[0718] Step 3:

[0719] The server preprocesses the collected data. Preprocessing includes data cleansing, missing value imputation, and normalization. Cleansing removes unnecessary or inconsistent data, and missing value imputation maintains data integrity. Normalization standardizes the data format. The input here is raw data, and the output is preprocessed data.

[0720] Step 4:

[0721] The server analyzes the preprocessed data. Specifically, it calculates key indicators such as repair frequency, availability rate, and failure trends, and generates visualized data such as heat maps and line graphs. The input here is the preprocessed data, and the output is the analysis results and visualized data.

[0722] Step 5:

[0723] The emotion engine analyzes the user's facial expressions and tone of voice in real time from the device to determine their emotional state. The input here is raw data on the user's emotional state, and the output is information on the determined emotional state.

[0724] Step 6:

[0725] The server dynamically adjusts the content and format of the report based on the user's emotional state. For example, if the user is nervous, it generates a simpler, more visually understandable report. The inputs here are the analysis results and the user's emotional state, and the output is a dynamically adjusted draft report.

[0726] Step 7:

[0727] The server automatically generates a final report based on the adjusted draft report and saves it in the specified format (e.g. PDF). The input here is the draft report, and the output is the final report file.

[0728] Step 8:

[0729] The terminal provides the final report file to the user, who can then review the report on the terminal and download or print it. The input at this stage is the final report file, and the output is a download link or file provided to the user.

[0730] The above is the flow of processing in the system for realizing the application example.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] [Third embodiment]

[0735] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0736] 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.

[0737] 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).

[0738] 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.

[0739] 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.

[0740] 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).

[0741] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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."

[0747] The present invention relates to a system for automatically generating business negotiation materials, and a specific implementation method thereof will be described in detail.

[0748] The system consists of a terminal operated by the user, a server that executes the processing, and a database required to create business negotiation materials.

[0749] First, a user logs in to the system using a terminal and specifies the target companies and target period for which business negotiation materials are to be created. The terminal then transmits this specified information to the server.

[0750] The server collects the necessary data from databases based on the received information on the target company and target period. The databases include customer relationship management (CRM), sales management systems, and enterprise resource planning (ERP) systems. This allows the collection of past sales negotiation data, sales data, customer information, product information, and more.

[0751] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0752] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[0753] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[0754] The server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualized data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. This makes the documents consistent and easier to understand.

[0755] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[0756] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system. It will then perform data cleansing and fill in missing values, calculate the success rate of sales negotiations and average order amount, and graph past sales negotiation trends. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[0757] In this way, the present invention realizes improved efficiency and quality in creating business negotiation materials.

[0758] The processing flow will be explained below.

[0759] Step 1:

[0760] The user logs in to the system using a terminal and requests the creation of business negotiation materials. The user inputs the name of the target company and the target period.

[0761] Step 2:

[0762] The terminal transmits the input information on the target company and target period to the server.

[0763] Step 3:

[0764] The server analyzes the received request and identifies the required data.

[0765] Step 4:

[0766] The server collects data related to the target company and the target period from databases such as a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP).

[0767] Step 5:

[0768] The server performs data cleansing on the collected data, which includes removing inconsistent and duplicate data.

[0769] Step 6:

[0770] The server imputes missing data values. Missing values ​​are imputed using averages or predicted values.

[0771] Step 7:

[0772] The server performs data normalization, so that the data is in a uniform format.

[0773] Step 8:

[0774] The server calculates KPIs such as the success rate of sales negotiations and the average order amount based on the pre-processed data.

[0775] Step 9:

[0776] The server performs time series analysis based on past sales negotiation data and extracts trends.

[0777] Step 10:

[0778] The server then creates visualizations of the data based on the analysis results, which may include generating line graphs, bar graphs, pie charts, etc.

[0779] Step 11:

[0780] The server automatically generates a draft of the sales documents based on the visualized data, and the report is created in PowerPoint or PDF format.

[0781] Step 12:

[0782] The server provides the generated sales negotiation materials as a link that the user can download.

[0783] Step 13:

[0784] The user accesses the provided link through the terminal and downloads or checks the business documents.

[0785] Through the above processing flow, negotiation materials are automatically generated efficiently and quickly provided to the user.

[0786] Example 1

[0787] 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."

[0788] Creating sales documents requires a great deal of time and effort, and because the data collection, preprocessing, analysis, and visualization processes are particularly complex, a system that can perform this work quickly and accurately is needed. Furthermore, there is the problem of integrating data collected from different data sources and resolving inconsistencies, which requires a lot of time and effort.

[0789] 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.

[0790] In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for cleansing the collected data, correcting inconsistent data, and filling in missing data values, means for calculating negotiation success rates, average order amounts, customer behavior patterns, etc. using the preprocessed data, means for generating line graphs, bar graphs, pie charts, heat maps, etc. based on the calculation results and visualizing the data, means for automatically generating negotiation materials using the visualized data and exporting them in a specified format, and means for providing the automatically generated negotiation materials to the user. This enables the rapid and accurate creation of negotiation materials.

[0791] A "user" is an individual or group that operates the system and instructs the creation of business negotiation materials.

[0792] "Target company" refers to the company for which business negotiation materials are to be created.

[0793] The "target period" is a specific time range related to the creation of the sales negotiation materials.

[0794] A "database" is an information management system that systematically stores information and makes it accessible as needed.

[0795] "Cleansing" is the process of de-duplication of data, correcting inconsistent data, and filling in missing values.

[0796] The "success rate of business negotiations" is an indicator that indicates the percentage of successful business negotiations within a certain period of time.

[0797] "Average order amount" is the average order amount in business negotiations.

[0798] "Customer behavior patterns" are behavioral data such as purchases and inquiries that a customer exhibits within a specific time range.

[0799] A "line graph" is a graph in which data points are connected by straight lines, and is used to visually represent changes and trends over time.

[0800] A "bar graph" is a graph in which different categories of data are represented by the length of the bars.

[0801] A "pie chart" is a graph in which segments of a circle represent proportions of a whole.

[0802] A "heat map" is a visual representation of data values ​​using shades or hues of color.

[0803] "Business negotiation materials" are documents that record the progress and results of business negotiations and include analysis results and graphs.

[0804] "Export" is the act of outputting a generated document in a particular format.

[0805] This invention relates to a system that is comprised of a terminal operated by a user, a server that executes processing, and a database required for creating negotiation materials, and also to a method for automatically generating negotiation materials. A specific implementation method will now be described in detail.

[0806] First, the user logs in to the system using a terminal and specifies the target company and target period for creating business negotiation materials. The terminal then sends this specified information to the server. For example, if the user specifies "Company XYZ" and the period "Q1 2023," the terminal sends this as an HTTP request to the server.

[0807] Based on the received information on the target company and target period, the server collects the necessary data from databases, including customer relationship management (CRM), sales management, and enterprise resource planning (ERP) systems. The server uses a database connection pool to issue queries to these systems and collect past sales data, sales data, customer information, product information, and other information related to the target company.

[0808] The server then preprocesses the collected data, using a data cleansing tool (e.g., OpenRefine) to remove duplicates and correct inconsistent data, as well as to impute missing values ​​and normalize the data to prepare it for analysis.

[0809] Once preprocessing is complete, the server performs data analysis. Specifically, it uses data analysis libraries (e.g., Pandas and NumPy) to calculate KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns. It also performs trend analysis based on past sales negotiation data to analyze trends in success rates and seasonal fluctuations in sales.

[0810] Based on the analysis results, the server visualizes the data using visualization libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc., which facilitates visual understanding of the data.

[0811] Next, the server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. It uses Python libraries (e.g., ReportLab and pptx) to assemble the sales documents and generate documents containing the necessary information and comments.

[0812] Finally, the server provides the automatically generated business documents to the user. The server uploads the generated documents to cloud storage and generates a download link. The server sends this link to the user's device or automatically sends the documents to a specified email address as needed. The user can view, download, or print the documents through the provided link.

[0813] As a concrete example, consider the case where the user specifies the target company "XYZ Company" and the period "Q1 2023." The server collects data related to "XYZ Company" from the CRM system and ERP system, performs data cleansing, and fills in missing values. It calculates the success rate of sales negotiations and average order amount, and creates graphs of past sales negotiation trends. Finally, it automatically generates sales negotiation materials in PDF format containing these analysis results and graphs, and provides them to the user.

[0814] An example of a prompt to enter is:

[0815] "When specifying the target company and period, please collect data from CRM and ERP and automatically generate sales negotiation materials. As a specific example, let's say the target company is "XYZ Company" and the period is "Q1 2023." Please cleanse the obtained data, calculate the success rate of sales negotiations and average order amount, and generate line graphs and bar graphs. Output the final sales negotiation materials in PDF format and provide them to the user."

[0816] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0817] Step 1:

[0818] The user logs into the system using a terminal. The user then enters the target company "XYZ Corporation" and the target period "Q1 2023" and presses the submit button. The terminal sends this information to the server as an HTTP request. The input includes the target company and period information, and the output passes this information to the server.

[0819] Specific operation: The user enters "XYZ Company" and "Q1 2023" into the form on the terminal and clicks the "Submit" button. The terminal sends this as an HTTP request in JSON format to the server.

[0820] Step 2:

[0821] The server accesses the database and collects the necessary data based on the target company and target period information received from the user. The input is the target company and period information, and the output is the data retrieved from the database. The server issues queries to the CRM system and ERP system to collect the corresponding data.

[0822] What happens: The server uses the database connection pool to access the CRM and ERP API endpoints, and queries to retrieve data related to "Company XYZ" and "Q1 2023."

[0823] Step 3:

[0824] The server preprocesses the collected data. The collected data may contain duplicates and inconsistencies, so cleansing is necessary. The input is raw data, and the output is cleansed data. Specifically, a data cleansing tool (e.g., OpenRefine) is used to remove duplicates, correct inconsistencies, and complete missing values.

[0825] What it does: The server uses OpenRefine to detect and remove duplicate data, correct inconsistent data, and impute missing values ​​with the mean or median.

[0826] Step 4:

[0827] The server performs data analysis using the preprocessed data. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses a data analysis library (e.g., Pandas or NumPy) to calculate the success rate of sales negotiations, average order amount, and customer behavior patterns.

[0828] What it does: Uses Pandas and NumPy to calculate aggregates, averages, and summary statistics for a dataset. Calculates win rates, average order value, and customer behavior patterns.

[0829] Step 5:

[0830] The server visualizes the analysis results. The input is the analysis results, and the output is visualized data (graphs, charts). This is done using libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc.

[0831] Specific operations: Using Matplotlib and Seaborn, the progress of sales success rates is visualized as a line graph, seasonal fluctuations in sales as a bar graph, and customer behavior patterns as pie charts and heat maps.

[0832] Step 6:

[0833] The server automatically generates sales documents based on the visualized data. The input is the visualized data and a prompt from the AI ​​model, and the output is sales documents in the specified format (e.g., PowerPoint, PDF). The documents are generated using Python libraries (e.g., ReportLab or pptx).

[0834] What it does: The server uses the ReportLab and pptx libraries to automatically generate a sales presentation, which includes analysis results, graphs, and automatically generated comments.

[0835] Step 7:

[0836] The server generates a download link for the automatically generated business documents and sends it to the user's device. The input is the generated business documents, and the output is a download link or email. The user receives this and downloads or prints the documents.

[0837] Specific operation: The server uploads the generated sales documents to cloud storage and generates a download link. The link is sent to the user via email. The user clicks the link to download the documents.

[0838] (Application example 1)

[0839] 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."

[0840] Logistics centers handle many types of data and are required to quickly organize and analyze it and provide appropriate reports to relevant parties. However, performing the entire process of data collection, preprocessing, analysis, visualization, and report creation manually is time-consuming and prone to errors. It is also important to report the analysis results in a visually easy-to-understand format, but this is also time-consuming. As such, there is a need to solve the issues of efficient and accurate data processing and report creation.

[0841] 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.

[0842] In this invention, the server includes: means for accepting input of a target company and a period from a user; means for collecting data related to the target company and the period from a database; means for preprocessing the collected data; means for analyzing the preprocessed data; means for visualizing data based on the analysis results; means for automatically generating business reports using the visualized data; means for providing the automatically generated business reports to a user; means for generating a link for displaying the generated reports and sending it to a user terminal; means for sending the reports by email as needed; and means for the reports to include inventory turnover, delivery time, and pick rate. This automates data processing and report generation at a logistics center, enabling efficient and accurate business operations.

[0843] "User terminal" means a device used by a user to view and manipulate commercial reporting materials, including a smartphone, tablet, smart glasses, etc.

[0844] "Target company" refers to the company that is the subject of data analysis and report creation for the invention.

[0845] "Time period" refers to a specific time range for data collection, analysis, and reporting.

[0846] A "database" is a system for storing data, which is composed of a customer management system, a transportation management system, an enterprise resource planning system, and the like.

[0847] "Preprocessing" refers to the process of removing duplicates, filling in missing values, and normalizing the collected data.

[0848] "Analysis" refers to the process of calculating specific indicators (KPIs) based on preprocessed data and interpreting the data based on them.

[0849] "Visualization" refers to the process of converting analytical results into a visually understandable format such as a line graph, bar graph, pie chart, or heat map.

[0850] "Commercial reporting materials" are reports containing data analysis results for the target company and period, and are provided in formats such as PDF or PowerPoint.

[0851] "Displayable link" refers to a link sent to a user's device that the user can access to view and download the report materials.

[0852] "Inventory turnover rate" refers to an indicator that shows the speed at which inventory is replaced at a logistics center.

[0853] "Delivery time" refers to an indicator that measures the time from when an order is received to when the product is delivered.

[0854] "Pick rate" refers to an indicator that indicates the frequency with which products are accurately picked up at a logistics center.

[0855] This invention relates to a system for automating data processing and report creation in a logistics center. The system is composed of a user terminal, a server that executes processing, and a database.

[0856] First, the user logs into the system using a terminal and specifies the target company and target period. The specified information is sent from the terminal to the server. Based on this information, the server collects the necessary data from the database. The database includes a customer relationship management system (CRM), a transportation management system (TMS), and an enterprise resource planning system (ERP). This allows the collection of past logistics data, delivery data, customer information, inventory information, and more.

[0857] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0858] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as inventory turnover, average delivery time, and pick rate, and performs trend analysis based on past logistics data. This allows the operational status of the logistics center and areas for improvement to be identified.

[0859] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data. Using this visualized data, a draft of the business report is created. Based on the visualized data, the server automatically generates the business report in the specified format (e.g., PowerPoint, PDF).

[0860] The automatically generated commercial report is generated as a displayable link and sent to the user's device. The user can view, download, or print the commercial report via the provided link. The system also has a function to automatically send the report to a specified email address, if necessary.

[0861] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past logistics and delivery data related to "XYZ Company" from the CRM system, TMS, and ERP system. It will then perform data cleansing and fill in missing values, calculate inventory turnover and average delivery time, and graph past logistics trends. Finally, it will automatically generate a business report containing these analysis results and graphs and provide it to the user.

[0862] Example prompt sentence:

[0863] Target company: “XYZ Company”

[0864] Target period: "Q1 2023"

[0865] Collected data: CRM data, TMS data, ERP data

[0866] Essential KPIs: Inventory turnover, delivery time, pick rate

[0867] Report format: PDF

[0868] In this way, the present invention improves the efficiency and quality of data processing and report generation in a logistics center.

[0869] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0870] Step 1:

[0871] The system accepts input of target companies and periods from the user. The user logs into the system using a terminal and inputs the target company (e.g., "XYZ Company") and target period (e.g., "Q1 2023"). The terminal sends this specified information to the server. The input is received as manual data from the user, and the output is the specified information for the target company and period.

[0872] Step 2:

[0873] Data related to the target company and period is collected from the database. Based on the received information on the target company and period, the server collects the necessary data from the CRM system, TMS, and ERP system. This includes past logistics data, delivery data, customer information, inventory information, etc. The input is the specified information on the target company and period, and the output is the collected data from each system.

[0874] Step 3:

[0875] The collected data is preprocessed. The server cleanses the data, removes duplicates and inconsistencies, and imputes missing values. It also normalizes the data and prepares it in a format suitable for analysis. The input is the collected data, and the output is the cleansed and normalized data.

[0876] Step 4:

[0877] The preprocessed data is analyzed. The server calculates KPIs such as inventory turnover, delivery time, and pick rate based on the cleansed and normalized data. It also performs trend analysis based on past logistics data. The input is the preprocessed data, and the output is the results of various KPIs and trend analysis.

[0878] Step 5:

[0879] The server visualizes the data based on the analysis results. The server visually represents the analysis results in the form of line graphs, bar graphs, pie charts, heat maps, etc. This makes it easier to understand the data. The input is the analysis results, and the output is the generated graphs and charts.

[0880] Step 6:

[0881] The visualized data is used to automatically generate business reports. The server generates business reports in a specified format (e.g., PDF, PowerPoint) based on the visualized data. The input is the visualized data, and the output is the business report.

[0882] Step 7:

[0883] Automatically generated commercial report materials are provided to users. The server sends the generated report materials to the user's terminal as a displayable link. The user can check the report materials via this link and download or print them. In addition, a function is provided to automatically send the materials to a specified email address, if necessary. The input is the generated report materials, and the output is a link that can be viewed on the user's terminal or an automatically sent email.

[0884] 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.

[0885] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[0886] The system consists of a terminal operated by the user, a server that processes various data, and a database. An emotion engine is also built into the terminal and server.

[0887] First, the user logs into the system using a terminal and requests the creation of business documents. The user inputs the name of the target company and the target period. At this time, the emotion engine recognizes the user's emotions in real time. The emotion engine can grasp the user's emotional state by analyzing the user's facial expressions, tone of voice, and the content of the input text.

[0888] The terminal sends the user's emotional information along with the input information to the server. The server then collects the necessary data from a database based on the received information on the target company and target period. The database includes a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP), which collects past sales negotiation data, sales data, customer information, product information, and other data.

[0889] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[0890] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[0891] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[0892] The server automatically generates sales documents in the specified format (e.g., PowerPoint or PDF) based on the visualization data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. The emotion engine dynamically adjusts the content and design of the documents according to the user's emotional state. For example, if the user is feeling stressed, the system will generate documents that are simpler and easier to read.

[0893] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[0894] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023" and the emotion engine detects the user's tension, the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system, perform data cleansing, and calculate the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it will generate simple, visually easy-to-understand materials that will reduce stress. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[0895] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[0896] The processing flow will be explained below.

[0897] Step 1:

[0898] The user logs into the system using a terminal and requests the creation of business documents. The user enters the name of the target company and the target period. At this time, the emotion engine analyzes the user's facial expressions, tone of voice, and text input in real time through the terminal's built-in camera, microphone, and keyboard input, and recognizes the user's emotions.

[0899] Step 2:

[0900] The terminal transmits the recognized emotion information of the user to the server together with the input information on the target company and target period.

[0901] Step 3:

[0902] The server analyzes the received request and identifies the required data relating to the target company and time period.

[0903] Step 4:

[0904] The server accesses each database (customer management system, sales management system, enterprise resource planning system) and collects data related to the specified target company and target period.

[0905] Step 5:

[0906] After collecting the data, the server performs data cleansing, which includes removing duplicate data and correcting inconsistent data.

[0907] Step 6:

[0908] The server completes the missing values ​​in the collected data by predicting and completing the missing values ​​using statistical methods and machine learning algorithms.

[0909] Step 7:

[0910] Once the data is cleaned, the server normalizes it, unifying data in different formats and making it suitable for analysis.

[0911] Step 8:

[0912] The server uses the pre-processed data to perform data analysis, specifically calculating important KPIs such as success rate, average order value, and customer behavior patterns.

[0913] Step 9:

[0914] The server performs time-series analysis based on past sales negotiation data to extract trends, allowing analysis of sales negotiation history with target companies and seasonal fluctuations in sales.

[0915] Step 10:

[0916] The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data.

[0917] Step 11:

[0918] The server automatically generates a draft of a sales document based on the visualized data. The content and format of the document are dynamically adjusted based on the user's emotional data collected by the emotion engine. For example, if the user is nervous, the structure of the document is simplified and visually intuitive elements are enhanced.

[0919] Step 12:

[0920] The server provides the user with automatically generated business documents in a specified format (e.g., PowerPoint, PDF) and sends them to the user's device as a trusted link.

[0921] Step 13:

[0922] Users can view the sales documents through the provided link and download, print, or email them. By viewing the documents generated by the emotion engine, users can reduce stress and tension, increasing the success rate of sales negotiations.

[0923] Through the above processing flow, business negotiation materials are automatically generated efficiently and are provided in a form that takes into consideration the user's feelings.

[0924] Example 2

[0925] 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."

[0926] Conventional sales document creation systems require users to input data on target companies and time periods, and then automatically generate documents based on that data. However, they were unable to consider the user's emotional state. This meant that they lacked the flexibility to adjust the content and format of the documents depending on the user's emotional state. Furthermore, there was a problem with the design of sales documents being inappropriate when the user was emotionally stressed.

[0927] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for preprocessing the collected data, means for analyzing the preprocessed data, means for visualizing data based on the analysis results, means for automatically generating negotiation materials using the visualized data, means for recognizing the user's emotions, means for dynamically adjusting the content and format of the negotiation materials based on the user's emotional information, and means for providing the automatically generated negotiation materials to the user. This enables flexible and efficient creation of negotiation materials that take the user's emotional state into consideration.

[0928] "User" refers to a person who accesses and operates the system.

[0929] "Terminal" refers to a device such as a computer or smartphone that is operated by a user.

[0930] A "server" refers to a computer system that processes requests from multiple terminals and performs data collection, analysis, document generation, etc.

[0931] The term "target company" refers to a specific company that the user designates in order to create business negotiation materials.

[0932] "Period" refers to a specific time range for extracting data necessary for creating sales documents.

[0933] A "database" is a system for storing information, and includes customer management systems, sales management systems, enterprise resource planning systems, and the like.

[0934] An "emotion engine" refers to a system that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, and input text.

[0935] "Data cleansing" refers to the process of removing duplicates and inconsistencies in data and filling in missing values.

[0936] "Data normalization" refers to the process of organizing data based on certain rules and making it consistent.

[0937] "KPI" stands for Key Performance Indicator and refers to key indicators such as success rate of sales negotiations, average order amount, and customer behavior patterns.

[0938] "Visualization" refers to converting the results of data analysis into a visually easy-to-understand format (e.g., graphs, charts).

[0939] "Business negotiation materials" refers to materials that are automatically generated based on collected and analyzed data and are used in business negotiations.

[0940] A "prompt sentence" refers to an instruction sentence input to a generative AI model.

[0941] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[0942] System Configuration

[0943] Terminal: A device operated by a user, such as a computer or smartphone.

[0944] Server: A computer system that processes, analyzes, and generates various data.

[0945] Database: Data storage consisting of customer relationship management (CRM), sales management, enterprise resource planning (ERP), etc.

[0946] Emotion engine: Software that analyzes a user's facial expressions, tone of voice, and input text to recognize emotions.

[0947] Program processing flow

[0948] 1. A user operates a terminal and logs in to the system:

[0949] A user accesses the system at a terminal and authenticates by entering a username and password.

[0950] If authentication is successful, the user can access the main screen of the system.

[0951] 2. User enters target information:

[0952] The user fills in the required data in a form to input the name of the target company and the period.

[0953] 3. Emotion Recognition with Emotion Engine:

[0954] The device's built-in emotion engine analyzes the user's facial expressions, tone of voice, and input text to grasp their emotional state in real time.

[0955] The analysis results are output as a probability-based emotional state (tension, joy, stress, etc.).

[0956] 4. Data transmission:

[0957] The terminal generates a data packet containing the target company name, period, and emotion information and transmits it to the server.

[0958] 5. Data Collection:

[0959] Based on the received company name and period information, the server collects relevant data from databases such as customer relationship management (CRM), sales management systems, and enterprise resource planning systems (ERP).

[0960] 6. Data Preprocessing:

[0961] The server cleanses the collected data, removing duplicates and inconsistencies and filling in missing data.

[0962] Normalize the data into a format suitable for analysis.

[0963] 7. Data Analysis:

[0964] Based on the pre-processed data, the server calculates key performance indicators (KPIs) such as success rate, average order amount, and customer behavior patterns.

[0965] Conduct trend analysis to understand seasonal fluctuations and sales history.

[0966] 8. Data Visualization:

[0967] The server visualizes the analysis results in a visually easy-to-understand format (line graphs, bar graphs, pie charts, heat maps, etc.).

[0968] 9. Automatic generation of sales documents:

[0969] The server generates business documents in a specified format (e.g., PowerPoint, PDF) based on the visualized data.

[0970] The content and design of materials are dynamically adjusted based on information from the emotion engine. For example, if a user is feeling stressed, simple, visually easy-to-understand materials are provided.

[0971] 10. Provision of business materials:

[0972] The server generates a downloadable link for the generated business negotiation materials and transmits the link to the user's terminal.

[0973] If necessary, the system also has the function to automatically send documents to a specified email address.

[0974] Specific examples

[0975] When a user specifies the target company "Company A" and the period "Q1 2023" and the emotion engine detects the user's tension, the server collects past sales negotiation data and sales data related to "Company A" from the CRM system and ERP system, cleans the data, and calculates the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it generates simple, visually easy-to-understand materials that reduce stress. Finally, it automatically generates sales negotiation materials including these analysis results and graphs and provides them to the user.

[0976] Prompt Sentence Examples

[0977] "Please create a sales document for Company A for the period Q1 2023. Because users are feeling nervous, please create a simple and visually easy-to-understand format."

[0978] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[0979] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0980] Step 1: User login and input of target information

[0981] Specific operation: The user accesses the system login screen using a terminal and enters the username and password. After successful authentication, the system's main screen is displayed.

[0982] Input: Username, Password

[0983] Output: Main screen if login is successful, authentication error message if unsuccessful

[0984] Step 2: Enter the target company and period

[0985] Specific operation: The user enters the name of the target company and the period, then submits the input form. The entered information is temporarily saved on the device.

[0986] Input: Target company name, period

[0987] Output: A data packet containing the target company name and time period

[0988] Step 3: Emotion Recognition

[0989] How it works: The emotion engine analyzes the user's facial expressions, tone of voice, and input text in real time, and outputs a probability-based emotional state. The analysis results are stored on the device.

[0990] Input: User facial expressions, tone of voice, input text

[0991] Output: Emotional state (e.g., nervous, happy, stressed, etc.)

[0992] Step 4: Send data

[0993] Specific operation: The device generates a data packet containing the target company name, period, and emotion information and sends it to the server.

[0994] Input: Target company name, period, sentiment information

[0995] Output: Data packet sent to the server

[0996] Step 5: Data collection

[0997] Specific operation: The server receives the data packet and extracts the necessary data from the database (CRM, sales management system, ERP, etc.) based on the target company name and period.

[0998] Input: Target company name, period

[0999] Output: Collected sales opportunity data, sales data, and customer information

[1000] Step 6: Data Preprocessing

[1001] What it does: It cleanses the data collected by the server, removing duplicates and inconsistencies, filling in missing data, and normalizing the data into a format suitable for analysis.

[1002] Input: Collected data

[1003] Output: Cleansed and normalized data

[1004] Step 7: Data analysis

[1005] Specific operation: The server uses the preprocessed data to calculate KPIs such as success rate, average order amount, and customer behavior patterns, and performs trend analysis.

[1006] Input: Normalized data

[1007] Output: Analysis results (sales success rate, average order amount, trend data, etc.)

[1008] Step 8: Data Visualization

[1009] Specific operation: The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, etc.

[1010] Input: Analysis results

[1011] Output: Visualized data (graphs and charts)

[1012] Step 9: Auto-generate sales documents

[1013] Specific operation: The server generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. The design and content of the documents are dynamically adjusted based on the information from the emotion engine.

[1014] Input: Visualization data, emotion information

[1015] Output: Auto-generated sales documents

[1016] Step 10: Provide sales materials

[1017] Specific operation: The server generates a downloadable link for the generated sales documents and sends this link to the user's device. If necessary, the server also sends the documents to the email address specified by the user.

[1018] Input: Auto-generated sales document

[1019] Output: Download link, email to be sent

[1020] (Application example 2)

[1021] 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."

[1022] Creating reports on equipment operation and maintenance in factories takes time and effort, and there is also the problem that the quality and efficiency of the reports are affected by the emotional state of the person in charge. Furthermore, when a person in charge is feeling stressed or tired, there is a demand for reports that are visually easy to understand and concise. To solve these issues, there is a need for a dynamic report generation system that responds to the user's emotions.

[1023] 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.

[1024] In this invention, the server includes means for receiving input of target equipment and period from the user, means for collecting data related to the target equipment and period from the database, and means for pre-processing the collected data, thereby enabling dynamic report generation according to the emotional state of the user.

[1025] "Covered Equipment" refers to specific machinery and equipment used within a factory.

[1026] "Time period" refers to the specific time range for collecting and analyzing data for the subject equipment.

[1027] A "means" refers to a method, device, or part of a system used to achieve a specific purpose.

[1028] A "database" refers to a digital system for systematically storing and managing various information.

[1029] "Collection" refers to the operation of gathering necessary information from a database.

[1030] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze.

[1031] "Analysis" refers to the calculation and evaluation of specific indicators and trends based on pre-processed data.

[1032] "Visualization" refers to displaying the results of data analysis in a visually easy-to-understand form (for example, graphs or charts).

[1033] "Automatic generation" refers to the system automatically creating materials in a specified format.

[1034] "Emotional state" refers to the user's psychological and emotional state, which is analyzed from the user's facial expressions, tone of voice, input text, etc.

[1035] "Dynamic adjustment" refers to changing the content or format of materials in real time according to specific conditions or circumstances.

[1036] "Providing" refers to the operation of handing over the generated materials to the user.

[1037] This invention is a system that automatically generates reports on the maintenance and operation of machinery and equipment used in factories. The system accepts input from users about the equipment and period of time in question, collects related data from a database, and preprocesses, analyzes, and visualizes that data. Furthermore, the system can analyze the user's emotional state and dynamically adjust the report content and format based on the user's emotion.

[1038] Hardware and Software Use

[1039] The following hardware and software are used to implement the present invention.

[1040] 1. Device:

[1041] A device used by a user to input information (e.g., smartphone, tablet, dedicated touch panel terminal).

[1042] 2. Server:

[1043] A central server for performing data collection, pre-processing, analysis, visualization, and report generation.

[1044] 3. Database:

[1045] A database for storing various information about equipment in a factory (e.g., customer management system, sales management system, enterprise resource planning system).

[1046] 4. Emotion Engine:

[1047] A software module (e.g., EmotionEngine) for analyzing a user's emotional state from facial expressions, tone of voice, and input text.

[1048] Data processing and calculation

[1049] 1. Data Collection:

[1050] The server receives information about the equipment and period entered by the user from the terminal, and collects data such as related maintenance logs, operating hours, and failure history from the database.

[1051] 2. Pretreatment:

[1052] Cleanse the data, impute missing values, normalize, and prepare it in a format suitable for analysis.

[1053] 3. Data Analysis:

[1054] Key indicators such as repair frequency, availability rate, and failure trends are calculated, and heat maps and line graphs are generated as needed.

[1055] 4. Emotion analysis:

[1056] The emotion engine analyzes the user's emotional state in real time to determine how stressed or tired they are.

[1057] 5. Report Generation:

[1058] Based on the analysis results, a report is automatically generated that reflects the user's emotional state. For example, if the user is nervous, the report will be presented in a simpler, more visually understandable format.

[1059] Specific examples

[1060] Suppose a user wants to create a maintenance report for a large machine tool in a factory. The user enters the ID of the target machine and a period (e.g., Q1 2023) on their device. If the emotion engine detects the user's state of tension, the server collects the necessary information from the database, preprocesses, and analyzes the data. It then generates a simple report that reflects the user's state of tension and provides it to the user. Through this process, the user can obtain the necessary report efficiently and without stress.

[1061] Prompt Sentence Examples

[1062] Enter the machine ID: "MXT-2001"

[1063] Enter the start date of the period (YYYY-MM-DD): "2023-01-01"

[1064] Enter the end date of the period (YYYY-MM-DD): "2023-03-31"

[1065] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1066] Step 1:

[1067] The terminal accepts the ID of the target device and the start and end dates of the period as input from the user. The input data is sent to the system and saved on the server. The input here is the ID of the target device and the period, and the necessary data is collected based on that.

[1068] Step 2:

[1069] The server collects data such as related maintenance logs, operating hours, and failure history from the database based on the ID and period information of the target equipment received from the terminal. The collected data is prepared as a preliminary step for data analysis. The input here is the ID and period of the target equipment, and the corresponding output is the collected raw data.

[1070] Step 3:

[1071] The server preprocesses the collected data. Preprocessing includes data cleansing, missing value imputation, and normalization. Cleansing removes unnecessary or inconsistent data, and missing value imputation maintains data integrity. Normalization standardizes the data format. The input here is raw data, and the output is preprocessed data.

[1072] Step 4:

[1073] The server analyzes the preprocessed data. Specifically, it calculates key indicators such as repair frequency, availability rate, and failure trends, and generates visualized data such as heat maps and line graphs. The input here is the preprocessed data, and the output is the analysis results and visualized data.

[1074] Step 5:

[1075] The emotion engine analyzes the user's facial expressions and tone of voice in real time from the device to determine their emotional state. The input here is raw data on the user's emotional state, and the output is information on the determined emotional state.

[1076] Step 6:

[1077] The server dynamically adjusts the content and format of the report based on the user's emotional state. For example, if the user is nervous, it generates a simpler, more visually understandable report. The inputs here are the analysis results and the user's emotional state, and the output is a dynamically adjusted draft report.

[1078] Step 7:

[1079] The server automatically generates a final report based on the adjusted draft report and saves it in the specified format (e.g. PDF). The input here is the draft report, and the output is the final report file.

[1080] Step 8:

[1081] The terminal provides the final report file to the user, who can then review the report on the terminal and download or print it. The input at this stage is the final report file, and the output is a download link or file provided to the user.

[1082] The above is the flow of processing in the system for realizing the application example.

[1083] 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.

[1084] 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.

[1085] 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.

[1086] [Fourth embodiment]

[1087] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1088] 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.

[1089] 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).

[1090] 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.

[1091] 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.

[1092] 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).

[1093] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1094] 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.

[1095] 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.

[1096] 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.

[1097] 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.

[1098] 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.

[1099] 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."

[1100] The present invention relates to a system for automatically generating business negotiation materials, and a specific implementation method thereof will be described in detail.

[1101] The system consists of a terminal operated by the user, a server that executes the processing, and a database required to create business negotiation materials.

[1102] First, a user logs in to the system using a terminal and specifies the target companies and target period for which business negotiation materials are to be created. The terminal then transmits this specified information to the server.

[1103] The server collects the necessary data from databases based on the received information on the target company and target period. The databases include customer relationship management (CRM), sales management systems, and enterprise resource planning (ERP) systems. This allows the collection of past sales negotiation data, sales data, customer information, product information, and more.

[1104] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[1105] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[1106] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[1107] The server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualized data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. This makes the documents consistent and easier to understand.

[1108] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[1109] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system. It will then perform data cleansing and fill in missing values, calculate the success rate of sales negotiations and average order amount, and graph past sales negotiation trends. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[1110] In this way, the present invention realizes improved efficiency and quality in creating business negotiation materials.

[1111] The processing flow will be explained below.

[1112] Step 1:

[1113] The user logs in to the system using a terminal and requests the creation of business negotiation materials. The user inputs the name of the target company and the target period.

[1114] Step 2:

[1115] The terminal transmits the input information on the target company and target period to the server.

[1116] Step 3:

[1117] The server analyzes the received request and identifies the required data.

[1118] Step 4:

[1119] The server collects data related to the target company and the target period from databases such as a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP).

[1120] Step 5:

[1121] The server performs data cleansing on the collected data, which includes removing inconsistent and duplicate data.

[1122] Step 6:

[1123] The server imputes missing data values. Missing values ​​are imputed using averages or predicted values.

[1124] Step 7:

[1125] The server performs data normalization, so that the data is in a uniform format.

[1126] Step 8:

[1127] The server calculates KPIs such as the success rate of sales negotiations and the average order amount based on the pre-processed data.

[1128] Step 9:

[1129] The server performs time series analysis based on past sales negotiation data and extracts trends.

[1130] Step 10:

[1131] The server then creates visualizations of the data based on the analysis results, which may include generating line graphs, bar graphs, pie charts, etc.

[1132] Step 11:

[1133] The server automatically generates a draft of the sales documents based on the visualized data, and the report is created in PowerPoint or PDF format.

[1134] Step 12:

[1135] The server provides the generated sales negotiation materials as a link that the user can download.

[1136] Step 13:

[1137] The user accesses the provided link through the terminal and downloads or checks the business documents.

[1138] Through the above processing flow, negotiation materials are automatically generated efficiently and quickly provided to the user.

[1139] Example 1

[1140] 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."

[1141] Creating sales documents requires a great deal of time and effort, and because the data collection, preprocessing, analysis, and visualization processes are particularly complex, a system that can perform this work quickly and accurately is needed. Furthermore, there is the problem of integrating data collected from different data sources and resolving inconsistencies, which requires a lot of time and effort.

[1142] 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.

[1143] In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for cleansing the collected data, correcting inconsistent data, and filling in missing data values, means for calculating negotiation success rates, average order amounts, customer behavior patterns, etc. using the preprocessed data, means for generating line graphs, bar graphs, pie charts, heat maps, etc. based on the calculation results and visualizing the data, means for automatically generating negotiation materials using the visualized data and exporting them in a specified format, and means for providing the automatically generated negotiation materials to the user. This enables the rapid and accurate creation of negotiation materials.

[1144] A "user" is an individual or group that operates the system and instructs the creation of business negotiation materials.

[1145] "Target company" refers to the company for which business negotiation materials are to be created.

[1146] The "target period" is a specific time range related to the creation of the sales negotiation materials.

[1147] A "database" is an information management system that systematically stores information and makes it accessible as needed.

[1148] "Cleansing" is the process of de-duplication of data, correcting inconsistent data, and filling in missing values.

[1149] The "success rate of business negotiations" is an indicator that indicates the percentage of successful business negotiations within a certain period of time.

[1150] "Average order amount" is the average order amount in business negotiations.

[1151] "Customer behavior patterns" are behavioral data such as purchases and inquiries that a customer exhibits within a specific time range.

[1152] A "line graph" is a graph in which data points are connected by straight lines, and is used to visually represent changes and trends over time.

[1153] A "bar graph" is a graph in which different categories of data are represented by the length of the bars.

[1154] A "pie chart" is a graph in which segments of a circle represent proportions of a whole.

[1155] A "heat map" is a visual representation of data values ​​using shades or hues of color.

[1156] "Business negotiation materials" are documents that record the progress and results of business negotiations and include analysis results and graphs.

[1157] "Export" is the act of outputting a generated document in a particular format.

[1158] This invention relates to a system that is comprised of a terminal operated by a user, a server that executes processing, and a database required for creating negotiation materials, and also to a method for automatically generating negotiation materials. A specific implementation method will now be described in detail.

[1159] First, the user logs in to the system using a terminal and specifies the target company and target period for creating business negotiation materials. The terminal then sends this specified information to the server. For example, if the user specifies "Company XYZ" and the period "Q1 2023," the terminal sends this as an HTTP request to the server.

[1160] Based on the received information on the target company and target period, the server collects the necessary data from databases, including customer relationship management (CRM), sales management, and enterprise resource planning (ERP) systems. The server uses a database connection pool to issue queries to these systems and collect past sales data, sales data, customer information, product information, and other information related to the target company.

[1161] The server then preprocesses the collected data, using a data cleansing tool (e.g., OpenRefine) to remove duplicates and correct inconsistent data, as well as to impute missing values ​​and normalize the data to prepare it for analysis.

[1162] Once preprocessing is complete, the server performs data analysis. Specifically, it uses data analysis libraries (e.g., Pandas and NumPy) to calculate KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns. It also performs trend analysis based on past sales negotiation data to analyze trends in success rates and seasonal fluctuations in sales.

[1163] Based on the analysis results, the server visualizes the data using visualization libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc., which facilitates visual understanding of the data.

[1164] Next, the server automatically generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. It uses Python libraries (e.g., ReportLab and pptx) to assemble the sales documents and generate documents containing the necessary information and comments.

[1165] Finally, the server provides the automatically generated business documents to the user. The server uploads the generated documents to cloud storage and generates a download link. The server sends this link to the user's device or automatically sends the documents to a specified email address as needed. The user can view, download, or print the documents through the provided link.

[1166] As a concrete example, consider the case where the user specifies the target company "XYZ Company" and the period "Q1 2023." The server collects data related to "XYZ Company" from the CRM system and ERP system, performs data cleansing, and fills in missing values. It calculates the success rate of sales negotiations and average order amount, and creates graphs of past sales negotiation trends. Finally, it automatically generates sales negotiation materials in PDF format containing these analysis results and graphs, and provides them to the user.

[1167] An example of a prompt to enter is:

[1168] "When specifying the target company and period, please collect data from CRM and ERP and automatically generate sales negotiation materials. As a specific example, let's say the target company is "XYZ Company" and the period is "Q1 2023." Please cleanse the obtained data, calculate the success rate of sales negotiations and average order amount, and generate line graphs and bar graphs. Output the final sales negotiation materials in PDF format and provide them to the user."

[1169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1170] Step 1:

[1171] The user logs into the system using a terminal. The user then enters the target company "XYZ Corporation" and the target period "Q1 2023" and presses the submit button. The terminal sends this information to the server as an HTTP request. The input includes the target company and period information, and the output passes this information to the server.

[1172] Specific operation: The user enters "XYZ Company" and "Q1 2023" into the form on the terminal and clicks the "Submit" button. The terminal sends this as an HTTP request in JSON format to the server.

[1173] Step 2:

[1174] The server accesses the database and collects the necessary data based on the target company and target period information received from the user. The input is the target company and period information, and the output is the data retrieved from the database. The server issues queries to the CRM system and ERP system to collect the corresponding data.

[1175] What happens: The server uses the database connection pool to access the CRM and ERP API endpoints, and queries to retrieve data related to "Company XYZ" and "Q1 2023."

[1176] Step 3:

[1177] The server preprocesses the collected data. The collected data may contain duplicates and inconsistencies, so cleansing is necessary. The input is raw data, and the output is cleansed data. Specifically, a data cleansing tool (e.g., OpenRefine) is used to remove duplicates, correct inconsistencies, and complete missing values.

[1178] What it does: The server uses OpenRefine to detect and remove duplicate data, correct inconsistent data, and impute missing values ​​with the mean or median.

[1179] Step 4:

[1180] The server performs data analysis using the preprocessed data. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses a data analysis library (e.g., Pandas or NumPy) to calculate the success rate of sales negotiations, average order amount, and customer behavior patterns.

[1181] What it does: Uses Pandas and NumPy to calculate aggregates, averages, and summary statistics for a dataset. Calculates win rates, average order value, and customer behavior patterns.

[1182] Step 5:

[1183] The server visualizes the analysis results. The input is the analysis results, and the output is visualized data (graphs, charts). This is done using libraries such as Matplotlib and Seaborn to generate line graphs, bar graphs, pie charts, heat maps, etc.

[1184] Specific operations: Using Matplotlib and Seaborn, the progress of sales success rates is visualized as a line graph, seasonal fluctuations in sales as a bar graph, and customer behavior patterns as pie charts and heat maps.

[1185] Step 6:

[1186] The server automatically generates sales documents based on the visualized data. The input is the visualized data and a prompt from the AI ​​model, and the output is sales documents in the specified format (e.g., PowerPoint, PDF). The documents are generated using Python libraries (e.g., ReportLab or pptx).

[1187] What it does: The server uses the ReportLab and pptx libraries to automatically generate a sales presentation, which includes analysis results, graphs, and automatically generated comments.

[1188] Step 7:

[1189] The server generates a download link for the automatically generated business documents and sends it to the user's device. The input is the generated business documents, and the output is a download link or email. The user receives this and downloads or prints the documents.

[1190] Specific operation: The server uploads the generated sales documents to cloud storage and generates a download link. The link is sent to the user via email. The user clicks the link to download the documents.

[1191] (Application example 1)

[1192] 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."

[1193] Logistics centers handle many types of data and are required to quickly organize and analyze it and provide appropriate reports to relevant parties. However, performing the entire process of data collection, preprocessing, analysis, visualization, and report creation manually is time-consuming and prone to errors. It is also important to report the analysis results in a visually easy-to-understand format, but this is also time-consuming. As such, there is a need to solve the issues of efficient and accurate data processing and report creation.

[1194] 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.

[1195] In this invention, the server includes: means for accepting input of a target company and a period from a user; means for collecting data related to the target company and the period from a database; means for preprocessing the collected data; means for analyzing the preprocessed data; means for visualizing data based on the analysis results; means for automatically generating business reports using the visualized data; means for providing the automatically generated business reports to a user; means for generating a link for displaying the generated reports and sending it to a user terminal; means for sending the reports by email as needed; and means for the reports to include inventory turnover, delivery time, and pick rate. This automates data processing and report generation at a logistics center, enabling efficient and accurate business operations.

[1196] "User terminal" means a device used by a user to view and manipulate commercial reporting materials, including a smartphone, tablet, smart glasses, etc.

[1197] "Target company" refers to the company that is the subject of data analysis and report creation for the invention.

[1198] "Time period" refers to a specific time range for data collection, analysis, and reporting.

[1199] A "database" is a system for storing data, which is composed of a customer management system, a transportation management system, an enterprise resource planning system, and the like.

[1200] "Preprocessing" refers to the process of removing duplicates, filling in missing values, and normalizing the collected data.

[1201] "Analysis" refers to the process of calculating specific indicators (KPIs) based on preprocessed data and interpreting the data based on them.

[1202] "Visualization" refers to the process of converting analytical results into a visually understandable format such as a line graph, bar graph, pie chart, or heat map.

[1203] "Commercial reporting materials" are reports containing data analysis results for the target company and period, and are provided in formats such as PDF or PowerPoint.

[1204] "Displayable link" refers to a link sent to a user's device that the user can access to view and download the report materials.

[1205] "Inventory turnover rate" refers to an indicator that shows the speed at which inventory is replaced at a logistics center.

[1206] "Delivery time" refers to an indicator that measures the time from when an order is received to when the product is delivered.

[1207] "Pick rate" refers to an indicator that indicates the frequency with which products are accurately picked up at a logistics center.

[1208] This invention relates to a system for automating data processing and report creation in a logistics center. The system is composed of a user terminal, a server that executes processing, and a database.

[1209] First, the user logs into the system using a terminal and specifies the target company and target period. The specified information is sent from the terminal to the server. Based on this information, the server collects the necessary data from the database. The database includes a customer relationship management system (CRM), a transportation management system (TMS), and an enterprise resource planning system (ERP). This allows the collection of past logistics data, delivery data, customer information, inventory information, and more.

[1210] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[1211] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as inventory turnover, average delivery time, and pick rate, and performs trend analysis based on past logistics data. This allows the operational status of the logistics center and areas for improvement to be identified.

[1212] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data. Using this visualized data, a draft of the business report is created. Based on the visualized data, the server automatically generates the business report in the specified format (e.g., PowerPoint, PDF).

[1213] The automatically generated commercial report is generated as a displayable link and sent to the user's device. The user can view, download, or print the commercial report via the provided link. The system also has a function to automatically send the report to a specified email address, if necessary.

[1214] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023," the server will collect past logistics and delivery data related to "XYZ Company" from the CRM system, TMS, and ERP system. It will then perform data cleansing and fill in missing values, calculate inventory turnover and average delivery time, and graph past logistics trends. Finally, it will automatically generate a business report containing these analysis results and graphs and provide it to the user.

[1215] Example prompt sentence:

[1216] Target company: “XYZ Company”

[1217] Target period: "Q1 2023"

[1218] Collected data: CRM data, TMS data, ERP data

[1219] Essential KPIs: Inventory turnover, delivery time, pick rate

[1220] Report format: PDF

[1221] In this way, the present invention improves the efficiency and quality of data processing and report generation in a logistics center.

[1222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1223] Step 1:

[1224] The system accepts input of target companies and periods from the user. The user logs into the system using a terminal and inputs the target company (e.g., "XYZ Company") and target period (e.g., "Q1 2023"). The terminal sends this specified information to the server. The input is received as manual data from the user, and the output is the specified information for the target company and period.

[1225] Step 2:

[1226] Data related to the target company and period is collected from the database. Based on the received information on the target company and period, the server collects the necessary data from the CRM system, TMS, and ERP system. This includes past logistics data, delivery data, customer information, inventory information, etc. The input is the specified information on the target company and period, and the output is the collected data from each system.

[1227] Step 3:

[1228] The collected data is preprocessed. The server cleanses the data, removes duplicates and inconsistencies, and imputes missing values. It also normalizes the data and prepares it in a format suitable for analysis. The input is the collected data, and the output is the cleansed and normalized data.

[1229] Step 4:

[1230] The preprocessed data is analyzed. The server calculates KPIs such as inventory turnover, delivery time, and pick rate based on the cleansed and normalized data. It also performs trend analysis based on past logistics data. The input is the preprocessed data, and the output is the results of various KPIs and trend analysis.

[1231] Step 5:

[1232] The server visualizes the data based on the analysis results. The server visually represents the analysis results in the form of line graphs, bar graphs, pie charts, heat maps, etc. This makes it easier to understand the data. The input is the analysis results, and the output is the generated graphs and charts.

[1233] Step 6:

[1234] The visualized data is used to automatically generate business reports. The server generates business reports in a specified format (e.g., PDF, PowerPoint) based on the visualized data. The input is the visualized data, and the output is the business report.

[1235] Step 7:

[1236] Automatically generated commercial report materials are provided to users. The server sends the generated report materials to the user's terminal as a displayable link. The user can check the report materials via this link and download or print them. In addition, a function is provided to automatically send the materials to a specified email address, if necessary. The input is the generated report materials, and the output is a link that can be viewed on the user's terminal or an automatically sent email.

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

[1238] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[1239] The system consists of a terminal operated by the user, a server that processes various data, and a database. An emotion engine is also built into the terminal and server.

[1240] First, the user logs into the system using a terminal and requests the creation of business documents. The user inputs the name of the target company and the target period. At this time, the emotion engine recognizes the user's emotions in real time. The emotion engine can grasp the user's emotional state by analyzing the user's facial expressions, tone of voice, and the content of the input text.

[1241] The terminal sends the user's emotional information along with the input information to the server. The server then collects the necessary data from a database based on the received information on the target company and target period. The database includes a customer relationship management system (CRM), a sales management system, and an enterprise resource planning system (ERP), which collects past sales negotiation data, sales data, customer information, product information, and other data.

[1242] The server then preprocesses the collected data, cleansing it to remove duplicates and inconsistencies, filling in missing values, and normalizing it to prepare it for analysis.

[1243] Once preprocessing is complete, the server performs data analysis. Specifically, it calculates KPIs such as the success rate of sales negotiations, average order amount, and customer behavior patterns, and performs trend analysis based on past sales negotiation data. This makes it possible to understand the sales negotiation history with the target company and seasonal fluctuations in sales.

[1244] Based on the analysis results, the server visualizes the data, generating line graphs, bar graphs, pie charts, heat maps, and other visualizations to facilitate visual understanding of the data. These visualizations are then used to create drafts of sales documents.

[1245] The server automatically generates sales documents in the specified format (e.g., PowerPoint or PDF) based on the visualization data. The documents include analysis results, key numerical indicators, graphs, charts, and automatically generated comments. The emotion engine dynamically adjusts the content and design of the documents according to the user's emotional state. For example, if the user is feeling stressed, the system will generate documents that are simpler and easier to read.

[1246] Finally, the server provides the automatically generated business documents to the user. Specifically, it generates a downloadable link for the documents and sends it to the user's device. It also has a function to automatically send the documents to a specified email address, if necessary. The user can view, download, or print the documents via the provided link.

[1247] As a specific example, if a user specifies the target company "XYZ Company" and the period "Q1 2023" and the emotion engine detects the user's tension, the server will collect past sales negotiation data and sales data related to "XYZ Company" from the CRM system and ERP system, perform data cleansing, and calculate the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it will generate simple, visually easy-to-understand materials that will reduce stress. Finally, it will automatically generate sales negotiation materials including these analysis results and graphs and provide them to the user.

[1248] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[1249] The processing flow will be explained below.

[1250] Step 1:

[1251] The user logs into the system using a terminal and requests the creation of business documents. The user enters the name of the target company and the target period. At this time, the emotion engine analyzes the user's facial expressions, tone of voice, and text input in real time through the terminal's built-in camera, microphone, and keyboard input, and recognizes the user's emotions.

[1252] Step 2:

[1253] The terminal transmits the recognized emotion information of the user to the server together with the input information on the target company and target period.

[1254] Step 3:

[1255] The server analyzes the received request and identifies the required data relating to the target company and time period.

[1256] Step 4:

[1257] The server accesses each database (customer management system, sales management system, enterprise resource planning system) and collects data related to the specified target company and target period.

[1258] Step 5:

[1259] After collecting the data, the server performs data cleansing, which includes removing duplicate data and correcting inconsistent data.

[1260] Step 6:

[1261] The server completes the missing values ​​in the collected data by predicting and completing the missing values ​​using statistical methods and machine learning algorithms.

[1262] Step 7:

[1263] Once the data is cleaned, the server normalizes it, unifying data in different formats and making it suitable for analysis.

[1264] Step 8:

[1265] The server uses the pre-processed data to perform data analysis, specifically calculating important KPIs such as success rate, average order value, and customer behavior patterns.

[1266] Step 9:

[1267] The server performs time-series analysis based on past sales negotiation data to extract trends, allowing analysis of sales negotiation history with target companies and seasonal fluctuations in sales.

[1268] Step 10:

[1269] The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, and other graphs to facilitate visual understanding of the data.

[1270] Step 11:

[1271] The server automatically generates a draft of a sales document based on the visualized data. The content and format of the document are dynamically adjusted based on the user's emotional data collected by the emotion engine. For example, if the user is nervous, the structure of the document is simplified and visually intuitive elements are enhanced.

[1272] Step 12:

[1273] The server provides the user with automatically generated business documents in a specified format (e.g., PowerPoint, PDF) and sends them to the user's device as a trusted link.

[1274] Step 13:

[1275] Users can view the sales documents through the provided link and download, print, or email them. By viewing the documents generated by the emotion engine, users can reduce stress and tension, increasing the success rate of sales negotiations.

[1276] Through the above processing flow, business negotiation materials are automatically generated efficiently and are provided in a form that takes into consideration the user's feelings.

[1277] Example 2

[1278] 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."

[1279] Conventional sales document creation systems require users to input data on target companies and time periods, and then automatically generate documents based on that data. However, they were unable to consider the user's emotional state. This meant that they lacked the flexibility to adjust the content and format of the documents depending on the user's emotional state. Furthermore, there was a problem with the design of sales documents being inappropriate when the user was emotionally stressed.

[1280] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting input of a target company and a period from a user, means for collecting data related to the target company and the period from a database, means for preprocessing the collected data, means for analyzing the preprocessed data, means for visualizing data based on the analysis results, means for automatically generating negotiation materials using the visualized data, means for recognizing the user's emotions, means for dynamically adjusting the content and format of the negotiation materials based on the user's emotional information, and means for providing the automatically generated negotiation materials to the user. This enables flexible and efficient creation of negotiation materials that take the user's emotional state into consideration.

[1281] "User" refers to a person who accesses and operates the system.

[1282] "Terminal" refers to a device such as a computer or smartphone that is operated by a user.

[1283] A "server" refers to a computer system that processes requests from multiple terminals and performs data collection, analysis, document generation, etc.

[1284] The term "target company" refers to a specific company that the user designates in order to create business negotiation materials.

[1285] "Period" refers to a specific time range for extracting data necessary for creating sales documents.

[1286] A "database" is a system for storing information, and includes customer management systems, sales management systems, enterprise resource planning systems, and the like.

[1287] An "emotion engine" refers to a system that recognizes a user's emotional state by analyzing their facial expressions, tone of voice, and input text.

[1288] "Data cleansing" refers to the process of removing duplicates and inconsistencies in data and filling in missing values.

[1289] "Data normalization" refers to the process of organizing data based on certain rules and making it consistent.

[1290] "KPI" stands for Key Performance Indicator and refers to key indicators such as success rate of sales negotiations, average order amount, and customer behavior patterns.

[1291] "Visualization" refers to converting the results of data analysis into a visually easy-to-understand format (e.g., graphs, charts).

[1292] "Business negotiation materials" refers to materials that are automatically generated based on collected and analyzed data and are used in business negotiations.

[1293] A "prompt sentence" refers to an instruction sentence input to a generative AI model.

[1294] This invention relates to a system that accepts input of target companies and time periods from users, collects related data from a database, analyzes and visualizes the data after preprocessing, and automatically generates negotiation materials based on that data. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the content and format of the negotiation materials can be dynamically adjusted.

[1295] System Configuration

[1296] Terminal: A device operated by a user, such as a computer or smartphone.

[1297] Server: A computer system that processes, analyzes, and generates various data.

[1298] Database: Data storage consisting of customer relationship management (CRM), sales management, enterprise resource planning (ERP), etc.

[1299] Emotion engine: Software that analyzes a user's facial expressions, tone of voice, and input text to recognize emotions.

[1300] Program processing flow

[1301] 1. A user operates a terminal and logs in to the system:

[1302] A user accesses the system at a terminal and authenticates by entering a username and password.

[1303] If authentication is successful, the user can access the main screen of the system.

[1304] 2. User enters target information:

[1305] The user fills in the required data in a form to input the name of the target company and the period.

[1306] 3. Emotion Recognition with Emotion Engine:

[1307] The device's built-in emotion engine analyzes the user's facial expressions, tone of voice, and input text to grasp their emotional state in real time.

[1308] The analysis results are output as a probability-based emotional state (tension, joy, stress, etc.).

[1309] 4. Data transmission:

[1310] The terminal generates a data packet containing the target company name, period, and emotion information and transmits it to the server.

[1311] 5. Data Collection:

[1312] Based on the received company name and period information, the server collects relevant data from databases such as customer relationship management (CRM), sales management systems, and enterprise resource planning systems (ERP).

[1313] 6. Data Preprocessing:

[1314] The server cleanses the collected data, removing duplicates and inconsistencies and filling in missing data.

[1315] Normalize the data into a format suitable for analysis.

[1316] 7. Data Analysis:

[1317] Based on the pre-processed data, the server calculates key performance indicators (KPIs) such as success rate, average order amount, and customer behavior patterns.

[1318] Conduct trend analysis to understand seasonal fluctuations and sales history.

[1319] 8. Data Visualization:

[1320] The server visualizes the analysis results in a visually easy-to-understand format (line graphs, bar graphs, pie charts, heat maps, etc.).

[1321] 9. Automatic generation of sales documents:

[1322] The server generates business documents in a specified format (e.g., PowerPoint, PDF) based on the visualized data.

[1323] The content and design of materials are dynamically adjusted based on information from the emotion engine. For example, if a user is feeling stressed, simple, visually easy-to-understand materials are provided.

[1324] 10. Provision of business materials:

[1325] The server generates a downloadable link for the generated business negotiation materials and transmits the link to the user's terminal.

[1326] If necessary, the system also has the function to automatically send documents to a specified email address.

[1327] Specific examples

[1328] When a user specifies the target company "Company A" and the period "Q1 2023" and the emotion engine detects the user's tension, the server collects past sales negotiation data and sales data related to "Company A" from the CRM system and ERP system, cleans the data, and calculates the success rate of sales negotiations and average order amount. Then, based on the information from the emotion engine, it generates simple, visually easy-to-understand materials that reduce stress. Finally, it automatically generates sales negotiation materials including these analysis results and graphs and provides them to the user.

[1329] Prompt Sentence Examples

[1330] "Please create a sales document for Company A for the period Q1 2023. Because users are feeling nervous, please create a simple and visually easy-to-understand format."

[1331] In this way, the present invention realizes an improvement in the efficiency and quality of the creation of business negotiation materials, and further enables flexible creation of materials that take into account the emotional state of the user.

[1332] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1333] Step 1: User login and input of target information

[1334] Specific operation: The user accesses the system login screen using a terminal and enters the username and password. After successful authentication, the system's main screen is displayed.

[1335] Input: Username, Password

[1336] Output: Main screen if login is successful, authentication error message if unsuccessful

[1337] Step 2: Enter the target company and period

[1338] Specific operation: The user enters the name of the target company and the period, then submits the input form. The entered information is temporarily saved on the device.

[1339] Input: Target company name, period

[1340] Output: A data packet containing the target company name and time period

[1341] Step 3: Emotion Recognition

[1342] How it works: The emotion engine analyzes the user's facial expressions, tone of voice, and input text in real time, and outputs a probability-based emotional state. The analysis results are stored on the device.

[1343] Input: User facial expressions, tone of voice, input text

[1344] Output: Emotional state (e.g., nervous, happy, stressed, etc.)

[1345] Step 4: Send data

[1346] Specific operation: The device generates a data packet containing the target company name, period, and emotion information and sends it to the server.

[1347] Input: Target company name, period, sentiment information

[1348] Output: Data packet sent to the server

[1349] Step 5: Data collection

[1350] Specific operation: The server receives the data packet and extracts the necessary data from the database (CRM, sales management system, ERP, etc.) based on the target company name and period.

[1351] Input: Target company name, period

[1352] Output: Collected sales opportunity data, sales data, and customer information

[1353] Step 6: Data Preprocessing

[1354] What it does: It cleanses the data collected by the server, removing duplicates and inconsistencies, filling in missing data, and normalizing the data into a format suitable for analysis.

[1355] Input: Collected data

[1356] Output: Cleansed and normalized data

[1357] Step 7: Data analysis

[1358] Specific operation: The server uses the preprocessed data to calculate KPIs such as success rate, average order amount, and customer behavior patterns, and performs trend analysis.

[1359] Input: Normalized data

[1360] Output: Analysis results (sales success rate, average order amount, trend data, etc.)

[1361] Step 8: Data Visualization

[1362] Specific operation: The server visualizes the data based on the analysis results, generating line graphs, bar graphs, pie charts, heat maps, etc.

[1363] Input: Analysis results

[1364] Output: Visualized data (graphs and charts)

[1365] Step 9: Auto-generate sales documents

[1366] Specific operation: The server generates sales documents in the specified format (e.g., PowerPoint, PDF) based on the visualization data. The design and content of the documents are dynamically adjusted based on the information from the emotion engine.

[1367] Input: Visualization data, emotion information

[1368] Output: Auto-generated sales documents

[1369] Step 10: Provide sales materials

[1370] Specific operation: The server generates a downloadable link for the generated sales documents and sends this link to the user's device. If necessary, the server also sends the documents to the email address specified by the user.

[1371] Input: Auto-generated sales document

[1372] Output: Download link, email to be sent

[1373] (Application example 2)

[1374] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1375] Creating reports on equipment operation and maintenance in factories takes time and effort, and there is also the problem that the quality and efficiency of the reports are affected by the emotional state of the person in charge. Furthermore, when a person in charge is feeling stressed or tired, there is a demand for reports that are visually easy to understand and concise. To solve these issues, there is a need for a dynamic report generation system that responds to the user's emotions.

[1376] 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.

[1377] In this invention, the server includes means for receiving input of target equipment and period from the user, means for collecting data related to the target equipment and period from the database, and means for pre-processing the collected data, thereby enabling dynamic report generation according to the emotional state of the user.

[1378] "Covered Equipment" refers to specific machinery and equipment used within a factory.

[1379] "Time period" refers to the specific time range for collecting and analyzing data for the subject equipment.

[1380] A "means" refers to a method, device, or part of a system used to achieve a specific purpose.

[1381] A "database" refers to a digital system for systematically storing and managing various information.

[1382] "Collection" refers to the operation of gathering necessary information from a database.

[1383] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze.

[1384] "Analysis" refers to the calculation and evaluation of specific indicators and trends based on pre-processed data.

[1385] "Visualization" refers to displaying the results of data analysis in a visually easy-to-understand form (for example, graphs or charts).

[1386] "Automatic generation" refers to the system automatically creating materials in a specified format.

[1387] "Emotional state" refers to the user's psychological and emotional state, which is analyzed from the user's facial expressions, tone of voice, input text, etc.

[1388] "Dynamic adjustment" refers to changing the content or format of materials in real time according to specific conditions or circumstances.

[1389] "Providing" refers to the operation of handing over the generated materials to the user.

[1390] This invention is a system that automatically generates reports on the maintenance and operation of machinery and equipment used in factories. The system accepts input from users about the equipment and period of time in question, collects related data from a database, and preprocesses, analyzes, and visualizes that data. Furthermore, the system can analyze the user's emotional state and dynamically adjust the report content and format based on the user's emotion.

[1391] Hardware and Software Use

[1392] The following hardware and software are used to implement the present invention.

[1393] 1. Device:

[1394] A device used by a user to input information (e.g., smartphone, tablet, dedicated touch panel terminal).

[1395] 2. Server:

[1396] A central server for performing data collection, pre-processing, analysis, visualization, and report generation.

[1397] 3. Database:

[1398] A database for storing various information about equipment in a factory (e.g., customer management system, sales management system, enterprise resource planning system).

[1399] 4. Emotion Engine:

[1400] A software module (e.g., EmotionEngine) for analyzing a user's emotional state from facial expressions, tone of voice, and input text.

[1401] Data processing and calculation

[1402] 1. Data Collection:

[1403] The server receives information about the equipment and period entered by the user from the terminal, and collects data such as related maintenance logs, operating hours, and failure history from the database.

[1404] 2. Pretreatment:

[1405] Cleanse the data, impute missing values, normalize, and prepare it in a format suitable for analysis.

[1406] 3. Data Analysis:

[1407] Key indicators such as repair frequency, availability rate, and failure trends are calculated, and heat maps and line graphs are generated as needed.

[1408] 4. Emotion analysis:

[1409] The emotion engine analyzes the user's emotional state in real time to determine how stressed or tired they are.

[1410] 5. Report Generation:

[1411] Based on the analysis results, a report is automatically generated that reflects the user's emotional state. For example, if the user is nervous, the report will be presented in a simpler, more visually understandable format.

[1412] Specific examples

[1413] Suppose a user wants to create a maintenance report for a large machine tool in a factory. The user enters the ID of the target machine and a period (e.g., Q1 2023) on their device. If the emotion engine detects the user's state of tension, the server collects the necessary information from the database, preprocesses, and analyzes the data. It then generates a simple report that reflects the user's state of tension and provides it to the user. Through this process, the user can obtain the necessary report efficiently and without stress.

[1414] Prompt Sentence Examples

[1415] Enter the machine ID: "MXT-2001"

[1416] Enter the start date of the period (YYYY-MM-DD): "2023-01-01"

[1417] Enter the end date of the period (YYYY-MM-DD): "2023-03-31"

[1418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1419] Step 1:

[1420] The terminal accepts the ID of the target device and the start and end dates of the period as input from the user. The input data is sent to the system and saved on the server. The input here is the ID of the target device and the period, and the necessary data is collected based on that.

[1421] Step 2:

[1422] The server collects data such as related maintenance logs, operating hours, and failure history from the database based on the ID and period information of the target equipment received from the terminal. The collected data is prepared as a preliminary step for data analysis. The input here is the ID and period of the target equipment, and the corresponding output is the collected raw data.

[1423] Step 3:

[1424] The server preprocesses the collected data. Preprocessing includes data cleansing, missing value imputation, and normalization. Cleansing removes unnecessary or inconsistent data, and missing value imputation maintains data integrity. Normalization standardizes the data format. The input here is raw data, and the output is preprocessed data.

[1425] Step 4:

[1426] The server analyzes the preprocessed data. Specifically, it calculates key indicators such as repair frequency, availability rate, and failure trends, and generates visualized data such as heat maps and line graphs. The input here is the preprocessed data, and the output is the analysis results and visualized data.

[1427] Step 5:

[1428] The emotion engine analyzes the user's facial expressions and tone of voice in real time from the device to determine their emotional state. The input here is raw data on the user's emotional state, and the output is information on the determined emotional state.

[1429] Step 6:

[1430] The server dynamically adjusts the content and format of the report based on the user's emotional state. For example, if the user is nervous, it generates a simpler, more visually understandable report. The inputs here are the analysis results and the user's emotional state, and the output is a dynamically adjusted draft report.

[1431] Step 7:

[1432] The server automatically generates a final report based on the adjusted draft report and saves it in the specified format (e.g. PDF). The input here is the draft report, and the output is the final report file.

[1433] Step 8:

[1434] The terminal provides the final report file to the user, who can then review the report on the terminal and download or print it. The input at this stage is the final report file, and the output is a download link or file provided to the user.

[1435] The above is the flow of processing in the system for realizing the application example.

[1436] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1437] 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.

[1438] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1439] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1440] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1441] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1442] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1443] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1444] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1445] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1446] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1447] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1448] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1449] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1450] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1451] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1452] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1453] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1454] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1455] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1456] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1457] The following is further disclosed regarding the above embodiment.

[1458] (Claim 1)

[1459] A means for accepting input of target companies and periods from a user;

[1460] a means for collecting data relating to the target company and period from the database;

[1461] a means for pre-processing the collected data;

[1462] means for analyzing the preprocessed data;

[1463] A means of visualizing data based on the analysis results,

[1464] A means for automatically generating business negotiation materials using the visualized data;

[1465] A means for providing automatically generated business negotiation materials to a user;

[1466] A system including:

[1467] (Claim 2)

[1468] 2. The system of claim 1, wherein the data collected from the database includes data from a customer management system, a sales management system, and an enterprise resource planning system.

[1469] (Claim 3)

[1470] 2. The system of claim 1, wherein the preprocessing means performs data cleansing, missing value imputation, and data normalization.

[1471] "Example 1"

[1472] (Claim 1)

[1473] A means for accepting input of target companies and periods from a user;

[1474] a means for collecting data relating to the target company and period from the database;

[1475] A means for cleansing the collected data, correcting inconsistent data, and completing missing data values;

[1476] Using the pre-processed data, a means to calculate the success rate of negotiations, average order amount, customer behavior patterns, etc.

[1477] A means to visualize data by generating line graphs, bar graphs, pie charts, heat maps, etc. based on the calculation results,

[1478] A means to automatically generate sales documents using visualized data and export them in a specified format.

[1479] A means for providing automatically generated business negotiation materials to a user;

[1480] A system including:

[1481] (Claim 2)

[1482] 2. The system of claim 1, wherein the data collected from the database includes data from a customer management system, a sales management system, and an enterprise resource planning system.

[1483] (Claim 3)

[1484] 2. The system according to claim 1, wherein the cleansing means performs data duplication removal, data inconsistency correction, missing value completion, and data normalization.

[1485] "Application Example 1"

[1486] (Claim 1)

[1487] A means for accepting input of target companies and periods from a user;

[1488] a means for collecting data relating to the target company and period from the database;

[1489] a means for pre-processing the collected data;

[1490] means for analyzing the preprocessed data;

[1491] A means of visualizing data based on the analysis results,

[1492] A means for automatically generating business report materials using the visualized data;

[1493] means for providing automatically generated business reporting materials to a user;

[1494] means for generating a link that enables the generated report material to be displayed and transmitting the link to a user terminal;

[1495] A means to email reporting materials as needed;

[1496] the reporting material includes inventory turnover, delivery time, and pick rate;

[1497] A system including:

[1498] (Claim 2)

[1499] 2. The system of claim 1, wherein the data collected from the database includes data from a customer management system, a transportation management system, and an enterprise resource planning system.

[1500] (Claim 3)

[1501] 2. The system of claim 1, wherein the preprocessing means performs data cleansing, missing value imputation, and data normalization.

[1502] "Example 2: Combining Emotion Engines"

[1503] (Claim 1)

[1504] A means for accepting input of target companies and periods from a user;

[1505] a means for collecting data relating to the target company and period from the database;

[1506] a means for pre-processing the collected data;

[1507] means for analyzing the preprocessed data;

[1508] A means of visualizing data based on the analysis results,

[1509] A means for automatically generating business negotiation materials using the visualized data;

[1510] means for recognizing a user's emotion;

[1511] A means for dynamically adjusting the content and format of the business negotiation materials based on the user's emotional information;

[1512] A means for providing automatically generated business negotiation materials to a user;

[1513] A system including:

[1514] (Claim 2)

[1515] 2. The system of claim 1, wherein the data collected from the database includes data from a customer management system, a sales management system, and an enterprise resource planning system.

[1516] (Claim 3)

[1517] 2. The system of claim 1, wherein the preprocessing means performs data cleansing, missing value imputation, and data normalization.

[1518] "Application example 2 when combining emotion engines"

[1519] (Claim 1)

[1520] means for receiving input of target equipment and period from a user;

[1521] means for collecting data relating to the target equipment and time period from the database;

[1522] a means for pre-processing the collected data;

[1523] means for analyzing the preprocessed data;

[1524] A means of visualizing data based on the analysis results,

[1525] A means for automatically generating business negotiation materials using the visualized data;

[1526] means for analyzing the emotional state of a user;

[1527] a means of dynamically adjusting the content and format of materials depending on emotional state;

[1528] A means for providing automatically generated business negotiation materials to a user;

[1529] A system including:

[1530] (Claim 2)

[1531] 2. The system of claim 1, wherein the data collected from the database includes data from a customer management system, a sales management system, and an enterprise resource planning system.

[1532] (Claim 3)

[1533] 2. The system of claim 1, wherein the preprocessing means performs data cleansing, missing value imputation, and data normalization. [Explanation of symbols]

[1534] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for accepting input of target companies and periods from a user; a means for collecting data relating to the target company and period from the database; a means for pre-processing the collected data; means for analyzing the preprocessed data; A means of visualizing data based on the analysis results, A means for automatically generating business negotiation materials using the visualized data; A means for providing automatically generated business negotiation materials to a user; A system including:

2. 2. The system of claim 1, wherein the data collected from the databases includes data from a customer management system, a sales management system, and an enterprise resource planning system.

3. 2. The system of claim 1, wherein the preprocessing means cleanses the data, imputes missing values, and normalizes the data.

Images