system

Abstract

Provide a system. A means for collecting request data; A means for analyzing the collected data using a natural language processing engine and extracting key information; A means for generating a business process flow model based on the extracted key information; A means for identifying waste and points for improvement based on an analysis of the generated business process flow model; A means of proposing improvement proposals for identified waste and improvement points, A means for generating and outputting reports based on improvement proposals and business process flow models; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern companies, business processes are complex and diverse, requiring efficient business processing. However, business processing flows are often inefficient and contain unnecessary steps. Furthermore, insufficient collaboration between departments leads to delays and poor quality in business operations. These situations contribute to a decline in a company's competitiveness. The present invention aims to solve the above problems by providing a system for visualizing and streamlining business processing flows. [Means for solving the problem]

[0005] The present invention solves the aforementioned problems by providing a system including the following means: means for collecting request data; means for analyzing the collected data using a natural language processing engine and extracting key information; means for generating a business process flow model based on the extracted key information; means for identifying waste and areas for improvement based on an analysis of the generated business process flow model; means for presenting improvement proposals for the identified waste and areas for improvement; and means for generating and outputting a report based on the improvement proposals and the business process flow model. This system enables visualization and efficiency improvements of business process flow models, thereby reducing waste and improving quality.

[0006] "Request data" refers to data that includes instructions and application details related to business processing.

[0007] A "natural language processing engine" is a software engine for analyzing text data and extracting structured information.

[0008] "Key information" refers to important information items in business processing, including, for example, deadlines, persons in charge, and content.

[0009] A "business process flow model" is a model that visually represents a series of business procedures and processes.

[0010] "Waste" refers to inefficient and unnecessary steps or tasks in business processes.

[0011] "Improvement points" refer to areas in business processing where efficiency and quality can be improved.

[0012] "Improvement proposals" refer to specific solutions or suggestions for addressing waste or areas for improvement.

[0013] A "report" is a report generated based on a business process flow model and improvement proposals.

[0014] "Analytical tools" are methods or functions for analyzing data or information and finding meaning and patterns. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] System Overview

[0037] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[0038] Program processing description

[0039] 1. Data Collection

[0040] Subject: Server

[0041] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or designated folders. This makes it possible to comprehensively collect request data related to all business processes.

[0042] 2. Data Analysis

[0043] Subject: Server

[0044] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations, allowing it to be used efficiently.

[0045] 3. Flow Modeling

[0046] Subject: Server

[0047] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. This model is displayed graphically using a flow design tool.

[0048] 4. Identifying waste and areas for improvement

[0049] Subject: AI

[0050] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps, explicitly identifying factors that hinder business efficiency, such as multiple data entry or multiple approval steps that delay procedures.

[0051] 5. Proposal for improvement

[0052] Subject: AI

[0053] The AI ​​generates specific improvement proposals for the identified waste and improvement points. The proposals are simulated to predict their effects and then present the optimal solution. The proposals are organized in text and visual formats and sent to the server.

[0054] 6. Report Generation

[0055] Subject: Server

[0056] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user.

[0057] Specific examples

[0058] Example: A new product development project

[0059] Data collection

[0060] The server collects emails such as new product development requests from the sales department and database change requests from the IT department.

[0061] Data analysis

[0062] The natural language processing engine extracts keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka."

[0063] Flow Modeling

[0064] The server generates a business processing flow from the sales department to the IT department to the quality control department to the marketing department, and displays it graphically.

[0065] Identifying waste and areas for improvement

[0066] AI points out that the same data is being entered multiple times across multiple departments, and that multiple approval steps are causing delays in work.

[0067] Proposal of improvement proposals

[0068] AI suggests centralizing data entry and automating approval steps.

[0069] Report Generation

[0070] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[0071] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] Subject: Server

[0075] Specific operation: The server connects to the mail server at regular intervals to retrieve new emails. This is done using the POP3 or IMAP protocol. The retrieved emails are saved in temporary storage. It also scans database application forms and related documents from the file server or a specified folder and saves them in temporary storage as well.

[0076] Step 2:

[0077] Subject: Server

[0078] Specific operation: The server analyzes the stored emails and documents and sends them to a natural language processing engine. The natural language processing engine tokenizes the email body and documents and extracts key information (delivery date, person in charge, content, etc.). The extracted key information is saved as structured data in JSON format or similar.

[0079] Step 3:

[0080] Subject: Server

[0081] Specific operation: The server generates a business process flow model based on the extracted structured data. In this process, it compares it with an existing business process database and determines the sequence of business steps. The generated business process flow model is saved in BPMN (Business Process Model and Notation) format and displayed in a flow design tool or dashboard.

[0082] Step 4:

[0083] Subject: AI

[0084] How it works: The AI ​​analyzes the generated business process flow model and identifies wasteful or inefficient steps within the process. For example, it detects cases where the same data is being entered multiple times by multiple departments or where there are unnecessary approval steps. This is done using past statistical data and a rule base.

[0085] Step 5:

[0086] Subject: AI

[0087] Specific Actions: Based on the identified waste and improvement points, the AI ​​generates specific improvement suggestions, such as centralizing data entry and automating approval processes. The improvement suggestions are organized in text and visual formats and used to generate subsequent reports.

[0088] Step 6:

[0089] Subject: Server

[0090] Specific operation: The server generates a report based on the improvement proposals generated by the AI ​​and the business process flow model. This report includes a visualization of the business process flow in graphs and charts, details of waste and improvement points, and the proposed improvement proposals. The generated report is output in PDF or HTML format and provided to the user.

[0091] Example 1

[0092] 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."

[0093] Today's increasingly complex business processes require efficient management and analysis, but manual data collection and analysis is time-consuming and prone to errors. It's also difficult to identify wasteful or inefficient parts of business processes, and finding solutions requires a great deal of time and effort. This creates challenges, reducing the efficiency of the entire company and hindering smooth business operations.

[0094] 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.

[0095] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for visually displaying the business process flow model, means for polling new data from a mail server and a file server at a specific interval, and means for using an external API as the natural language processing engine. This makes it possible to rapidly and accurately identify waste in business processes and present specific improvement proposals, thereby significantly improving the efficiency of the entire business.

[0096] "Request data" refers to data that includes information about requests and applications related to business processes.

[0097] A "natural language processing engine" is software or an API for analyzing text data and extracting key information.

[0098] "Key information" is specific information that is considered important in a business process, such as deadlines, people in charge, and content.

[0099] A "business process flow model" is a model that visually represents the flow of a series of business procedures and processes.

[0100] "Waste" refers to unnecessary steps and inefficient operations in a business process.

[0101] "Improvement points" are points that need to be improved to improve the efficiency of a business process.

[0102] An "improvement proposal" is a proposal that presents specific solutions to waste or areas for improvement.

[0103] A "report" is a document that includes details of improvement proposals and business process flow models.

[0104] "Visually displaying" means expressing a business process flow model graphically and providing it to the user in a format that is easy to understand.

[0105] "Polling" is the process of periodically checking and collecting new data from a server.

[0106] An "external API" is an interface for accessing functions provided by other software or services.

[0107] MODE FOR CARRYING OUT THE INVENTION

[0108] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[0109] Data collection

[0110] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or specified folders. This makes it possible to comprehensively collect request data related to all business processes. Specifically, the server accesses the mail server at a specific interval, every five minutes, to check whether new emails exist. This process uses standard mail server protocols (e.g., IMAP or POP3).

[0111] Data analysis

[0112] The server sends the retrieved emails and documents to a natural language processing engine (e.g., Google® NLP API), which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations, allowing it to be used efficiently. The key information is stored as structured data in a database on the server side and is used for subsequent processing.

[0113] Flow Modeling

[0114] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. The model is displayed graphically using a flow design tool such as Microsoft® Visio. This makes it easier for employees to understand the overall picture of the business process and make decisions regarding the flow of work.

[0115] Identifying waste and areas for improvement

[0116] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps. This explicitly identifies factors that hinder business efficiency. For example, it identifies cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. Using a machine learning model enables highly accurate analysis based on past data.

[0117] Proposal of improvement proposals

[0118] AI generates specific improvement proposals for identified waste and improvement points. The proposals are simulated to predict their effects and then present optimal solutions. For example, it suggests centralizing data entry and automating approval processes. The proposals are organized in text and visual formats and sent to a server, allowing for the rapid provision of specific, actionable improvement measures.

[0119] Report Generation

[0120] The server generates a detailed report based on the improvement proposals proposed by the AI ​​and the business process flow model. This report includes specific improvement proposals for reducing waste in business and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then use this report to implement improvements to their business processes.

[0121] Specific examples

[0122] Example: A new product development project

[0123] Data collection

[0124] The server collects emails from the sales department requesting new product development, emails from the IT department requesting database changes, etc. It also retrieves newly added document files from designated folders on the file server.

[0125] Data analysis

[0126] A natural language processing engine (e.g., Google NLP API) extracts key information such as "Delivery date: 2023-12-31," "Person in charge: Tanaka," and "New product specifications," and the server stores this in a database.

[0127] Flow Modeling

[0128] The server generates a business flow model of "Sales Department → IT Department → Quality Control Department → Marketing Department" and displays it visually using Microsoft Visio.

[0129] Identifying waste and areas for improvement

[0130] AI detects duplicate data entry across departments and multiple approval steps that delay work.

[0131] Proposal of improvement proposals

[0132] AI will propose centralizing data entry and automating approval processes, and will also perform simulations to predict the effects.

[0133] Report Generation

[0134] The server generates a report containing specific improvement proposals and submits it to the user in PDF format, allowing the user to implement improvements to their business processes based on this report.

[0135] Prompt Sentence Examples

[0136] "Please tell us some specific improvement ideas for streamlining the business processes in new product development projects."

[0137] "Please identify waste in the database change application process and suggest improvements."

[0138] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] The server collects request data from the mail server and file server. The server accesses the mail server every five minutes to check for new emails. If new emails exist, it reads their contents and searches the subject and body of the email for keywords related to "request" or "application." At the same time, the server accesses the specified folder on the file server to retrieve newly added document files. This process obtains the request data as input, which is used in the next step.

[0142] Step 2:

[0143] The server sends the collected emails and documents to a natural language processing engine. Specifically, it uses the Google NLP API to analyze the text data. This engine extracts important key information for business processing. For example, information such as "delivery date," "person in charge," and "content" is obtained as analysis results. The server then stores this extracted key information in a database as structured data. Through this process, emails and documents become input data, and the key information becomes output data.

[0144] Step 3:

[0145] The server generates a business process flow model based on the key information stored in the database. From the extracted key information, a series of business procedures and processes are visually represented in the form of a flowchart. Using a flow design tool such as Microsoft Visio, the flow of the business process is displayed graphically. For example, a business process flow of "Sales Department → IT Department → Quality Control Department → Marketing Department" is generated. In this process, the key information is used as input data, and a business process flow model is generated as output data.

[0146] Step 4:

[0147] The AI ​​analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. It uses a machine learning model to identify wasteful procedures and inefficient work. For example, it detects cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. The AI ​​sends these analysis results to a server. In this step, the business process flow model is the input data, and a list of waste and areas for improvement is the output data.

[0148] Step 5:

[0149] The AI ​​generates specific improvement proposals based on the identified waste and improvement points. These proposals may include centralizing data entry and automating the approval process. These proposals are presented after simulations are run to predict their effectiveness. The proposals are organized in text and visual formats and sent to a server. In this process, the list of waste and improvement points is the input data, and the improvement proposals are the output data.

[0150] Step 6:

[0151] The server generates a detailed report based on the improvement proposals and business process flow model presented by the AI. The report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then implement business process improvements based on this report. In this step, the improvement proposals and business process flow model are the input data, and the report is the output data.

[0152] (Application example 1)

[0153] 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."

[0154] Efficiently managing and analyzing complex business processes in today's corporate environment is challenging. Existing systems are particularly inadequate when it comes to real-time data collection and analysis, as well as immediate feedback. There is also a need to identify redundant steps and wasteful processes and quickly propose improvements, but there is a lack of comprehensive solutions that can achieve this. While real-time process optimization using autonomous machines is particularly important in factories and manufacturing lines, current technology does not adequately meet this need.

[0155] 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.

[0156] In this invention, the server includes: means for collecting request data; means for analyzing the collected data using a natural language processing engine and extracting key information; means for generating a business process flow model based on the extracted key information; means for identifying waste and areas for improvement based on an analysis of the generated business process flow model; means for presenting improvement proposals for the identified waste and areas for improvement; means for generating and outputting a report based on the improvement proposals and the business process flow model; means for being installed in an autonomous machine operating within a work area and for collecting and analyzing data in real time; and means for visually displaying the collected data and providing immediate feedback. This enables efficient data collection and analysis in real time even in factories and production lines, enabling immediate identification of waste and the presentation of effective improvement proposals.

[0157] "Request data" refers to data that includes advance information about a business process.

[0158] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning and information.

[0159] "Key information" refers to important attributes and elements in a business process, and includes information such as "delivery date" and "person in charge."

[0160] A "business process flow model" is a model that visually and systematically represents each step of a business process and the relationships between them.

[0161] "Waste" refers to unnecessary steps or duplication in business processes that hinder efficiency.

[0162] "Improvement points" are areas in a business process that require improvement in order to improve efficiency and quality.

[0163] An "improvement plan" is a specific proposal or method aimed at improving efficiency and quality in response to identified waste or areas for improvement.

[0164] A "report" is a document that includes information such as analysis results and improvement proposals, and is compiled in the form of text and charts.

[0165] An "autonomous machine" is a mechanical device that is designed to operate autonomously and perform a specific task or operation.

[0166] "Real-time" is a time concept that means data processing and analysis are carried out almost immediately.

[0167] "Visual display" means presenting analysis results and business models in a graphical format that is easy for people to understand.

[0168] "Immediate feedback" means immediately reflecting the results of data collection and analysis, and providing prompt notifications and suggestions for improvement to workers.

[0169] This invention is a system for efficiently managing and analyzing business processes within a factory. This system has the following main components and functions:

[0170] 1. System Configuration

[0171] Hardware:

[0172] Autonomous machines: Robots that move around the factory and collect the necessary data.

[0173] Server: A central processing unit that collects and analyzes data and generates reports.

[0174] Sensors: Various sensor devices mounted on autonomous machines to measure data.

[0175] software:

[0176] Natural language processing engine (spaCy): Analyzes collected text data and extracts key information.

[0177] Data analysis tools (PyPDF2, watchdog): Tools for analyzing PDF documents and monitoring the file system.

[0178] Graphical display tool (graphviz): A tool for visually displaying business process flow models.

[0179] 2. Data Collection

[0180] The server periodically retrieves new request data from the mail server, and autonomous machines in the factory use sensors to collect data in real time and send it to the server, ensuring that the latest information about business processes is always available.

[0181] 3. Data Analysis

[0182] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data. Through the analysis, key information such as "delivery date" and "person in charge" is extracted. This information forms the basis for the next step, business process flow modeling.

[0183] 4. Flow Modeling

[0184] The server generates a business process flow model based on the extracted key information. This flow model visually represents the business procedures and the relationships between each step, and clearly shows the data flow. A graphical display tool (e.g., graphviz) is used for display.

[0185] 5. Identifying waste and areas for improvement

[0186] AI analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. For example, it can identify cases where the same data is being entered multiple times across multiple departments, or where there are multiple approval steps that are delaying work. Waste and areas for improvement are analyzed with high precision using machine learning models.

[0187] 6. Proposal for improvement

[0188] AI proposes specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness. The proposals are organized in text and visual formats for easy understanding.

[0189] 7. Report Generation

[0190] The server generates a detailed report based on the improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the factory manager.

[0191] Specific examples

[0192] A concrete example is process improvement in a manufacturing plant. Autonomous machines collect data from the product line and send it to a server. Natural language processing reveals that there is a lot of overlapping data between "Production Line 1" and the "Quality Control Department." AI analyzes this and suggests an automated data entry system. The server compiles these suggestions into a report and presents it to the plant manager.

[0193] Example prompt sentence:

[0194] Input: Data from production line 1 to the quality control department. PDF data collected by robot scanning.

[0195] Output: A report containing a business process flow model, wasteful steps, and improvement suggestions.

[0196] The above are the main components and procedures for implementing the present invention, which can improve the efficiency and quality of work processes within a factory.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1: Data collection

[0199] The server periodically polls the mail server to retrieve new request emails and database application emails. At the same time, autonomous machines move around the factory and use sensors to collect data in real time, which is then sent to the server.

[0200] Input: Request emails and data sent from each department within the factory, and real-time data from sensors.

[0201] Output: Request data and real-time data collected on the server.

[0202] Specific operation: The server obtains the latest data from the mail server and sensors and stores it in a database.

[0203] Step 2: Data analysis

[0204] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data and extracts key information such as "delivery date" and "person in charge."

[0205] Input: Requested data and real-time data collected in step 1.

[0206] Output: Extracted key information (e.g., "Delivery Date", "Contact Person", etc.).

[0207] Specific operation: The server sends text data to the natural language processing engine, obtains the analysis results, and stores the key information in a database.

[0208] Step 3: Flow Modeling

[0209] The server generates a business process flow model based on the extracted key information, which visually represents the business procedures and the relationships between each step.

[0210] Input: The key information extracted in step 2.

[0211] Output: Business process flow model.

[0212] Specific operation: The server analyzes the key information and generates a flow model using a graphical display tool (e.g., graphviz).

[0213] Step 4: Identify waste and areas for improvement

[0214] The AI ​​on the server analyzes the generated business process flow model and identifies unnecessary steps and process gaps, such as when the same data is being entered multiple times across multiple departments.

[0215] Input: The business process flow model generated in step 3.

[0216] Output: Results identifying wasteful steps and gaps in the process.

[0217] How it works: The AI ​​on the server uses machine learning models to analyze the flow model and identify waste and areas for improvement.

[0218] Step 5: Propose improvements

[0219] AI generates specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness.

[0220] Input: Wasteful steps or process gaps identified in Step 4.

[0221] Output: Improvement suggestions (text and visual formats).

[0222] Specific operation: The AI ​​runs a simulation, generates improvement proposals, and sends them to the server.

[0223] Step 6: Generate reports

[0224] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI, and the report is output in PDF or HTML format and submitted to the user.

[0225] Input: Improvement proposals and business process flow models generated in Step 5.

[0226] Output: Detailed report in PDF or HTML format.

[0227] Specific operation: The server integrates the improvement proposal and the flow model, generates a report using a report creation tool, and saves it in the specified format.

[0228] Step 7: Real-time feedback

[0229] The autonomous machines visually display the data they collect and provide immediate feedback to factory workers, allowing them to review and take action on suggested improvements in real time.

[0230] Input: Real-time data continuously obtained from step 1.

[0231] Output: Visual feedback and improvement suggestions for the worker.

[0232] Specific operation: The autonomous machine notifies the worker of the results of data analysis via a display and audio alert, prompting immediate action.

[0233] 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.

[0234] System Overview

[0235] This invention is a new system for streamlining business processes. It combines conventional business flow management with an emotion engine that analyzes user emotions to achieve more precise and effective business improvements. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. The system then analyzes the generated business process flow model to identify waste and areas for improvement. The emotion engine then recognizes user emotions and incorporates them into the business process flow model to generate more precise improvement proposals and output them as a report.

[0236] Program processing description

[0237] 1. Data Collection

[0238] Subject: Server

[0239] The server periodically retrieves new emails from the mail server, and database application forms and related documents from the file server. These data are temporarily stored in storage.

[0240] 2. Data Analysis

[0241] Subject: Server

[0242] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. As a result of the analysis, key information important for business processing (e.g., "delivery date," "person in charge," and "content") is extracted.

[0243] 3. Flow Modeling

[0244] Subject: Server

[0245] The server generates a business process flow model based on the extracted key information. The generated model visually represents a series of business procedures and processes and is displayed in a flow design tool or dashboard.

[0246] 4. Emotion analysis

[0247] Subject: Emotion Engine

[0248] The emotion engine analyzes user emotions and uses that data to identify factors that affect the business process flow model. For example, it extracts emotional data from user emails and feedback and incorporates it into the business process model.

[0249] 5. Identifying waste and areas for improvement

[0250] Subject: AI

[0251] AI analyzes the generated business process flow model and sentiment data to detect wasteful steps and process gaps, thereby clearly indicating the identified wasteful and inefficient steps.

[0252] 6. Proposal for improvement

[0253] Subject: AI

[0254] The AI ​​generates specific improvement proposals based on the identified waste and areas for improvement, taking into account feedback based on emotional data to present optimal improvement proposals.

[0255] 7. Report Generation

[0256] Subject: Server

[0257] The server generates a detailed report based on the AI-generated improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The report is output in PDF or HTML format and provided to the user via their device.

[0258] Specific examples

[0259] Example: A new product development project

[0260] Data collection

[0261] The sales department sends an email requesting new product development.

[0262] The IT department submits the required database change request.

[0263] The marketing department sends out the survey data via email.

[0264] Data analysis

[0265] The server uses a natural language processing engine to extract information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the email.

[0266] Flow Modeling

[0267] The server generates and visualizes a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department.

[0268] Emotion analysis

[0269] The emotion engine analyzes emails and feedback from users (project managers) to detect pressure and stress levels.

[0270] Identifying waste and areas for improvement

[0271] The AI ​​pointed out that the same data was being entered multiple times across multiple departments and that there were multiple approval steps.

[0272] Proposal of improvement proposals

[0273] AI takes emotional data into account and suggests centralizing data entry and automating approval steps. For highly stressed employees, it also suggests allocating some of the tasks to other members.

[0274] Report Generation

[0275] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[0276] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[0277] The processing flow will be explained below.

[0278] Step 1:

[0279] Subject: Server

[0280] Specific operation: The server periodically accesses the mail server to retrieve new request emails and database application emails. The retrieved emails are saved in temporary storage. It also retrieves related documents such as database application forms from the file server or a specified folder. This is done using the file access API.

[0281] Step 2:

[0282] Subject: Server

[0283] Specific operation: The server sends the stored emails and documents to a natural language processing (NLP) engine, which analyzes the text data. The NLP engine tokenizes the text and extracts key information such as "delivery date," "person in charge," and "content." The extracted key information is saved in JSON format.

[0284] Step 3:

[0285] Subject: Server

[0286] Specific operation: The server generates a business process flow model based on the extracted key information. This model is a visual representation of a series of business procedures and processes, and is displayed in a business process design tool or dashboard. The model is then compared with an existing business process database to optimize the flow.

[0287] Step 4:

[0288] Subject: Emotion Engine

[0289] Specific operation: The emotion engine analyzes emails and feedback from users and extracts emotional data. For example, it uses text analysis to identify emotions such as "dissatisfaction," "stress," and "satisfaction" contained in user text. The extracted emotional data is incorporated into the business process flow model.

[0290] Step 5:

[0291] Subject: Server

[0292] Specific operation: The server uses AI to perform analysis based on a business process flow model that includes emotional data. The AI ​​identifies unnecessary steps and process gaps. This analysis also references past business data and statistical information.

[0293] Step 6:

[0294] Subject: AI

[0295] Specific operation: The AI ​​generates improvement proposals based on the business process flow model and emotion data. For example, it suggests distributing tasks to high-stress departments, centralizing data entry, automating procedures, etc. The improvement proposals are sent to the server in text and visual formats.

[0296] Step 7:

[0297] Subject: Server

[0298] Specific operation: The server integrates the AI-generated improvement proposals into the business process flow model and generates a detailed report. The report includes identified waste areas, improvement points, analysis results of emotion data, and proposed improvement proposals. The final report is output in PDF or HTML format and provided to the user.

[0299] Examples:

[0300] For new product development projects

[0301] Step 1:

[0302] The sales department sends an email requesting new product development.

[0303] The IT department stores the necessary database change request forms on a file server.

[0304] Step 2:

[0305] The server uses an NLP engine to extract keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the request email and application form.

[0306] Step 3:

[0307] The server generates a flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it on a dashboard.

[0308] Step 4:

[0309] The emotion engine analyzes feedback emails from users (staff) and extracts emotional data such as "high stress" and "dissatisfaction."

[0310] Step 5:

[0311] The server analyzes the flow model, which includes emotional data, and the AI ​​identifies unnecessary steps and inefficient processes.

[0312] Step 6:

[0313] The AI ​​takes emotional data into account and makes suggestions for distributing tasks, centralizing data entry, and automating tasks.

[0314] Step 7:

[0315] The server generates a report and provides it to the user in PDF format, which includes specific improvement suggestions, identified waste areas, and the results of the analysis of sentiment data.

[0316] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[0317] Example 2

[0318] 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."

[0319] In modern business processes, traditional workflow management systems have improved efficiency in some respects, but they do not take into account the emotional burden and stress placed on users. Therefore, while improving the overall efficiency and quality of work, there is a need for systems that take into account the emotional state of users and appropriately allocate the workload. Furthermore, there is a need for systems that can automatically identify wasteful and inefficient steps and propose specific improvement proposals.

[0320] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0321] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on the analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for analyzing user emotions, and means for integrating emotion analysis data into the business process flow model. This improves the efficiency and quality of business processes and enables appropriate workload allocation taking into account the emotional state of users.

[0322] "Request data" refers to necessary information and requirements related to business operations, and includes document data such as emails and application forms.

[0323] A "natural language processing engine" refers to a group of algorithms and programs that allow a computer to understand and analyze human language.

[0324] "Key information" refers to important data items in a business process, and includes, for example, "delivery date" and "person in charge."

[0325] A "business process flow model" is a model that visually represents a business process, and includes a diagrammatic representation of business procedures and process flows.

[0326] "Emotion analysis" refers to the process of analyzing a user's emotional state from text data and feedback, and assessing their psychological state, such as stress and satisfaction.

[0327] "Improvement proposals" refer to specific proposals and measures aimed at streamlining business processes and improving quality.

[0328] A "machine learning model" refers to a group of algorithms or programs that learn from large amounts of data and automatically analyze patterns and trends.

[0329] A "report" is a document that summarizes analysis results and improvement proposals, and is provided in PDF or HTML format.

[0330] "Emotion analysis data" refers to data relating to the user's emotional state obtained as a result of emotion analysis.

[0331] This invention is a system for streamlining business processes and improving business processes by taking into account the emotional state of users. This system combines multiple hardware and software components to collect and analyze request data, generate a business process flow model, identify waste and areas for improvement, and present improvement proposals that integrate user emotional data.

[0332] Hardware and Software Configuration

[0333] Hardware:

[0334] Server: Responsible for main processes such as data collection, analysis, flow modeling, and report generation.

[0335] Terminal: Serves as an interface for users to access and view the generated reports.

[0336] software:

[0337] Natural language processing engine: Analyzes requested data and extracts key information using Google Cloud Natural Language API, etc.

[0338] Emotion analysis engine: Using IBM Watson (registered trademark) Tone Analyzer, etc., analyzes the user's emotional state and generates numerical data.

[0339] Machine learning models: Used to analyze business process flow models and sentiment data to identify waste and areas for improvement.

[0340] Dashboard tools: Visualize business process flow models using tools such as Microsoft Power BI.

[0341] Program Processing Overview

[0342] The program of this system implements the following main functions:

[0343] 1. Data Collection:

[0344] The server periodically retrieves new emails from the mail server and stores them in storage. It also collects related documents such as database application forms from the file server and stores them in storage.

[0345] 2. Data Analysis:

[0346] The server sends the emails and documents stored in the storage to a natural language processing engine, which analyzes the text data. Important key information (e.g., "delivery date," "person in charge," and "content") is extracted and stored in a database.

[0347] 3. Flow Modeling:

[0348] The server generates a business process flow model based on the key information stored in the database. The generated model is visualized using a dashboard tool.

[0349] 4. Emotion analysis:

[0350] The emotion engine analyzes emails and feedback forms sent by users and generates numerical data representing the user's emotional state. This emotional data is sent to the server and integrated into the business process flow model.

[0351] 5. Identify waste and areas for improvement:

[0352] AI analyzes business process flow models and sentiment analysis data to identify unnecessary steps and inefficiencies.

[0353] 6. Proposal for improvement:

[0354] Based on the identified waste and areas for improvement, the AI ​​generates specific improvement proposals, taking into account emotional data and proposing things like workload and task reallocation.

[0355] 7. Report Generation:

[0356] The server creates a detailed report based on the generated improvement proposals and business process flow model. The report is output in PDF or HTML format and provided to the user via their terminal.

[0357] Specific examples

[0358] For new product development projects

[0359] Data collection: The server collects emails requesting new product development sent by the sales department and database change request forms sent by the IT department, and stores them in storage.

[0360] Data analysis: The server analyzes the request email, extracts key information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka", and stores it in a database.

[0361] Flow modeling: Based on the extracted key information, the server generates a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it using a dashboard tool.

[0362] Sentiment analysis: The emotion engine analyzes emails and feedback sent by project managers and generates emotional data such as "high stress level."

[0363] Identifying waste and areas for improvement: AI analyzes workflow models and sentiment data to identify duplicate data entries across multiple departments and multiple approval steps.

[0364] Suggested improvements: AI can suggest improvements such as centralizing data entry, automating approval steps, or delegating specific tasks to other members.

[0365] Report generation: The server generates a detailed report based on the improvement proposal and provides it to the person in charge (Tanaka) via the terminal.

[0366] Example prompt sentence:

[0367] Please extract key information about the business flow from the following email. Email content: 'The sales department requests the start of the next new product development project as follows. The deadline is 2023-12-31, and the person in charge is Tanaka.'

[0368] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0369] Step 1:

[0370] The server periodically retrieves new emails from the mail server. The mail server connection information and a query to retrieve new emails are used as input. The server temporarily stores the retrieved emails in storage. It also collects database application forms and related documents from the file server and stores them in storage. This completes the collection of request data.

[0371] Step 2:

[0372] The server sends the emails and documents stored in storage to a natural language processing engine (e.g., Google Cloud Natural Language API). The stored emails and documents are used as input. The natural language processing engine analyzes the text data and extracts key information such as delivery date, person in charge, and content. The server stores the extracted key information in a database and records the analysis results in a log. This extracts the key information.

[0373] Step 3:

[0374] The server generates a business process flow model based on key information stored in the database. The key information is used as input. The server uses this key information to visualize the business flow step by step, creating a series of business procedures and processes. The generated business process flow model is visualized using a dashboard tool. This generates a business process flow model.

[0375] Step 4:

[0376] The emotion engine (e.g. IBM Watson Tone Analyzer) analyzes emails and feedback forms sent by users. The emails and feedback sent by users are used as input. The emotion engine analyzes the user's emotional state (e.g. stress, satisfaction, etc.) from this text data and generates numerical data. The emotion analysis data is sent to the server, which then analyzes the user's emotional state.

[0377] Step 5:

[0378] The AI ​​uses the business process flow model and sentiment analysis data provided by the server to identify wasteful steps and inefficient areas. The business process flow model and sentiment analysis data are used as input. The AI ​​performs analysis using a machine learning model, generates a report detailing the identified problems, and sends it to the server. This identifies waste and areas for improvement.

[0379] Step 6:

[0380] The AI ​​creates specific improvement proposals based on the identified waste and improvement points. The waste and improvement points are used as input. The AI ​​generates improvement proposals that include suggestions for centralizing data entry, automating approval steps, and reassigning tasks. Sentiment analysis data is also taken into account, and measures to reduce user stress are included. The improvement proposals are sent to the server. This generates specific improvement proposals.

[0381] Step 7:

[0382] The server creates a detailed report based on the improvement proposals provided by the AI. The improvement proposals and the business process flow model are used as input. The server generates a report that includes a visual representation of the business process flow model, detected problems, and specific improvement suggestions. The generated report is output in PDF or HTML format and provided to the user via their terminal. This completes the report generation process.

[0383] (Application example 2)

[0384] 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."

[0385] Conventional business process management systems have the problem that they are unable to take into account the emotions and stress levels of users when identifying wasteful work flows and areas for improvement, making it difficult to improve work efficiently. This problem is particularly important in brick-and-mortar stores, where the emotions and motivation of staff members directly affect work efficiency.

[0386] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for incorporating user emotion data into the generated business process flow model and performing emotion analysis, means for identifying waste and improvement points based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and improvement points, and means for generating and outputting a report based on the improvement proposals and the business process flow model. This enables precise business improvement that takes user emotions into consideration.

[0387] "Request data" refers to data that includes information and requirements related to business processes.

[0388] A "natural language processing engine" is a software function that analyzes text data and extracts meaning and key information.

[0389] "Key information" is information that extracts important parameters and topics from the collected data.

[0390] A "business process flow model" is a model that visually and structurally represents business procedures and processes.

[0391] "Emotion analysis" is a method of converting user emotions into data and using the results to identify factors that affect business processes.

[0392] "Waste" refers to inefficient steps or unnecessary work in a business process.

[0393] "Improvement points" refer to areas that can be improved to make business processes more efficient.

[0394] "Improvement proposals" refer to specific proposals for eliminating waste and inefficiencies in business processes.

[0395] The "means for generating and outputting reports" is a function that creates a detailed report based on the generated business process flow model and improvement proposals, and provides it to the user.

[0396] "Emotion data" is data obtained by analyzing and quantifying the user's emotional state.

[0397] "Structured data" is data in which key information is organized and arranged according to a certain format.

[0398] A "machine learning model" is an algorithm that recognizes patterns based on data and automatically performs analysis and predictions.

[0399] System Overview

[0400] The present invention is a new system that combines the efficiency of business processes in brick-and-mortar stores with user emotion analysis. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. Then, it analyzes user emotions using an emotion engine and incorporates them into the business process flow model to generate precise improvement proposals and output them as a report. Specific embodiments are described below.

[0401] Hardware and software used

[0402] Smartphones: Used as individual staff devices.

[0403] Emotion engine: Powered by Microsoft Azure (registered trademark) Cognitive Services.

[0404] Natural language processing engine: Uses Google Cloud Natural Language API.

[0405] Database: Uses Firebase Realtime Database.

[0406] Flow Design Tool: A flow design dashboard powered by React.js.

[0407] Program processing

[0408] The server includes the following means:

[0409] 1. Data Collection Methods

[0410] The server collects business data from each device in the store. For example, it aggregates business data entered by staff on their smartphones and event data from sensors. This data is temporarily stored in a database.

[0411] 2. Natural Language Processing Methods

[0412] The collected data is sent to the server's natural language processing engine, where key information is extracted, such as "break time," "number of customer interactions," and "product replenishment work."

[0413] 3. Method for generating business process flow models

[0414] Based on the extracted key information, a business process flow model is generated on the server. This model visually represents business procedures and processes and can be viewed on a dashboard.

[0415] 4. Emotion analysis means

[0416] The server uses an emotion engine to analyze the emotional data of the staff, which is expressed as, for example, the staff's "stress level" or "motivation index."

[0417] 5. Identifying waste and areas for improvement

[0418] Based on the generated business process flow model and emotional data, AI identifies unnecessary steps and areas for improvement, focusing on analyzing business flows where the emotional data indicates high stress.

[0419] 6. Means for presenting improvement proposals

[0420] The server generates specific improvement proposals based on the identified waste and improvement points, such as centralizing data entry, automating approval steps, and redistributing tasks.

[0421] 7. Report Generation Methods

[0422] The server generates a detailed report based on the business process flow model and improvement proposals, and outputs it in PDF or HTML format. The report can be viewed on a smartphone or PC.

[0423] Specific examples

[0424] Example: Improving business processes in physical stores

[0425] In physical stores, staff record their daily work on their smartphones. For example, data such as "product inventory" and "customer service details" is entered. The data is stored in a Firebase database, and the server periodically retrieves it. A natural language processing engine extracts key information and generates a business process flow model. An emotion engine analyzes staff daily reports and feedback emails to detect stress levels. AI identifies unnecessary steps and areas for improvement, and proposes specific improvement proposals, including automating data entry and dividing up tasks. Finally, a detailed report is generated and provided to managers.

[0426] Prompt Sentence Examples

[0427] "We are developing a new operational improvement tool for our brick-and-mortar stores. This tool analyzes staff work processes and emotions and generates specific improvement proposals. Please explain the steps to perform the following operations.

[0428] 1. Collecting data from Firebase Realtime Database

[0429] 2. Obtaining sentiment scores using a sentiment analysis engine

[0430] 3. Creation and visualization of business flow models

[0431] 4. Preparation of a detailed report with improvement suggestions

[0432] The present invention enables precise business improvement that takes into account the user's emotions.

[0433] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0434] Step 1:

[0435] The server collects business data from each device in the physical store. Specifically, it aggregates business data entered by staff on their smartphones and event data from sensors in the store. The entered data is collected in file format or via API, and temporarily stored in the Firebase Realtime Database. This data becomes the input data for the next processing step.

[0436] Step 2:

[0437] The server retrieves the collected data from Firebase and sends it to a natural language processing engine (Google Cloud Natural Language API). At this time, business data in text format becomes the input data. The natural language processing engine analyzes this data and extracts key information important to the business process (for example, "break time," "number of customer interactions," "product replenishment work," etc.). The extracted key information is sent to the next step as output data.

[0438] Step 3:

[0439] The server generates a business process flow model based on the extracted key information. The input data is the key information extracted in the previous step, and the generated business process flow model is expressed in XML or JSON format. This model visually represents business procedures and processes, and is displayed on a flow design dashboard using React.js. The generated business process flow model becomes the output data.

[0440] Step 4:

[0441] The server uses an emotion engine (Microsoft Azure Cognitive Services) to analyze staff emotional data. The input data is staff daily reports and feedback emails. The emotion engine analyzes this text data and generates emotional scores such as "stress level" and "motivation index" as output data.

[0442] Step 5:

[0443] The server reanalyzes the business process model based on the generated business process flow model and emotion score. The input data are the business process flow model and emotion score, and the AI ​​(machine learning model) identifies wasteful steps and areas for improvement. For example, if a high stress level is detected in a specific business process, it suggests that the business steps are inefficient. A business process flow model with wasteful steps and areas for improvement marked is generated as output data.

[0444] Step 6:

[0445] The server generates specific improvement proposals based on the identified waste and improvement points. The input data is a business process flow model that includes wasteful steps and improvement points. The AI ​​generates specific improvement proposals, such as centralizing data entry, automating approval steps, and redistributing tasks. The generated improvement proposals are sent to the next step as output data.

[0446] Step 7:

[0447] The server generates a detailed report based on the business process flow model and improvement proposals. The input data are the improvement proposals and the business process flow model. The server formats this data into a document and creates a report in PDF or HTML format. The generated report is sent to the user's device as output data. The user can view the report on their smartphone or computer and use it as a guideline for specific business improvements.

[0448] Through the above steps, precise business improvement that takes into account the user's emotions is realized.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] [Second embodiment]

[0453] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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."

[0465] System Overview

[0466] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[0467] Program processing description

[0468] 1. Data Collection

[0469] Subject: Server

[0470] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or designated folders. This makes it possible to comprehensively collect request data related to all business processes.

[0471] 2. Data Analysis

[0472] Subject: Server

[0473] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations, allowing it to be used efficiently.

[0474] 3. Flow Modeling

[0475] Subject: Server

[0476] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. This model is displayed graphically using a flow design tool.

[0477] 4. Identifying waste and areas for improvement

[0478] Subject: AI

[0479] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps, explicitly identifying factors that hinder business efficiency, such as multiple data entry or multiple approval steps that delay procedures.

[0480] 5. Proposal for improvement

[0481] Subject: AI

[0482] The AI ​​generates specific improvement proposals for the identified waste and improvement points. The proposals are simulated to predict their effects and then present the optimal solution. The proposals are organized in text and visual formats and sent to the server.

[0483] 6. Report Generation

[0484] Subject: Server

[0485] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user.

[0486] Specific examples

[0487] Example: A new product development project

[0488] Data collection

[0489] The server collects emails such as new product development requests from the sales department and database change requests from the IT department.

[0490] Data analysis

[0491] The natural language processing engine extracts keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka."

[0492] Flow Modeling

[0493] The server generates a business processing flow from the sales department to the IT department to the quality control department to the marketing department, and displays it graphically.

[0494] Identifying waste and areas for improvement

[0495] AI points out that the same data is being entered multiple times across multiple departments, and that multiple approval steps are causing delays in work.

[0496] Proposal of improvement proposals

[0497] AI suggests centralizing data entry and automating approval steps.

[0498] Report Generation

[0499] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[0500] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[0501] The processing flow will be explained below.

[0502] Step 1:

[0503] Subject: Server

[0504] Specific operation: The server connects to the mail server at regular intervals to retrieve new emails. This is done using the POP3 or IMAP protocol. The retrieved emails are saved in temporary storage. It also scans database application forms and related documents from the file server or a specified folder and saves them in temporary storage as well.

[0505] Step 2:

[0506] Subject: Server

[0507] Specific operation: The server analyzes the stored emails and documents and sends them to a natural language processing engine. The natural language processing engine tokenizes the email body and documents and extracts key information (delivery date, person in charge, content, etc.). The extracted key information is saved as structured data in JSON format or similar.

[0508] Step 3:

[0509] Subject: Server

[0510] Specific operation: The server generates a business process flow model based on the extracted structured data. In this process, it compares it with an existing business process database and determines the sequence of business steps. The generated business process flow model is saved in BPMN (Business Process Model and Notation) format and displayed in a flow design tool or dashboard.

[0511] Step 4:

[0512] Subject: AI

[0513] How it works: The AI ​​analyzes the generated business process flow model and identifies wasteful or inefficient steps within the process. For example, it detects cases where the same data is being entered multiple times by multiple departments or where there are unnecessary approval steps. This is done using past statistical data and a rule base.

[0514] Step 5:

[0515] Subject: AI

[0516] Specific Actions: Based on the identified waste and improvement points, the AI ​​generates specific improvement suggestions, such as centralizing data entry and automating approval processes. The improvement suggestions are organized in text and visual formats and used to generate subsequent reports.

[0517] Step 6:

[0518] Subject: Server

[0519] Specific operation: The server generates a report based on the improvement proposals generated by the AI ​​and the business process flow model. This report includes a visualization of the business process flow in graphs and charts, details of waste and improvement points, and the proposed improvement proposals. The generated report is output in PDF or HTML format and provided to the user.

[0520] Example 1

[0521] 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."

[0522] Today's increasingly complex business processes require efficient management and analysis, but manual data collection and analysis is time-consuming and prone to errors. It's also difficult to identify wasteful or inefficient parts of business processes, and finding solutions requires a great deal of time and effort. This creates challenges, reducing the efficiency of the entire company and hindering smooth business operations.

[0523] 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.

[0524] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for visually displaying the business process flow model, means for polling new data from a mail server and a file server at a specific interval, and means for using an external API as the natural language processing engine. This makes it possible to rapidly and accurately identify waste in business processes and present specific improvement proposals, thereby significantly improving the efficiency of the entire business.

[0525] "Request data" refers to data that includes information about requests and applications related to business processes.

[0526] A "natural language processing engine" is software or an API for analyzing text data and extracting key information.

[0527] "Key information" is specific information that is considered important in a business process, such as deadlines, people in charge, and content.

[0528] A "business process flow model" is a model that visually represents the flow of a series of business procedures and processes.

[0529] "Waste" refers to unnecessary steps and inefficient operations in a business process.

[0530] "Improvement points" are points that need to be improved to improve the efficiency of a business process.

[0531] An "improvement proposal" is a proposal that presents specific solutions to waste or areas for improvement.

[0532] A "report" is a document that includes details of improvement proposals and business process flow models.

[0533] "Visually displaying" means expressing a business process flow model graphically and providing it to the user in a format that is easy to understand.

[0534] "Polling" is the process of periodically checking and collecting new data from a server.

[0535] An "external API" is an interface for accessing functions provided by other software or services.

[0536] MODE FOR CARRYING OUT THE INVENTION

[0537] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[0538] Data collection

[0539] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or specified folders. This makes it possible to comprehensively collect request data related to all business processes. Specifically, the server accesses the mail server at a specific interval, every five minutes, to check whether new emails exist. This process uses standard mail server protocols (e.g., IMAP or POP3).

[0540] Data analysis

[0541] The server sends the retrieved emails and documents to a natural language processing engine (e.g., Google NLP API), which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations and enables it to be used efficiently. The key information is stored as structured data in a database on the server side and is used for subsequent processing.

[0542] Flow Modeling

[0543] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. The model is displayed graphically using a flow design tool such as Microsoft Visio. This makes it easier for employees to understand the overall picture of the business process and make decisions regarding the flow of work.

[0544] Identifying waste and areas for improvement

[0545] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps. This explicitly identifies factors that hinder business efficiency. For example, it identifies cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. Using a machine learning model enables highly accurate analysis based on past data.

[0546] Proposal of improvement proposals

[0547] AI generates specific improvement proposals for identified waste and improvement points. The proposals are simulated to predict their effects and then present optimal solutions. For example, it suggests centralizing data entry and automating approval processes. The proposals are organized in text and visual formats and sent to a server, allowing for the rapid provision of specific, actionable improvement measures.

[0548] Report Generation

[0549] The server generates a detailed report based on the improvement proposals proposed by the AI ​​and the business process flow model. This report includes specific improvement proposals for reducing waste in business and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then use this report to implement improvements to their business processes.

[0550] Specific examples

[0551] Example: A new product development project

[0552] Data collection

[0553] The server collects emails from the sales department requesting new product development, emails from the IT department requesting database changes, etc. It also retrieves newly added document files from designated folders on the file server.

[0554] Data analysis

[0555] A natural language processing engine (e.g., Google NLP API) extracts key information such as "Delivery date: 2023-12-31," "Person in charge: Tanaka," and "New product specifications," and the server stores this in a database.

[0556] Flow Modeling

[0557] The server generates a business flow model of "Sales Department → IT Department → Quality Control Department → Marketing Department" and displays it visually using Microsoft Visio.

[0558] Identifying waste and areas for improvement

[0559] AI detects duplicate data entry across departments and multiple approval steps that delay work.

[0560] Proposal of improvement proposals

[0561] AI will propose centralizing data entry and automating approval processes, and will also perform simulations to predict the effects.

[0562] Report Generation

[0563] The server generates a report containing specific improvement proposals and submits it to the user in PDF format, allowing the user to implement improvements to their business processes based on this report.

[0564] Prompt Sentence Examples

[0565] "Please tell us some specific improvement ideas for streamlining the business processes in new product development projects."

[0566] "Please identify waste in the database change application process and suggest improvements."

[0567] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[0568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0569] Step 1:

[0570] The server collects request data from the mail server and file server. The server accesses the mail server every five minutes to check for new emails. If new emails exist, it reads their contents and searches the subject and body of the email for keywords related to "request" or "application." At the same time, the server accesses the specified folder on the file server to retrieve newly added document files. This process obtains the request data as input, which is used in the next step.

[0571] Step 2:

[0572] The server sends the collected emails and documents to a natural language processing engine. Specifically, it uses the Google NLP API to analyze the text data. This engine extracts important key information for business processing. For example, information such as "delivery date," "person in charge," and "content" is obtained as analysis results. The server then stores this extracted key information in a database as structured data. Through this process, emails and documents become input data, and the key information becomes output data.

[0573] Step 3:

[0574] The server generates a business process flow model based on the key information stored in the database. From the extracted key information, a series of business procedures and processes are visually represented in the form of a flowchart. Using a flow design tool such as Microsoft Visio, the flow of the business process is displayed graphically. For example, a business process flow of "Sales Department → IT Department → Quality Control Department → Marketing Department" is generated. In this process, the key information is used as input data, and a business process flow model is generated as output data.

[0575] Step 4:

[0576] The AI ​​analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. It uses a machine learning model to identify wasteful procedures and inefficient work. For example, it detects cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. The AI ​​sends these analysis results to a server. In this step, the business process flow model is the input data, and a list of waste and areas for improvement is the output data.

[0577] Step 5:

[0578] The AI ​​generates specific improvement proposals based on the identified waste and improvement points. These proposals may include centralizing data entry and automating the approval process. These proposals are presented after simulations are run to predict their effectiveness. The proposals are organized in text and visual formats and sent to a server. In this process, the list of waste and improvement points is the input data, and the improvement proposals are the output data.

[0579] Step 6:

[0580] The server generates a detailed report based on the improvement proposals and business process flow model presented by the AI. The report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then implement business process improvements based on this report. In this step, the improvement proposals and business process flow model are the input data, and the report is the output data.

[0581] (Application example 1)

[0582] 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."

[0583] Efficiently managing and analyzing complex business processes in today's corporate environment is challenging. Existing systems are particularly inadequate when it comes to real-time data collection and analysis, as well as immediate feedback. There is also a need to identify redundant steps and wasteful processes and quickly propose improvements, but there is a lack of comprehensive solutions that can achieve this. While real-time process optimization using autonomous machines is particularly important in factories and manufacturing lines, current technology does not adequately meet this need.

[0584] 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.

[0585] In this invention, the server includes: means for collecting request data; means for analyzing the collected data using a natural language processing engine and extracting key information; means for generating a business process flow model based on the extracted key information; means for identifying waste and areas for improvement based on an analysis of the generated business process flow model; means for presenting improvement proposals for the identified waste and areas for improvement; means for generating and outputting a report based on the improvement proposals and the business process flow model; means for being installed in an autonomous machine operating within a work area and for collecting and analyzing data in real time; and means for visually displaying the collected data and providing immediate feedback. This enables efficient data collection and analysis in real time even in factories and production lines, enabling immediate identification of waste and the presentation of effective improvement proposals.

[0586] "Request data" refers to data that includes advance information about a business process.

[0587] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning and information.

[0588] "Key information" refers to important attributes and elements in a business process, and includes information such as "delivery date" and "person in charge."

[0589] A "business process flow model" is a model that visually and systematically represents each step of a business process and the relationships between them.

[0590] "Waste" refers to unnecessary steps or duplication in business processes that hinder efficiency.

[0591] "Improvement points" are areas in a business process that require improvement in order to improve efficiency and quality.

[0592] An "improvement plan" is a specific proposal or method aimed at improving efficiency and quality in response to identified waste or areas for improvement.

[0593] A "report" is a document that includes information such as analysis results and improvement proposals, and is compiled in the form of text and charts.

[0594] An "autonomous machine" is a mechanical device that is designed to operate autonomously and perform a specific task or operation.

[0595] "Real-time" is a time concept that means data processing and analysis are carried out almost immediately.

[0596] "Visual display" means presenting analysis results and business models in a graphical format that is easy for people to understand.

[0597] "Immediate feedback" means immediately reflecting the results of data collection and analysis, and providing prompt notifications and suggestions for improvement to workers.

[0598] This invention is a system for efficiently managing and analyzing business processes within a factory. This system has the following main components and functions:

[0599] 1. System Configuration

[0600] Hardware:

[0601] Autonomous machines: Robots that move around the factory and collect the necessary data.

[0602] Server: A central processing unit that collects and analyzes data and generates reports.

[0603] Sensors: Various sensor devices mounted on autonomous machines to measure data.

[0604] software:

[0605] Natural language processing engine (spaCy): Analyzes collected text data and extracts key information.

[0606] Data analysis tools (PyPDF2, watchdog): Tools for analyzing PDF documents and monitoring the file system.

[0607] Graphical display tool (graphviz): A tool for visually displaying business process flow models.

[0608] 2. Data Collection

[0609] The server periodically retrieves new request data from the mail server, and autonomous machines in the factory use sensors to collect data in real time and send it to the server, ensuring that the latest information about business processes is always available.

[0610] 3. Data Analysis

[0611] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data. Through the analysis, key information such as "delivery date" and "person in charge" is extracted. This information forms the basis for the next step, business process flow modeling.

[0612] 4. Flow Modeling

[0613] The server generates a business process flow model based on the extracted key information. This flow model visually represents the business procedures and the relationships between each step, and clearly shows the data flow. A graphical display tool (e.g., graphviz) is used for display.

[0614] 5. Identifying waste and areas for improvement

[0615] AI analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. For example, it can identify cases where the same data is being entered multiple times across multiple departments, or where there are multiple approval steps that are delaying work. Waste and areas for improvement are analyzed with high precision using machine learning models.

[0616] 6. Proposal for improvement

[0617] AI proposes specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness. The proposals are organized in text and visual formats for easy understanding.

[0618] 7. Report Generation

[0619] The server generates a detailed report based on the improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the factory manager.

[0620] Specific examples

[0621] A concrete example is process improvement in a manufacturing plant. Autonomous machines collect data from the product line and send it to a server. Natural language processing reveals that there is a lot of overlapping data between "Production Line 1" and the "Quality Control Department." AI analyzes this and suggests an automated data entry system. The server compiles these suggestions into a report and presents it to the plant manager.

[0622] Example prompt sentence:

[0623] Input: Data from production line 1 to the quality control department. PDF data collected by robot scanning.

[0624] Output: A report containing a business process flow model, wasteful steps, and improvement suggestions.

[0625] The above are the main components and procedures for implementing the present invention, which can improve the efficiency and quality of work processes within a factory.

[0626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0627] Step 1: Data collection

[0628] The server periodically polls the mail server to retrieve new request emails and database application emails. At the same time, autonomous machines move around the factory and use sensors to collect data in real time, which is then sent to the server.

[0629] Input: Request emails and data sent from each department within the factory, and real-time data from sensors.

[0630] Output: Request data and real-time data collected on the server.

[0631] Specific operation: The server obtains the latest data from the mail server and sensors and stores it in a database.

[0632] Step 2: Data analysis

[0633] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data and extracts key information such as "delivery date" and "person in charge."

[0634] Input: Requested data and real-time data collected in step 1.

[0635] Output: Extracted key information (e.g., "Delivery Date", "Contact Person", etc.).

[0636] Specific operation: The server sends text data to the natural language processing engine, obtains the analysis results, and stores the key information in a database.

[0637] Step 3: Flow Modeling

[0638] The server generates a business process flow model based on the extracted key information, which visually represents the business procedures and the relationships between each step.

[0639] Input: The key information extracted in step 2.

[0640] Output: Business process flow model.

[0641] Specific operation: The server analyzes the key information and generates a flow model using a graphical display tool (e.g., graphviz).

[0642] Step 4: Identify waste and areas for improvement

[0643] The AI ​​on the server analyzes the generated business process flow model and identifies unnecessary steps and process gaps, such as when the same data is being entered multiple times across multiple departments.

[0644] Input: The business process flow model generated in step 3.

[0645] Output: Results identifying wasteful steps and gaps in the process.

[0646] How it works: The AI ​​on the server uses machine learning models to analyze the flow model and identify waste and areas for improvement.

[0647] Step 5: Propose improvements

[0648] AI generates specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness.

[0649] Input: Wasteful steps or process gaps identified in Step 4.

[0650] Output: Improvement suggestions (text and visual formats).

[0651] Specific operation: The AI ​​runs a simulation, generates improvement proposals, and sends them to the server.

[0652] Step 6: Generate reports

[0653] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI, and the report is output in PDF or HTML format and submitted to the user.

[0654] Input: Improvement proposals and business process flow models generated in Step 5.

[0655] Output: Detailed report in PDF or HTML format.

[0656] Specific operation: The server integrates the improvement proposal and the flow model, generates a report using a report creation tool, and saves it in the specified format.

[0657] Step 7: Real-time feedback

[0658] The autonomous machines visually display the data they collect and provide immediate feedback to factory workers, allowing them to review and take action on suggested improvements in real time.

[0659] Input: Real-time data continuously obtained from step 1.

[0660] Output: Visual feedback and improvement suggestions for the worker.

[0661] Specific operation: The autonomous machine notifies the worker of the results of data analysis via a display and audio alert, prompting immediate action.

[0662] 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.

[0663] System Overview

[0664] This invention is a new system for streamlining business processes. It combines conventional business flow management with an emotion engine that analyzes user emotions to achieve more precise and effective business improvements. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. The system then analyzes the generated business process flow model to identify waste and areas for improvement. The emotion engine then recognizes user emotions and incorporates them into the business process flow model to generate more precise improvement proposals and output them as a report.

[0665] Program processing description

[0666] 1. Data Collection

[0667] Subject: Server

[0668] The server periodically retrieves new emails from the mail server, and database application forms and related documents from the file server. These data are temporarily stored in storage.

[0669] 2. Data Analysis

[0670] Subject: Server

[0671] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. As a result of the analysis, key information important for business processing (e.g., "delivery date," "person in charge," and "content") is extracted.

[0672] 3. Flow Modeling

[0673] Subject: Server

[0674] The server generates a business process flow model based on the extracted key information. The generated model visually represents a series of business procedures and processes and is displayed in a flow design tool or dashboard.

[0675] 4. Emotion analysis

[0676] Subject: Emotion Engine

[0677] The emotion engine analyzes user emotions and uses that data to identify factors that affect the business process flow model. For example, it extracts emotional data from user emails and feedback and incorporates it into the business process model.

[0678] 5. Identifying waste and areas for improvement

[0679] Subject: AI

[0680] AI analyzes the generated business process flow model and sentiment data to detect wasteful steps and process gaps, thereby clearly indicating the identified wasteful and inefficient steps.

[0681] 6. Proposal for improvement

[0682] Subject: AI

[0683] The AI ​​generates specific improvement proposals based on the identified waste and areas for improvement, taking into account feedback based on emotional data to present optimal improvement proposals.

[0684] 7. Report Generation

[0685] Subject: Server

[0686] The server generates a detailed report based on the AI-generated improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The report is output in PDF or HTML format and provided to the user via their device.

[0687] Specific examples

[0688] Example: A new product development project

[0689] Data collection

[0690] The sales department sends an email requesting new product development.

[0691] The IT department submits the required database change request.

[0692] The marketing department sends out the survey data via email.

[0693] Data analysis

[0694] The server uses a natural language processing engine to extract information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the email.

[0695] Flow Modeling

[0696] The server generates and visualizes a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department.

[0697] Emotion analysis

[0698] The emotion engine analyzes emails and feedback from users (project managers) to detect pressure and stress levels.

[0699] Identifying waste and areas for improvement

[0700] The AI ​​pointed out that the same data was being entered multiple times across multiple departments and that there were multiple approval steps.

[0701] Proposal of improvement proposals

[0702] AI takes emotional data into account and suggests centralizing data entry and automating approval steps. For highly stressed employees, it also suggests allocating some of the tasks to other members.

[0703] Report Generation

[0704] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[0705] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[0706] The processing flow will be explained below.

[0707] Step 1:

[0708] Subject: Server

[0709] Specific operation: The server periodically accesses the mail server to retrieve new request emails and database application emails. The retrieved emails are saved in temporary storage. It also retrieves related documents such as database application forms from the file server or a specified folder. This is done using the file access API.

[0710] Step 2:

[0711] Subject: Server

[0712] Specific operation: The server sends the stored emails and documents to a natural language processing (NLP) engine, which analyzes the text data. The NLP engine tokenizes the text and extracts key information such as "delivery date," "person in charge," and "content." The extracted key information is saved in JSON format.

[0713] Step 3:

[0714] Subject: Server

[0715] Specific operation: The server generates a business process flow model based on the extracted key information. This model is a visual representation of a series of business procedures and processes, and is displayed in a business process design tool or dashboard. The model is then compared with an existing business process database to optimize the flow.

[0716] Step 4:

[0717] Subject: Emotion Engine

[0718] Specific operation: The emotion engine analyzes emails and feedback from users and extracts emotional data. For example, it uses text analysis to identify emotions such as "dissatisfaction," "stress," and "satisfaction" contained in user text. The extracted emotional data is incorporated into the business process flow model.

[0719] Step 5:

[0720] Subject: Server

[0721] Specific operation: The server uses AI to perform analysis based on a business process flow model that includes emotional data. The AI ​​identifies unnecessary steps and process gaps. This analysis also references past business data and statistical information.

[0722] Step 6:

[0723] Subject: AI

[0724] Specific operation: The AI ​​generates improvement proposals based on the business process flow model and emotion data. For example, it suggests distributing tasks to high-stress departments, centralizing data entry, automating procedures, etc. The improvement proposals are sent to the server in text and visual formats.

[0725] Step 7:

[0726] Subject: Server

[0727] Specific operation: The server integrates the AI-generated improvement proposals into the business process flow model and generates a detailed report. The report includes identified waste areas, improvement points, analysis results of emotion data, and proposed improvement proposals. The final report is output in PDF or HTML format and provided to the user.

[0728] Examples:

[0729] For new product development projects

[0730] Step 1:

[0731] The sales department sends an email requesting new product development.

[0732] The IT department stores the necessary database change request forms on a file server.

[0733] Step 2:

[0734] The server uses an NLP engine to extract keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the request email and application form.

[0735] Step 3:

[0736] The server generates a flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it on a dashboard.

[0737] Step 4:

[0738] The emotion engine analyzes feedback emails from users (staff) and extracts emotional data such as "high stress" and "dissatisfaction."

[0739] Step 5:

[0740] The server analyzes the flow model, which includes emotional data, and the AI ​​identifies unnecessary steps and inefficient processes.

[0741] Step 6:

[0742] The AI ​​takes emotional data into account and makes suggestions for distributing tasks, centralizing data entry, and automating tasks.

[0743] Step 7:

[0744] The server generates a report and provides it to the user in PDF format, which includes specific improvement suggestions, identified waste areas, and the results of the analysis of sentiment data.

[0745] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[0746] Example 2

[0747] 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."

[0748] In modern business processes, traditional workflow management systems have improved efficiency in some respects, but they do not take into account the emotional burden and stress placed on users. Therefore, while improving the overall efficiency and quality of work, there is a need for systems that take into account the emotional state of users and appropriately allocate the workload. Furthermore, there is a need for systems that can automatically identify wasteful and inefficient steps and propose specific improvement proposals.

[0749] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0750] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on the analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for analyzing user emotions, and means for integrating emotion analysis data into the business process flow model. This improves the efficiency and quality of business processes and enables appropriate workload allocation taking into account the emotional state of users.

[0751] "Request data" refers to necessary information and requirements related to business operations, and includes document data such as emails and application forms.

[0752] A "natural language processing engine" refers to a group of algorithms and programs that allow a computer to understand and analyze human language.

[0753] "Key information" refers to important data items in a business process, and includes, for example, "delivery date" and "person in charge."

[0754] A "business process flow model" is a model that visually represents a business process, and includes a diagrammatic representation of business procedures and process flows.

[0755] "Emotion analysis" refers to the process of analyzing a user's emotional state from text data and feedback, and assessing their psychological state, such as stress and satisfaction.

[0756] "Improvement proposals" refer to specific proposals and measures aimed at streamlining business processes and improving quality.

[0757] A "machine learning model" refers to a group of algorithms or programs that learn from large amounts of data and automatically analyze patterns and trends.

[0758] A "report" is a document that summarizes analysis results and improvement proposals, and is provided in PDF or HTML format.

[0759] "Emotion analysis data" refers to data relating to the user's emotional state obtained as a result of emotion analysis.

[0760] This invention is a system for streamlining business processes and improving business processes by taking into account the emotional state of users. This system combines multiple hardware and software components to collect and analyze request data, generate a business process flow model, identify waste and areas for improvement, and present improvement proposals that integrate user emotional data.

[0761] Hardware and Software Configuration

[0762] Hardware:

[0763] Server: Responsible for main processes such as data collection, analysis, flow modeling, and report generation.

[0764] Terminal: Serves as an interface for users to access and view the generated reports.

[0765] software:

[0766] Natural language processing engine: Analyzes requested data and extracts key information using Google Cloud Natural Language API, etc.

[0767] Emotion analysis engine: Using IBM Watson Tone Analyzer and other tools, analyzes the user's emotional state and generates numerical data.

[0768] Machine learning models: Used to analyze business process flow models and sentiment data to identify waste and areas for improvement.

[0769] Dashboard tools: Visualize business process flow models using tools such as Microsoft Power BI.

[0770] Program Processing Overview

[0771] The program of this system implements the following main functions:

[0772] 1. Data Collection:

[0773] The server periodically retrieves new emails from the mail server and stores them in storage. It also collects related documents such as database application forms from the file server and stores them in storage.

[0774] 2. Data Analysis:

[0775] The server sends the emails and documents stored in the storage to a natural language processing engine, which analyzes the text data. Important key information (e.g., "delivery date," "person in charge," and "content") is extracted and stored in a database.

[0776] 3. Flow Modeling:

[0777] The server generates a business process flow model based on the key information stored in the database. The generated model is visualized using a dashboard tool.

[0778] 4. Emotion analysis:

[0779] The emotion engine analyzes emails and feedback forms sent by users and generates numerical data representing the user's emotional state. This emotional data is sent to the server and integrated into the business process flow model.

[0780] 5. Identify waste and areas for improvement:

[0781] AI analyzes business process flow models and sentiment analysis data to identify unnecessary steps and inefficiencies.

[0782] 6. Proposal for improvement:

[0783] Based on the identified waste and areas for improvement, the AI ​​generates specific improvement proposals, taking into account emotional data and proposing things like workload and task reallocation.

[0784] 7. Report Generation:

[0785] The server creates a detailed report based on the generated improvement proposals and business process flow model. The report is output in PDF or HTML format and provided to the user via their terminal.

[0786] Specific examples

[0787] For new product development projects

[0788] Data collection: The server collects emails requesting new product development sent by the sales department and database change request forms sent by the IT department, and stores them in storage.

[0789] Data analysis: The server analyzes the request email, extracts key information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka", and stores it in a database.

[0790] Flow modeling: Based on the extracted key information, the server generates a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it using a dashboard tool.

[0791] Sentiment analysis: The emotion engine analyzes emails and feedback sent by project managers and generates emotional data such as "high stress level."

[0792] Identifying waste and areas for improvement: AI analyzes workflow models and sentiment data to identify duplicate data entries across multiple departments and multiple approval steps.

[0793] Suggested improvements: AI can suggest improvements such as centralizing data entry, automating approval steps, or delegating specific tasks to other members.

[0794] Report generation: The server generates a detailed report based on the improvement proposal and provides it to the person in charge (Tanaka) via the terminal.

[0795] Example prompt sentence:

[0796] Please extract key information about the business flow from the following email. Email content: 'The sales department requests the start of the next new product development project as follows. The deadline is 2023-12-31, and the person in charge is Tanaka.'

[0797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0798] Step 1:

[0799] The server periodically retrieves new emails from the mail server. The mail server connection information and a query to retrieve new emails are used as input. The server temporarily stores the retrieved emails in storage. It also collects database application forms and related documents from the file server and stores them in storage. This completes the collection of request data.

[0800] Step 2:

[0801] The server sends the emails and documents stored in storage to a natural language processing engine (e.g., Google Cloud Natural Language API). The stored emails and documents are used as input. The natural language processing engine analyzes the text data and extracts key information such as delivery date, person in charge, and content. The server stores the extracted key information in a database and records the analysis results in a log. This extracts the key information.

[0802] Step 3:

[0803] The server generates a business process flow model based on key information stored in the database. The key information is used as input. The server uses this key information to visualize the business flow step by step, creating a series of business procedures and processes. The generated business process flow model is visualized using a dashboard tool. This generates a business process flow model.

[0804] Step 4:

[0805] The emotion engine (e.g. IBM Watson Tone Analyzer) analyzes emails and feedback forms sent by users. The emails and feedback sent by users are used as input. The emotion engine analyzes the user's emotional state (e.g. stress, satisfaction, etc.) from this text data and generates numerical data. The emotion analysis data is sent to the server, which then analyzes the user's emotional state.

[0806] Step 5:

[0807] The AI ​​uses the business process flow model and sentiment analysis data provided by the server to identify wasteful steps and inefficient areas. The business process flow model and sentiment analysis data are used as input. The AI ​​performs analysis using a machine learning model, generates a report detailing the identified problems, and sends it to the server. This identifies waste and areas for improvement.

[0808] Step 6:

[0809] The AI ​​creates specific improvement proposals based on the identified waste and improvement points. The waste and improvement points are used as input. The AI ​​generates improvement proposals that include suggestions for centralizing data entry, automating approval steps, and reassigning tasks. Sentiment analysis data is also taken into account, and measures to reduce user stress are included. The improvement proposals are sent to the server. This generates specific improvement proposals.

[0810] Step 7:

[0811] The server creates a detailed report based on the improvement proposals provided by the AI. The improvement proposals and the business process flow model are used as input. The server generates a report that includes a visual representation of the business process flow model, detected problems, and specific improvement suggestions. The generated report is output in PDF or HTML format and provided to the user via their terminal. This completes the report generation process.

[0812] (Application example 2)

[0813] 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."

[0814] Conventional business process management systems have the problem that they are unable to take into account the emotions and stress levels of users when identifying wasteful work flows and areas for improvement, making it difficult to improve work efficiently. This problem is particularly important in brick-and-mortar stores, where the emotions and motivation of staff members directly affect work efficiency.

[0815] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for incorporating user emotion data into the generated business process flow model and performing emotion analysis, means for identifying waste and improvement points based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and improvement points, and means for generating and outputting a report based on the improvement proposals and the business process flow model. This enables precise business improvement that takes user emotions into consideration.

[0816] "Request data" refers to data that includes information and requirements related to business processes.

[0817] A "natural language processing engine" is a software function that analyzes text data and extracts meaning and key information.

[0818] "Key information" is information that extracts important parameters and topics from the collected data.

[0819] A "business process flow model" is a model that visually and structurally represents business procedures and processes.

[0820] "Emotion analysis" is a method of converting user emotions into data and using the results to identify factors that affect business processes.

[0821] "Waste" refers to inefficient steps or unnecessary work in a business process.

[0822] "Improvement points" refer to areas that can be improved to make business processes more efficient.

[0823] "Improvement proposals" refer to specific proposals for eliminating waste and inefficiencies in business processes.

[0824] The "means for generating and outputting reports" is a function that creates a detailed report based on the generated business process flow model and improvement proposals, and provides it to the user.

[0825] "Emotion data" is data obtained by analyzing and quantifying the user's emotional state.

[0826] "Structured data" is data in which key information is organized and arranged according to a certain format.

[0827] A "machine learning model" is an algorithm that recognizes patterns based on data and automatically performs analysis and predictions.

[0828] System Overview

[0829] The present invention is a new system that combines the efficiency of business processes in brick-and-mortar stores with user emotion analysis. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. Then, it analyzes user emotions using an emotion engine and incorporates them into the business process flow model to generate precise improvement proposals and output them as a report. Specific embodiments are described below.

[0830] Hardware and software used

[0831] Smartphones: Used as individual staff devices.

[0832] Emotion engine: Powered by Microsoft Azure Cognitive Services.

[0833] Natural language processing engine: Uses Google Cloud Natural Language API.

[0834] Database: Uses Firebase Realtime Database.

[0835] Flow Design Tool: A flow design dashboard powered by React.js.

[0836] Program processing

[0837] The server includes the following means:

[0838] 1. Data Collection Methods

[0839] The server collects business data from each device in the store. For example, it aggregates business data entered by staff on their smartphones and event data from sensors. This data is temporarily stored in a database.

[0840] 2. Natural Language Processing Methods

[0841] The collected data is sent to the server's natural language processing engine, where key information is extracted, such as "break time," "number of customer interactions," and "product replenishment work."

[0842] 3. Method for generating business process flow models

[0843] Based on the extracted key information, a business process flow model is generated on the server. This model visually represents business procedures and processes and can be viewed on a dashboard.

[0844] 4. Emotion analysis means

[0845] The server uses an emotion engine to analyze the emotional data of the staff, which is expressed as, for example, the staff's "stress level" or "motivation index."

[0846] 5. Identifying waste and areas for improvement

[0847] Based on the generated business process flow model and emotional data, AI identifies unnecessary steps and areas for improvement, focusing on analyzing business flows where the emotional data indicates high stress.

[0848] 6. Means for presenting improvement proposals

[0849] The server generates specific improvement proposals based on the identified waste and improvement points, such as centralizing data entry, automating approval steps, and redistributing tasks.

[0850] 7. Report Generation Methods

[0851] The server generates a detailed report based on the business process flow model and improvement proposals, and outputs it in PDF or HTML format. The report can be viewed on a smartphone or PC.

[0852] Specific examples

[0853] Example: Improving business processes in physical stores

[0854] In physical stores, staff record their daily work on their smartphones. For example, data such as "product inventory" and "customer service details" is entered. The data is stored in a Firebase database, and the server periodically retrieves it. A natural language processing engine extracts key information and generates a business process flow model. An emotion engine analyzes staff daily reports and feedback emails to detect stress levels. AI identifies unnecessary steps and areas for improvement, and proposes specific improvement proposals, including automating data entry and dividing up tasks. Finally, a detailed report is generated and provided to managers.

[0855] Prompt Sentence Examples

[0856] "We are developing a new operational improvement tool for our brick-and-mortar stores. This tool analyzes staff work processes and emotions and generates specific improvement proposals. Please explain the steps to perform the following operations.

[0857] 1. Collecting data from Firebase Realtime Database

[0858] 2. Obtaining sentiment scores using a sentiment analysis engine

[0859] 3. Creation and visualization of business flow models

[0860] 4. Preparation of a detailed report with improvement suggestions

[0861] The present invention enables precise business improvement that takes into account the user's emotions.

[0862] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0863] Step 1:

[0864] The server collects business data from each device in the physical store. Specifically, it aggregates business data entered by staff on their smartphones and event data from sensors in the store. The entered data is collected in file format or via API, and temporarily stored in the Firebase Realtime Database. This data becomes the input data for the next processing step.

[0865] Step 2:

[0866] The server retrieves the collected data from Firebase and sends it to a natural language processing engine (Google Cloud Natural Language API). At this time, business data in text format becomes the input data. The natural language processing engine analyzes this data and extracts key information important to the business process (for example, "break time," "number of customer interactions," "product replenishment work," etc.). The extracted key information is sent to the next step as output data.

[0867] Step 3:

[0868] The server generates a business process flow model based on the extracted key information. The input data is the key information extracted in the previous step, and the generated business process flow model is expressed in XML or JSON format. This model visually represents business procedures and processes, and is displayed on a flow design dashboard using React.js. The generated business process flow model becomes the output data.

[0869] Step 4:

[0870] The server uses an emotion engine (Microsoft Azure Cognitive Services) to analyze staff emotional data. The input data is staff daily reports and feedback emails. The emotion engine analyzes this text data and generates emotional scores such as "stress level" and "motivation index" as output data.

[0871] Step 5:

[0872] The server reanalyzes the business process model based on the generated business process flow model and emotion score. The input data are the business process flow model and emotion score, and the AI ​​(machine learning model) identifies wasteful steps and areas for improvement. For example, if a high stress level is detected in a specific business process, it suggests that the business steps are inefficient. A business process flow model with wasteful steps and areas for improvement marked is generated as output data.

[0873] Step 6:

[0874] The server generates specific improvement proposals based on the identified waste and improvement points. The input data is a business process flow model that includes wasteful steps and improvement points. The AI ​​generates specific improvement proposals, such as centralizing data entry, automating approval steps, and redistributing tasks. The generated improvement proposals are sent to the next step as output data.

[0875] Step 7:

[0876] The server generates a detailed report based on the business process flow model and improvement proposals. The input data are the improvement proposals and the business process flow model. The server formats this data into a document and creates a report in PDF or HTML format. The generated report is sent to the user's device as output data. The user can view the report on their smartphone or computer and use it as a guideline for specific business improvements.

[0877] Through the above steps, precise business improvement that takes into account the user's emotions is realized.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] [Third embodiment]

[0882] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0883] 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.

[0884] 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).

[0885] 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.

[0886] 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.

[0887] 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).

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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."

[0894] System Overview

[0895] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[0896] Program processing description

[0897] 1. Data Collection

[0898] Subject: Server

[0899] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or designated folders. This makes it possible to comprehensively collect request data related to all business processes.

[0900] 2. Data Analysis

[0901] Subject: Server

[0902] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations, allowing it to be used efficiently.

[0903] 3. Flow Modeling

[0904] Subject: Server

[0905] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. This model is displayed graphically using a flow design tool.

[0906] 4. Identifying waste and areas for improvement

[0907] Subject: AI

[0908] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps, explicitly identifying factors that hinder business efficiency, such as multiple data entry or multiple approval steps that delay procedures.

[0909] 5. Proposal for improvement

[0910] Subject: AI

[0911] The AI ​​generates specific improvement proposals for the identified waste and improvement points. The proposals are simulated to predict their effects and then present the optimal solution. The proposals are organized in text and visual formats and sent to the server.

[0912] 6. Report Generation

[0913] Subject: Server

[0914] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user.

[0915] Specific examples

[0916] Example: A new product development project

[0917] Data collection

[0918] The server collects emails such as new product development requests from the sales department and database change requests from the IT department.

[0919] Data analysis

[0920] The natural language processing engine extracts keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka."

[0921] Flow Modeling

[0922] The server generates a business processing flow from the sales department to the IT department to the quality control department to the marketing department, and displays it graphically.

[0923] Identifying waste and areas for improvement

[0924] AI points out that the same data is being entered multiple times across multiple departments, and that multiple approval steps are causing delays in work.

[0925] Proposal of improvement proposals

[0926] AI suggests centralizing data entry and automating approval steps.

[0927] Report Generation

[0928] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[0929] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[0930] The processing flow will be explained below.

[0931] Step 1:

[0932] Subject: Server

[0933] Specific operation: The server connects to the mail server at regular intervals to retrieve new emails. This is done using the POP3 or IMAP protocol. The retrieved emails are saved in temporary storage. It also scans database application forms and related documents from the file server or a specified folder and saves them in temporary storage as well.

[0934] Step 2:

[0935] Subject: Server

[0936] Specific operation: The server analyzes the stored emails and documents and sends them to a natural language processing engine. The natural language processing engine tokenizes the email body and documents and extracts key information (delivery date, person in charge, content, etc.). The extracted key information is saved as structured data in JSON format or similar.

[0937] Step 3:

[0938] Subject: Server

[0939] Specific operation: The server generates a business process flow model based on the extracted structured data. In this process, it compares it with an existing business process database and determines the sequence of business steps. The generated business process flow model is saved in BPMN (Business Process Model and Notation) format and displayed in a flow design tool or dashboard.

[0940] Step 4:

[0941] Subject: AI

[0942] How it works: The AI ​​analyzes the generated business process flow model and identifies wasteful or inefficient steps within the process. For example, it detects cases where the same data is being entered multiple times by multiple departments or where there are unnecessary approval steps. This is done using past statistical data and a rule base.

[0943] Step 5:

[0944] Subject: AI

[0945] Specific Actions: Based on the identified waste and improvement points, the AI ​​generates specific improvement suggestions, such as centralizing data entry and automating approval processes. The improvement suggestions are organized in text and visual formats and used to generate subsequent reports.

[0946] Step 6:

[0947] Subject: Server

[0948] Specific operation: The server generates a report based on the improvement proposals generated by the AI ​​and the business process flow model. This report includes a visualization of the business process flow in graphs and charts, details of waste and improvement points, and the proposed improvement proposals. The generated report is output in PDF or HTML format and provided to the user.

[0949] Example 1

[0950] 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."

[0951] Today's increasingly complex business processes require efficient management and analysis, but manual data collection and analysis is time-consuming and prone to errors. It's also difficult to identify wasteful or inefficient parts of business processes, and finding solutions requires a great deal of time and effort. This creates challenges, reducing the efficiency of the entire company and hindering smooth business operations.

[0952] 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.

[0953] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for visually displaying the business process flow model, means for polling new data from a mail server and a file server at a specific interval, and means for using an external API as the natural language processing engine. This makes it possible to rapidly and accurately identify waste in business processes and present specific improvement proposals, thereby significantly improving the efficiency of the entire business.

[0954] "Request data" refers to data that includes information about requests and applications related to business processes.

[0955] A "natural language processing engine" is software or an API for analyzing text data and extracting key information.

[0956] "Key information" is specific information that is considered important in a business process, such as deadlines, people in charge, and content.

[0957] A "business process flow model" is a model that visually represents the flow of a series of business procedures and processes.

[0958] "Waste" refers to unnecessary steps and inefficient operations in a business process.

[0959] "Improvement points" are points that need to be improved to improve the efficiency of a business process.

[0960] An "improvement proposal" is a proposal that presents specific solutions to waste or areas for improvement.

[0961] A "report" is a document that includes details of improvement proposals and business process flow models.

[0962] "Visually displaying" means expressing a business process flow model graphically and providing it to the user in a format that is easy to understand.

[0963] "Polling" is the process of periodically checking and collecting new data from a server.

[0964] An "external API" is an interface for accessing functions provided by other software or services.

[0965] MODE FOR CARRYING OUT THE INVENTION

[0966] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[0967] Data collection

[0968] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or specified folders. This makes it possible to comprehensively collect request data related to all business processes. Specifically, the server accesses the mail server at a specific interval, every five minutes, to check whether new emails exist. This process uses standard mail server protocols (e.g., IMAP or POP3).

[0969] Data analysis

[0970] The server sends the retrieved emails and documents to a natural language processing engine (e.g., Google NLP API), which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations and enables it to be used efficiently. The key information is stored as structured data in a database on the server side and is used for subsequent processing.

[0971] Flow Modeling

[0972] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. The model is displayed graphically using a flow design tool such as Microsoft Visio. This makes it easier for employees to understand the overall picture of the business process and make decisions regarding the flow of work.

[0973] Identifying waste and areas for improvement

[0974] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps. This explicitly identifies factors that hinder business efficiency. For example, it identifies cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. Using a machine learning model enables highly accurate analysis based on past data.

[0975] Proposal of improvement proposals

[0976] AI generates specific improvement proposals for identified waste and improvement points. The proposals are simulated to predict their effects and then present optimal solutions. For example, it suggests centralizing data entry and automating approval processes. The proposals are organized in text and visual formats and sent to a server, allowing for the rapid provision of specific, actionable improvement measures.

[0977] Report Generation

[0978] The server generates a detailed report based on the improvement proposals proposed by the AI ​​and the business process flow model. This report includes specific improvement proposals for reducing waste in business and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then use this report to implement improvements to their business processes.

[0979] Specific examples

[0980] Example: A new product development project

[0981] Data collection

[0982] The server collects emails from the sales department requesting new product development, emails from the IT department requesting database changes, etc. It also retrieves newly added document files from designated folders on the file server.

[0983] Data analysis

[0984] A natural language processing engine (e.g., Google NLP API) extracts key information such as "Delivery date: 2023-12-31," "Person in charge: Tanaka," and "New product specifications," and the server stores this in a database.

[0985] Flow Modeling

[0986] The server generates a business flow model of "Sales Department → IT Department → Quality Control Department → Marketing Department" and displays it visually using Microsoft Visio.

[0987] Identifying waste and areas for improvement

[0988] AI detects duplicate data entry across departments and multiple approval steps that delay work.

[0989] Proposal of improvement proposals

[0990] AI will propose centralizing data entry and automating approval processes, and will also perform simulations to predict the effects.

[0991] Report Generation

[0992] The server generates a report containing specific improvement proposals and submits it to the user in PDF format, allowing the user to implement improvements to their business processes based on this report.

[0993] Prompt Sentence Examples

[0994] "Please tell us some specific improvement ideas for streamlining the business processes in new product development projects."

[0995] "Please identify waste in the database change application process and suggest improvements."

[0996] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[0997] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0998] Step 1:

[0999] The server collects request data from the mail server and file server. The server accesses the mail server every five minutes to check for new emails. If new emails exist, it reads their contents and searches the subject and body of the email for keywords related to "request" or "application." At the same time, the server accesses the specified folder on the file server to retrieve newly added document files. This process obtains the request data as input, which is used in the next step.

[1000] Step 2:

[1001] The server sends the collected emails and documents to a natural language processing engine. Specifically, it uses the Google NLP API to analyze the text data. This engine extracts important key information for business processing. For example, information such as "delivery date," "person in charge," and "content" is obtained as analysis results. The server then stores this extracted key information in a database as structured data. Through this process, emails and documents become input data, and the key information becomes output data.

[1002] Step 3:

[1003] The server generates a business process flow model based on the key information stored in the database. From the extracted key information, a series of business procedures and processes are visually represented in the form of a flowchart. Using a flow design tool such as Microsoft Visio, the flow of the business process is displayed graphically. For example, a business process flow of "Sales Department → IT Department → Quality Control Department → Marketing Department" is generated. In this process, the key information is used as input data, and a business process flow model is generated as output data.

[1004] Step 4:

[1005] The AI ​​analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. It uses a machine learning model to identify wasteful procedures and inefficient work. For example, it detects cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. The AI ​​sends these analysis results to a server. In this step, the business process flow model is the input data, and a list of waste and areas for improvement is the output data.

[1006] Step 5:

[1007] The AI ​​generates specific improvement proposals based on the identified waste and improvement points. These proposals may include centralizing data entry and automating the approval process. These proposals are presented after simulations are run to predict their effectiveness. The proposals are organized in text and visual formats and sent to a server. In this process, the list of waste and improvement points is the input data, and the improvement proposals are the output data.

[1008] Step 6:

[1009] The server generates a detailed report based on the improvement proposals and business process flow model presented by the AI. The report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then implement business process improvements based on this report. In this step, the improvement proposals and business process flow model are the input data, and the report is the output data.

[1010] (Application example 1)

[1011] 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."

[1012] Efficiently managing and analyzing complex business processes in today's corporate environment is challenging. Existing systems are particularly inadequate when it comes to real-time data collection and analysis, as well as immediate feedback. There is also a need to identify redundant steps and wasteful processes and quickly propose improvements, but there is a lack of comprehensive solutions that can achieve this. While real-time process optimization using autonomous machines is particularly important in factories and manufacturing lines, current technology does not adequately meet this need.

[1013] 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.

[1014] In this invention, the server includes: means for collecting request data; means for analyzing the collected data using a natural language processing engine and extracting key information; means for generating a business process flow model based on the extracted key information; means for identifying waste and areas for improvement based on an analysis of the generated business process flow model; means for presenting improvement proposals for the identified waste and areas for improvement; means for generating and outputting a report based on the improvement proposals and the business process flow model; means for being installed in an autonomous machine operating within a work area and for collecting and analyzing data in real time; and means for visually displaying the collected data and providing immediate feedback. This enables efficient data collection and analysis in real time even in factories and production lines, enabling immediate identification of waste and the presentation of effective improvement proposals.

[1015] "Request data" refers to data that includes advance information about a business process.

[1016] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning and information.

[1017] "Key information" refers to important attributes and elements in a business process, and includes information such as "delivery date" and "person in charge."

[1018] A "business process flow model" is a model that visually and systematically represents each step of a business process and the relationships between them.

[1019] "Waste" refers to unnecessary steps or duplication in business processes that hinder efficiency.

[1020] "Improvement points" are areas in a business process that require improvement in order to improve efficiency and quality.

[1021] An "improvement plan" is a specific proposal or method aimed at improving efficiency and quality in response to identified waste or areas for improvement.

[1022] A "report" is a document that includes information such as analysis results and improvement proposals, and is compiled in the form of text and charts.

[1023] An "autonomous machine" is a mechanical device that is designed to operate autonomously and perform a specific task or operation.

[1024] "Real-time" is a time concept that means data processing and analysis are carried out almost immediately.

[1025] "Visual display" means presenting analysis results and business models in a graphical format that is easy for people to understand.

[1026] "Immediate feedback" means immediately reflecting the results of data collection and analysis, and providing prompt notifications and suggestions for improvement to workers.

[1027] This invention is a system for efficiently managing and analyzing business processes within a factory. This system has the following main components and functions:

[1028] 1. System Configuration

[1029] Hardware:

[1030] Autonomous machines: Robots that move around the factory and collect the necessary data.

[1031] Server: A central processing unit that collects and analyzes data and generates reports.

[1032] Sensors: Various sensor devices mounted on autonomous machines to measure data.

[1033] software:

[1034] Natural language processing engine (spaCy): Analyzes collected text data and extracts key information.

[1035] Data analysis tools (PyPDF2, watchdog): Tools for analyzing PDF documents and monitoring the file system.

[1036] Graphical display tool (graphviz): A tool for visually displaying business process flow models.

[1037] 2. Data Collection

[1038] The server periodically retrieves new request data from the mail server, and autonomous machines in the factory use sensors to collect data in real time and send it to the server, ensuring that the latest information about business processes is always available.

[1039] 3. Data Analysis

[1040] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data. Through the analysis, key information such as "delivery date" and "person in charge" is extracted. This information forms the basis for the next step, business process flow modeling.

[1041] 4. Flow Modeling

[1042] The server generates a business process flow model based on the extracted key information. This flow model visually represents the business procedures and the relationships between each step, and clearly shows the data flow. A graphical display tool (e.g., graphviz) is used for display.

[1043] 5. Identifying waste and areas for improvement

[1044] AI analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. For example, it can identify cases where the same data is being entered multiple times across multiple departments, or where there are multiple approval steps that are delaying work. Waste and areas for improvement are analyzed with high precision using machine learning models.

[1045] 6. Proposal for improvement

[1046] AI proposes specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness. The proposals are organized in text and visual formats for easy understanding.

[1047] 7. Report Generation

[1048] The server generates a detailed report based on the improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the factory manager.

[1049] Specific examples

[1050] A concrete example is process improvement in a manufacturing plant. Autonomous machines collect data from the product line and send it to a server. Natural language processing reveals that there is a lot of overlapping data between "Production Line 1" and the "Quality Control Department." AI analyzes this and suggests an automated data entry system. The server compiles these suggestions into a report and presents it to the plant manager.

[1051] Example prompt sentence:

[1052] Input: Data from production line 1 to the quality control department. PDF data collected by robot scanning.

[1053] Output: A report containing a business process flow model, wasteful steps, and improvement suggestions.

[1054] The above are the main components and procedures for implementing the present invention, which can improve the efficiency and quality of work processes within a factory.

[1055] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1056] Step 1: Data collection

[1057] The server periodically polls the mail server to retrieve new request emails and database application emails. At the same time, autonomous machines move around the factory and use sensors to collect data in real time, which is then sent to the server.

[1058] Input: Request emails and data sent from each department within the factory, and real-time data from sensors.

[1059] Output: Request data and real-time data collected on the server.

[1060] Specific operation: The server obtains the latest data from the mail server and sensors and stores it in a database.

[1061] Step 2: Data analysis

[1062] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data and extracts key information such as "delivery date" and "person in charge."

[1063] Input: Requested data and real-time data collected in step 1.

[1064] Output: Extracted key information (e.g., "Delivery Date", "Contact Person", etc.).

[1065] Specific operation: The server sends text data to the natural language processing engine, obtains the analysis results, and stores the key information in a database.

[1066] Step 3: Flow Modeling

[1067] The server generates a business process flow model based on the extracted key information, which visually represents the business procedures and the relationships between each step.

[1068] Input: The key information extracted in step 2.

[1069] Output: Business process flow model.

[1070] Specific operation: The server analyzes the key information and generates a flow model using a graphical display tool (e.g., graphviz).

[1071] Step 4: Identify waste and areas for improvement

[1072] The AI ​​on the server analyzes the generated business process flow model and identifies unnecessary steps and process gaps, such as when the same data is being entered multiple times across multiple departments.

[1073] Input: The business process flow model generated in step 3.

[1074] Output: Results identifying wasteful steps and gaps in the process.

[1075] How it works: The AI ​​on the server uses machine learning models to analyze the flow model and identify waste and areas for improvement.

[1076] Step 5: Propose improvements

[1077] AI generates specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness.

[1078] Input: Wasteful steps or process gaps identified in Step 4.

[1079] Output: Improvement suggestions (text and visual formats).

[1080] Specific operation: The AI ​​runs a simulation, generates improvement proposals, and sends them to the server.

[1081] Step 6: Generate reports

[1082] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI, and the report is output in PDF or HTML format and submitted to the user.

[1083] Input: Improvement proposals and business process flow models generated in Step 5.

[1084] Output: Detailed report in PDF or HTML format.

[1085] Specific operation: The server integrates the improvement proposal and the flow model, generates a report using a report creation tool, and saves it in the specified format.

[1086] Step 7: Real-time feedback

[1087] The autonomous machines visually display the data they collect and provide immediate feedback to factory workers, allowing them to review and take action on suggested improvements in real time.

[1088] Input: Real-time data continuously obtained from step 1.

[1089] Output: Visual feedback and improvement suggestions for the worker.

[1090] Specific operation: The autonomous machine notifies the worker of the results of data analysis via a display and audio alert, prompting immediate action.

[1091] 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.

[1092] System Overview

[1093] This invention is a new system for streamlining business processes. It combines conventional business flow management with an emotion engine that analyzes user emotions to achieve more precise and effective business improvements. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. The system then analyzes the generated business process flow model to identify waste and areas for improvement. The emotion engine then recognizes user emotions and incorporates them into the business process flow model to generate more precise improvement proposals and output them as a report.

[1094] Program processing description

[1095] 1. Data Collection

[1096] Subject: Server

[1097] The server periodically retrieves new emails from the mail server, and database application forms and related documents from the file server. These data are temporarily stored in storage.

[1098] 2. Data Analysis

[1099] Subject: Server

[1100] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. As a result of the analysis, key information important for business processing (e.g., "delivery date," "person in charge," and "content") is extracted.

[1101] 3. Flow Modeling

[1102] Subject: Server

[1103] The server generates a business process flow model based on the extracted key information. The generated model visually represents a series of business procedures and processes and is displayed in a flow design tool or dashboard.

[1104] 4. Emotion analysis

[1105] Subject: Emotion Engine

[1106] The emotion engine analyzes user emotions and uses that data to identify factors that affect the business process flow model. For example, it extracts emotional data from user emails and feedback and incorporates it into the business process model.

[1107] 5. Identifying waste and areas for improvement

[1108] Subject: AI

[1109] AI analyzes the generated business process flow model and sentiment data to detect wasteful steps and process gaps, thereby clearly indicating the identified wasteful and inefficient steps.

[1110] 6. Proposal for improvement

[1111] Subject: AI

[1112] The AI ​​generates specific improvement proposals based on the identified waste and areas for improvement, taking into account feedback based on emotional data to present optimal improvement proposals.

[1113] 7. Report Generation

[1114] Subject: Server

[1115] The server generates a detailed report based on the AI-generated improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The report is output in PDF or HTML format and provided to the user via their device.

[1116] Specific examples

[1117] Example: A new product development project

[1118] Data collection

[1119] The sales department sends an email requesting new product development.

[1120] The IT department submits the required database change request.

[1121] The marketing department sends out the survey data via email.

[1122] Data analysis

[1123] The server uses a natural language processing engine to extract information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the email.

[1124] Flow Modeling

[1125] The server generates and visualizes a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department.

[1126] Emotion analysis

[1127] The emotion engine analyzes emails and feedback from users (project managers) to detect pressure and stress levels.

[1128] Identifying waste and areas for improvement

[1129] The AI ​​pointed out that the same data was being entered multiple times across multiple departments and that there were multiple approval steps.

[1130] Proposal of improvement proposals

[1131] AI takes emotional data into account and suggests centralizing data entry and automating approval steps. For highly stressed employees, it also suggests allocating some of the tasks to other members.

[1132] Report Generation

[1133] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[1134] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[1135] The processing flow will be explained below.

[1136] Step 1:

[1137] Subject: Server

[1138] Specific operation: The server periodically accesses the mail server to retrieve new request emails and database application emails. The retrieved emails are saved in temporary storage. It also retrieves related documents such as database application forms from the file server or a specified folder. This is done using the file access API.

[1139] Step 2:

[1140] Subject: Server

[1141] Specific operation: The server sends the stored emails and documents to a natural language processing (NLP) engine, which analyzes the text data. The NLP engine tokenizes the text and extracts key information such as "delivery date," "person in charge," and "content." The extracted key information is saved in JSON format.

[1142] Step 3:

[1143] Subject: Server

[1144] Specific operation: The server generates a business process flow model based on the extracted key information. This model is a visual representation of a series of business procedures and processes, and is displayed in a business process design tool or dashboard. The model is then compared with an existing business process database to optimize the flow.

[1145] Step 4:

[1146] Subject: Emotion Engine

[1147] Specific operation: The emotion engine analyzes emails and feedback from users and extracts emotional data. For example, it uses text analysis to identify emotions such as "dissatisfaction," "stress," and "satisfaction" contained in user text. The extracted emotional data is incorporated into the business process flow model.

[1148] Step 5:

[1149] Subject: Server

[1150] Specific operation: The server uses AI to perform analysis based on a business process flow model that includes emotional data. The AI ​​identifies unnecessary steps and process gaps. This analysis also references past business data and statistical information.

[1151] Step 6:

[1152] Subject: AI

[1153] Specific operation: The AI ​​generates improvement proposals based on the business process flow model and emotion data. For example, it suggests distributing tasks to high-stress departments, centralizing data entry, automating procedures, etc. The improvement proposals are sent to the server in text and visual formats.

[1154] Step 7:

[1155] Subject: Server

[1156] Specific operation: The server integrates the AI-generated improvement proposals into the business process flow model and generates a detailed report. The report includes identified waste areas, improvement points, analysis results of emotion data, and proposed improvement proposals. The final report is output in PDF or HTML format and provided to the user.

[1157] Examples:

[1158] For new product development projects

[1159] Step 1:

[1160] The sales department sends an email requesting new product development.

[1161] The IT department stores the necessary database change request forms on a file server.

[1162] Step 2:

[1163] The server uses an NLP engine to extract keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the request email and application form.

[1164] Step 3:

[1165] The server generates a flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it on a dashboard.

[1166] Step 4:

[1167] The emotion engine analyzes feedback emails from users (staff) and extracts emotional data such as "high stress" and "dissatisfaction."

[1168] Step 5:

[1169] The server analyzes the flow model, which includes emotional data, and the AI ​​identifies unnecessary steps and inefficient processes.

[1170] Step 6:

[1171] The AI ​​takes emotional data into account and makes suggestions for distributing tasks, centralizing data entry, and automating tasks.

[1172] Step 7:

[1173] The server generates a report and provides it to the user in PDF format, which includes specific improvement suggestions, identified waste areas, and the results of the analysis of sentiment data.

[1174] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[1175] Example 2

[1176] 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."

[1177] In modern business processes, traditional workflow management systems have improved efficiency in some respects, but they do not take into account the emotional burden and stress placed on users. Therefore, while improving the overall efficiency and quality of work, there is a need for systems that take into account the emotional state of users and appropriately allocate the workload. Furthermore, there is a need for systems that can automatically identify wasteful and inefficient steps and propose specific improvement proposals.

[1178] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1179] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on the analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for analyzing user emotions, and means for integrating emotion analysis data into the business process flow model. This improves the efficiency and quality of business processes and enables appropriate workload allocation taking into account the emotional state of users.

[1180] "Request data" refers to necessary information and requirements related to business operations, and includes document data such as emails and application forms.

[1181] A "natural language processing engine" refers to a group of algorithms and programs that allow a computer to understand and analyze human language.

[1182] "Key information" refers to important data items in a business process, and includes, for example, "delivery date" and "person in charge."

[1183] A "business process flow model" is a model that visually represents a business process, and includes a diagrammatic representation of business procedures and process flows.

[1184] "Emotion analysis" refers to the process of analyzing a user's emotional state from text data and feedback, and assessing their psychological state, such as stress and satisfaction.

[1185] "Improvement proposals" refer to specific proposals and measures aimed at streamlining business processes and improving quality.

[1186] A "machine learning model" refers to a group of algorithms or programs that learn from large amounts of data and automatically analyze patterns and trends.

[1187] A "report" is a document that summarizes analysis results and improvement proposals, and is provided in PDF or HTML format.

[1188] "Emotion analysis data" refers to data relating to the user's emotional state obtained as a result of emotion analysis.

[1189] This invention is a system for streamlining business processes and improving business processes by taking into account the emotional state of users. This system combines multiple hardware and software components to collect and analyze request data, generate a business process flow model, identify waste and areas for improvement, and present improvement proposals that integrate user emotional data.

[1190] Hardware and Software Configuration

[1191] Hardware:

[1192] Server: Responsible for main processes such as data collection, analysis, flow modeling, and report generation.

[1193] Terminal: Serves as an interface for users to access and view the generated reports.

[1194] software:

[1195] Natural language processing engine: Analyzes requested data and extracts key information using Google Cloud Natural Language API, etc.

[1196] Emotion analysis engine: Using IBM Watson Tone Analyzer and other tools, analyzes the user's emotional state and generates numerical data.

[1197] Machine learning models: Used to analyze business process flow models and sentiment data to identify waste and areas for improvement.

[1198] Dashboard tools: Visualize business process flow models using tools such as Microsoft Power BI.

[1199] Program Processing Overview

[1200] The program of this system implements the following main functions:

[1201] 1. Data Collection:

[1202] The server periodically retrieves new emails from the mail server and stores them in storage. It also collects related documents such as database application forms from the file server and stores them in storage.

[1203] 2. Data Analysis:

[1204] The server sends the emails and documents stored in the storage to a natural language processing engine, which analyzes the text data. Important key information (e.g., "delivery date," "person in charge," and "content") is extracted and stored in a database.

[1205] 3. Flow Modeling:

[1206] The server generates a business process flow model based on the key information stored in the database. The generated model is visualized using a dashboard tool.

[1207] 4. Emotion analysis:

[1208] The emotion engine analyzes emails and feedback forms sent by users and generates numerical data representing the user's emotional state. This emotional data is sent to the server and integrated into the business process flow model.

[1209] 5. Identify waste and areas for improvement:

[1210] AI analyzes business process flow models and sentiment analysis data to identify unnecessary steps and inefficiencies.

[1211] 6. Proposal for improvement:

[1212] Based on the identified waste and areas for improvement, the AI ​​generates specific improvement proposals, taking into account emotional data and proposing things like workload and task reallocation.

[1213] 7. Report Generation:

[1214] The server creates a detailed report based on the generated improvement proposals and business process flow model. The report is output in PDF or HTML format and provided to the user via their terminal.

[1215] Specific examples

[1216] For new product development projects

[1217] Data collection: The server collects emails requesting new product development sent by the sales department and database change request forms sent by the IT department, and stores them in storage.

[1218] Data analysis: The server analyzes the request email, extracts key information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka", and stores it in a database.

[1219] Flow modeling: Based on the extracted key information, the server generates a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it using a dashboard tool.

[1220] Sentiment analysis: The emotion engine analyzes emails and feedback sent by project managers and generates emotional data such as "high stress level."

[1221] Identifying waste and areas for improvement: AI analyzes workflow models and sentiment data to identify duplicate data entries across multiple departments and multiple approval steps.

[1222] Suggested improvements: AI can suggest improvements such as centralizing data entry, automating approval steps, or delegating specific tasks to other members.

[1223] Report generation: The server generates a detailed report based on the improvement proposal and provides it to the person in charge (Tanaka) via the terminal.

[1224] Example prompt sentence:

[1225] Please extract key information about the business flow from the following email. Email content: 'The sales department requests the start of the next new product development project as follows. The deadline is 2023-12-31, and the person in charge is Tanaka.'

[1226] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1227] Step 1:

[1228] The server periodically retrieves new emails from the mail server. The mail server connection information and a query to retrieve new emails are used as input. The server temporarily stores the retrieved emails in storage. It also collects database application forms and related documents from the file server and stores them in storage. This completes the collection of request data.

[1229] Step 2:

[1230] The server sends the emails and documents stored in storage to a natural language processing engine (e.g., Google Cloud Natural Language API). The stored emails and documents are used as input. The natural language processing engine analyzes the text data and extracts key information such as delivery date, person in charge, and content. The server stores the extracted key information in a database and records the analysis results in a log. This extracts the key information.

[1231] Step 3:

[1232] The server generates a business process flow model based on key information stored in the database. The key information is used as input. The server uses this key information to visualize the business flow step by step, creating a series of business procedures and processes. The generated business process flow model is visualized using a dashboard tool. This generates a business process flow model.

[1233] Step 4:

[1234] The emotion engine (e.g. IBM Watson Tone Analyzer) analyzes emails and feedback forms sent by users. The emails and feedback sent by users are used as input. The emotion engine analyzes the user's emotional state (e.g. stress, satisfaction, etc.) from this text data and generates numerical data. The emotion analysis data is sent to the server, which then analyzes the user's emotional state.

[1235] Step 5:

[1236] The AI ​​uses the business process flow model and sentiment analysis data provided by the server to identify wasteful steps and inefficient areas. The business process flow model and sentiment analysis data are used as input. The AI ​​performs analysis using a machine learning model, generates a report detailing the identified problems, and sends it to the server. This identifies waste and areas for improvement.

[1237] Step 6:

[1238] The AI ​​creates specific improvement proposals based on the identified waste and improvement points. The waste and improvement points are used as input. The AI ​​generates improvement proposals that include suggestions for centralizing data entry, automating approval steps, and reassigning tasks. Sentiment analysis data is also taken into account, and measures to reduce user stress are included. The improvement proposals are sent to the server. This generates specific improvement proposals.

[1239] Step 7:

[1240] The server creates a detailed report based on the improvement proposals provided by the AI. The improvement proposals and the business process flow model are used as input. The server generates a report that includes a visual representation of the business process flow model, detected problems, and specific improvement suggestions. The generated report is output in PDF or HTML format and provided to the user via their terminal. This completes the report generation process.

[1241] (Application example 2)

[1242] 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."

[1243] Conventional business process management systems have the problem that they are unable to take into account the emotions and stress levels of users when identifying wasteful work flows and areas for improvement, making it difficult to improve work efficiently. This problem is particularly important in brick-and-mortar stores, where the emotions and motivation of staff members directly affect work efficiency.

[1244] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for incorporating user emotion data into the generated business process flow model and performing emotion analysis, means for identifying waste and improvement points based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and improvement points, and means for generating and outputting a report based on the improvement proposals and the business process flow model. This enables precise business improvement that takes user emotions into consideration.

[1245] "Request data" refers to data that includes information and requirements related to business processes.

[1246] A "natural language processing engine" is a software function that analyzes text data and extracts meaning and key information.

[1247] "Key information" is information that extracts important parameters and topics from the collected data.

[1248] A "business process flow model" is a model that visually and structurally represents business procedures and processes.

[1249] "Emotion analysis" is a method of converting user emotions into data and using the results to identify factors that affect business processes.

[1250] "Waste" refers to inefficient steps or unnecessary work in a business process.

[1251] "Improvement points" refer to areas that can be improved to make business processes more efficient.

[1252] "Improvement proposals" refer to specific proposals for eliminating waste and inefficiencies in business processes.

[1253] The "means for generating and outputting reports" is a function that creates a detailed report based on the generated business process flow model and improvement proposals, and provides it to the user.

[1254] "Emotion data" is data obtained by analyzing and quantifying the user's emotional state.

[1255] "Structured data" is data in which key information is organized and arranged according to a certain format.

[1256] A "machine learning model" is an algorithm that recognizes patterns based on data and automatically performs analysis and predictions.

[1257] System Overview

[1258] The present invention is a new system that combines the efficiency of business processes in brick-and-mortar stores with user emotion analysis. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. Then, it analyzes user emotions using an emotion engine and incorporates them into the business process flow model to generate precise improvement proposals and output them as a report. Specific embodiments are described below.

[1259] Hardware and software used

[1260] Smartphones: Used as individual staff devices.

[1261] Emotion engine: Powered by Microsoft Azure Cognitive Services.

[1262] Natural language processing engine: Uses Google Cloud Natural Language API.

[1263] Database: Uses Firebase Realtime Database.

[1264] Flow Design Tool: A flow design dashboard powered by React.js.

[1265] Program processing

[1266] The server includes the following means:

[1267] 1. Data Collection Methods

[1268] The server collects business data from each device in the store. For example, it aggregates business data entered by staff on their smartphones and event data from sensors. This data is temporarily stored in a database.

[1269] 2. Natural Language Processing Methods

[1270] The collected data is sent to the server's natural language processing engine, where key information is extracted, such as "break time," "number of customer interactions," and "product replenishment work."

[1271] 3. Method for generating business process flow models

[1272] Based on the extracted key information, a business process flow model is generated on the server. This model visually represents business procedures and processes and can be viewed on a dashboard.

[1273] 4. Emotion analysis means

[1274] The server uses an emotion engine to analyze the emotional data of the staff, which is expressed as, for example, the staff's "stress level" or "motivation index."

[1275] 5. Identifying waste and areas for improvement

[1276] Based on the generated business process flow model and emotional data, AI identifies unnecessary steps and areas for improvement, focusing on analyzing business flows where the emotional data indicates high stress.

[1277] 6. Means for presenting improvement proposals

[1278] The server generates specific improvement proposals based on the identified waste and improvement points, such as centralizing data entry, automating approval steps, and redistributing tasks.

[1279] 7. Report Generation Methods

[1280] The server generates a detailed report based on the business process flow model and improvement proposals, and outputs it in PDF or HTML format. The report can be viewed on a smartphone or PC.

[1281] Specific examples

[1282] Example: Improving business processes in physical stores

[1283] In physical stores, staff record their daily work on their smartphones. For example, data such as "product inventory" and "customer service details" is entered. The data is stored in a Firebase database, and the server periodically retrieves it. A natural language processing engine extracts key information and generates a business process flow model. An emotion engine analyzes staff daily reports and feedback emails to detect stress levels. AI identifies unnecessary steps and areas for improvement, and proposes specific improvement proposals, including automating data entry and dividing up tasks. Finally, a detailed report is generated and provided to managers.

[1284] Prompt Sentence Examples

[1285] "We are developing a new operational improvement tool for our brick-and-mortar stores. This tool analyzes staff work processes and emotions and generates specific improvement proposals. Please explain the steps to perform the following operations.

[1286] 1. Collecting data from Firebase Realtime Database

[1287] 2. Obtaining sentiment scores using a sentiment analysis engine

[1288] 3. Creation and visualization of business flow models

[1289] 4. Preparation of a detailed report with improvement suggestions

[1290] The present invention enables precise business improvement that takes into account the user's emotions.

[1291] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1292] Step 1:

[1293] The server collects business data from each device in the physical store. Specifically, it aggregates business data entered by staff on their smartphones and event data from sensors in the store. The entered data is collected in file format or via API, and temporarily stored in the Firebase Realtime Database. This data becomes the input data for the next processing step.

[1294] Step 2:

[1295] The server retrieves the collected data from Firebase and sends it to a natural language processing engine (Google Cloud Natural Language API). At this time, business data in text format becomes the input data. The natural language processing engine analyzes this data and extracts key information important to the business process (for example, "break time," "number of customer interactions," "product replenishment work," etc.). The extracted key information is sent to the next step as output data.

[1296] Step 3:

[1297] The server generates a business process flow model based on the extracted key information. The input data is the key information extracted in the previous step, and the generated business process flow model is expressed in XML or JSON format. This model visually represents business procedures and processes, and is displayed on a flow design dashboard using React.js. The generated business process flow model becomes the output data.

[1298] Step 4:

[1299] The server uses an emotion engine (Microsoft Azure Cognitive Services) to analyze staff emotional data. The input data is staff daily reports and feedback emails. The emotion engine analyzes this text data and generates emotional scores such as "stress level" and "motivation index" as output data.

[1300] Step 5:

[1301] The server reanalyzes the business process model based on the generated business process flow model and emotion score. The input data are the business process flow model and emotion score, and the AI ​​(machine learning model) identifies wasteful steps and areas for improvement. For example, if a high stress level is detected in a specific business process, it suggests that the business steps are inefficient. A business process flow model with wasteful steps and areas for improvement marked is generated as output data.

[1302] Step 6:

[1303] The server generates specific improvement proposals based on the identified waste and improvement points. The input data is a business process flow model that includes wasteful steps and improvement points. The AI ​​generates specific improvement proposals, such as centralizing data entry, automating approval steps, and redistributing tasks. The generated improvement proposals are sent to the next step as output data.

[1304] Step 7:

[1305] The server generates a detailed report based on the business process flow model and improvement proposals. The input data are the improvement proposals and the business process flow model. The server formats this data into a document and creates a report in PDF or HTML format. The generated report is sent to the user's device as output data. The user can view the report on their smartphone or computer and use it as a guideline for specific business improvements.

[1306] Through the above steps, precise business improvement that takes into account the user's emotions is realized.

[1307] 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.

[1308] 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.

[1309] 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.

[1310] [Fourth embodiment]

[1311] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1312] 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.

[1313] 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).

[1314] 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.

[1315] 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.

[1316] 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).

[1317] 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.

[1318] 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.

[1319] 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.

[1320] 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.

[1321] 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.

[1322] 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.

[1323] 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."

[1324] System Overview

[1325] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[1326] Program processing description

[1327] 1. Data Collection

[1328] Subject: Server

[1329] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or designated folders. This makes it possible to comprehensively collect request data related to all business processes.

[1330] 2. Data Analysis

[1331] Subject: Server

[1332] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations, allowing it to be used efficiently.

[1333] 3. Flow Modeling

[1334] Subject: Server

[1335] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. This model is displayed graphically using a flow design tool.

[1336] 4. Identifying waste and areas for improvement

[1337] Subject: AI

[1338] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps, explicitly identifying factors that hinder business efficiency, such as multiple data entry or multiple approval steps that delay procedures.

[1339] 5. Proposal for improvement

[1340] Subject: AI

[1341] The AI ​​generates specific improvement proposals for the identified waste and improvement points. The proposals are simulated to predict their effects and then present the optimal solution. The proposals are organized in text and visual formats and sent to the server.

[1342] 6. Report Generation

[1343] Subject: Server

[1344] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user.

[1345] Specific examples

[1346] Example: A new product development project

[1347] Data collection

[1348] The server collects emails such as new product development requests from the sales department and database change requests from the IT department.

[1349] Data analysis

[1350] The natural language processing engine extracts keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka."

[1351] Flow Modeling

[1352] The server generates a business processing flow from the sales department to the IT department to the quality control department to the marketing department, and displays it graphically.

[1353] Identifying waste and areas for improvement

[1354] AI points out that the same data is being entered multiple times across multiple departments, and that multiple approval steps are causing delays in work.

[1355] Proposal of improvement proposals

[1356] AI suggests centralizing data entry and automating approval steps.

[1357] Report Generation

[1358] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[1359] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[1360] The processing flow will be explained below.

[1361] Step 1:

[1362] Subject: Server

[1363] Specific operation: The server connects to the mail server at regular intervals to retrieve new emails. This is done using the POP3 or IMAP protocol. The retrieved emails are saved in temporary storage. It also scans database application forms and related documents from the file server or a specified folder and saves them in temporary storage as well.

[1364] Step 2:

[1365] Subject: Server

[1366] Specific operation: The server analyzes the stored emails and documents and sends them to a natural language processing engine. The natural language processing engine tokenizes the email body and documents and extracts key information (delivery date, person in charge, content, etc.). The extracted key information is saved as structured data in JSON format or similar.

[1367] Step 3:

[1368] Subject: Server

[1369] Specific operation: The server generates a business process flow model based on the extracted structured data. In this process, it compares it with an existing business process database and determines the sequence of business steps. The generated business process flow model is saved in BPMN (Business Process Model and Notation) format and displayed in a flow design tool or dashboard.

[1370] Step 4:

[1371] Subject: AI

[1372] How it works: The AI ​​analyzes the generated business process flow model and identifies wasteful or inefficient steps within the process. For example, it detects cases where the same data is being entered multiple times by multiple departments or where there are unnecessary approval steps. This is done using past statistical data and a rule base.

[1373] Step 5:

[1374] Subject: AI

[1375] Specific Actions: Based on the identified waste and improvement points, the AI ​​generates specific improvement suggestions, such as centralizing data entry and automating approval processes. The improvement suggestions are organized in text and visual formats and used to generate subsequent reports.

[1376] Step 6:

[1377] Subject: Server

[1378] Specific operation: The server generates a report based on the improvement proposals generated by the AI ​​and the business process flow model. This report includes a visualization of the business process flow in graphs and charts, details of waste and improvement points, and the proposed improvement proposals. The generated report is output in PDF or HTML format and provided to the user.

[1379] Example 1

[1380] 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."

[1381] Today's increasingly complex business processes require efficient management and analysis, but manual data collection and analysis is time-consuming and prone to errors. It's also difficult to identify wasteful or inefficient parts of business processes, and finding solutions requires a great deal of time and effort. This creates challenges, reducing the efficiency of the entire company and hindering smooth business operations.

[1382] 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.

[1383] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for visually displaying the business process flow model, means for polling new data from a mail server and a file server at a specific interval, and means for using an external API as the natural language processing engine. This makes it possible to rapidly and accurately identify waste in business processes and present specific improvement proposals, thereby significantly improving the efficiency of the entire business.

[1384] "Request data" refers to data that includes information about requests and applications related to business processes.

[1385] A "natural language processing engine" is software or an API for analyzing text data and extracting key information.

[1386] "Key information" is specific information that is considered important in a business process, such as deadlines, people in charge, and content.

[1387] A "business process flow model" is a model that visually represents the flow of a series of business procedures and processes.

[1388] "Waste" refers to unnecessary steps and inefficient operations in a business process.

[1389] "Improvement points" are points that need to be improved to improve the efficiency of a business process.

[1390] An "improvement proposal" is a proposal that presents specific solutions to waste or areas for improvement.

[1391] A "report" is a document that includes details of improvement proposals and business process flow models.

[1392] "Visually displaying" means expressing a business process flow model graphically and providing it to the user in a format that is easy to understand.

[1393] "Polling" is the process of periodically checking and collecting new data from a server.

[1394] An "external API" is an interface for accessing functions provided by other software or services.

[1395] MODE FOR CARRYING OUT THE INVENTION

[1396] This invention is a system for efficiently managing and analyzing complex business processes. This system collects request data, analyzes the data using a natural language processing engine, and extracts key information. It generates a business process flow model based on the extracted key information, and identifies waste and areas for improvement based on an analysis of the model. It then presents specific improvement proposals for the identified waste and areas for improvement, and finally generates and outputs a report.

[1397] Data collection

[1398] The server periodically polls for new emails from the mail server and retrieves new request emails and database application emails. It also retrieves documents such as database application forms from the file server or specified folders. This makes it possible to comprehensively collect request data related to all business processes. Specifically, the server accesses the mail server at a specific interval, every five minutes, to check whether new emails exist. This process uses standard mail server protocols (e.g., IMAP or POP3).

[1399] Data analysis

[1400] The server sends the retrieved emails and documents to a natural language processing engine (e.g., Google NLP API), which analyzes the text data. The natural language processing engine extracts important key information for business processing, such as "delivery date," "person in charge," and "content." This analysis organizes the information necessary for business operations and enables it to be used efficiently. The key information is stored as structured data in a database on the server side and is used for subsequent processing.

[1401] Flow Modeling

[1402] The server generates a business process flow model based on the extracted key information. This business process flow model visually represents a series of business procedures and processes, and can clearly show the relationships between employees and departments. The model is displayed graphically using a flow design tool such as Microsoft Visio. This makes it easier for employees to understand the overall picture of the business process and make decisions regarding the flow of work.

[1403] Identifying waste and areas for improvement

[1404] AI analyzes the generated business process flow model to detect unnecessary steps and process gaps. This explicitly identifies factors that hinder business efficiency. For example, it identifies cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. Using a machine learning model enables highly accurate analysis based on past data.

[1405] Proposal of improvement proposals

[1406] AI generates specific improvement proposals for identified waste and improvement points. The proposals are simulated to predict their effects and then present optimal solutions. For example, it suggests centralizing data entry and automating approval processes. The proposals are organized in text and visual formats and sent to a server, allowing for the rapid provision of specific, actionable improvement measures.

[1407] Report Generation

[1408] The server generates a detailed report based on the improvement proposals proposed by the AI ​​and the business process flow model. This report includes specific improvement proposals for reducing waste in business and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then use this report to implement improvements to their business processes.

[1409] Specific examples

[1410] Example: A new product development project

[1411] Data collection

[1412] The server collects emails from the sales department requesting new product development, emails from the IT department requesting database changes, etc. It also retrieves newly added document files from designated folders on the file server.

[1413] Data analysis

[1414] A natural language processing engine (e.g., Google NLP API) extracts key information such as "Delivery date: 2023-12-31," "Person in charge: Tanaka," and "New product specifications," and the server stores this in a database.

[1415] Flow Modeling

[1416] The server generates a business flow model of "Sales Department → IT Department → Quality Control Department → Marketing Department" and displays it visually using Microsoft Visio.

[1417] Identifying waste and areas for improvement

[1418] AI detects duplicate data entry across departments and multiple approval steps that delay work.

[1419] Proposal of improvement proposals

[1420] AI will propose centralizing data entry and automating approval processes, and will also perform simulations to predict the effects.

[1421] Report Generation

[1422] The server generates a report containing specific improvement proposals and submits it to the user in PDF format, allowing the user to implement improvements to their business processes based on this report.

[1423] Prompt Sentence Examples

[1424] "Please tell us some specific improvement ideas for streamlining the business processes in new product development projects."

[1425] "Please identify waste in the database change application process and suggest improvements."

[1426] The above is a specific embodiment for carrying out the present invention. By showing the detailed implementation method of the invention, it is possible to improve the efficiency and quality of business processing.

[1427] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1428] Step 1:

[1429] The server collects request data from the mail server and file server. The server accesses the mail server every five minutes to check for new emails. If new emails exist, it reads their contents and searches the subject and body of the email for keywords related to "request" or "application." At the same time, the server accesses the specified folder on the file server to retrieve newly added document files. This process obtains the request data as input, which is used in the next step.

[1430] Step 2:

[1431] The server sends the collected emails and documents to a natural language processing engine. Specifically, it uses the Google NLP API to analyze the text data. This engine extracts important key information for business processing. For example, information such as "delivery date," "person in charge," and "content" is obtained as analysis results. The server then stores this extracted key information in a database as structured data. Through this process, emails and documents become input data, and the key information becomes output data.

[1432] Step 3:

[1433] The server generates a business process flow model based on the key information stored in the database. From the extracted key information, a series of business procedures and processes are visually represented in the form of a flowchart. Using a flow design tool such as Microsoft Visio, the flow of the business process is displayed graphically. For example, a business process flow of "Sales Department → IT Department → Quality Control Department → Marketing Department" is generated. In this process, the key information is used as input data, and a business process flow model is generated as output data.

[1434] Step 4:

[1435] The AI ​​analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. It uses a machine learning model to identify wasteful procedures and inefficient work. For example, it detects cases where the same data is entered multiple times or where there are multiple approval steps that delay procedures. The AI ​​sends these analysis results to a server. In this step, the business process flow model is the input data, and a list of waste and areas for improvement is the output data.

[1436] Step 5:

[1437] The AI ​​generates specific improvement proposals based on the identified waste and improvement points. These proposals may include centralizing data entry and automating the approval process. These proposals are presented after simulations are run to predict their effectiveness. The proposals are organized in text and visual formats and sent to a server. In this process, the list of waste and improvement points is the input data, and the improvement proposals are the output data.

[1438] Step 6:

[1439] The server generates a detailed report based on the improvement proposals and business process flow model presented by the AI. The report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the user. The user can then implement business process improvements based on this report. In this step, the improvement proposals and business process flow model are the input data, and the report is the output data.

[1440] (Application example 1)

[1441] 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."

[1442] Efficiently managing and analyzing complex business processes in today's corporate environment is challenging. Existing systems are particularly inadequate when it comes to real-time data collection and analysis, as well as immediate feedback. There is also a need to identify redundant steps and wasteful processes and quickly propose improvements, but there is a lack of comprehensive solutions that can achieve this. While real-time process optimization using autonomous machines is particularly important in factories and manufacturing lines, current technology does not adequately meet this need.

[1443] 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.

[1444] In this invention, the server includes: means for collecting request data; means for analyzing the collected data using a natural language processing engine and extracting key information; means for generating a business process flow model based on the extracted key information; means for identifying waste and areas for improvement based on an analysis of the generated business process flow model; means for presenting improvement proposals for the identified waste and areas for improvement; means for generating and outputting a report based on the improvement proposals and the business process flow model; means for being installed in an autonomous machine operating within a work area and for collecting and analyzing data in real time; and means for visually displaying the collected data and providing immediate feedback. This enables efficient data collection and analysis in real time even in factories and production lines, enabling immediate identification of waste and the presentation of effective improvement proposals.

[1445] "Request data" refers to data that includes advance information about a business process.

[1446] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning and information.

[1447] "Key information" refers to important attributes and elements in a business process, and includes information such as "delivery date" and "person in charge."

[1448] A "business process flow model" is a model that visually and systematically represents each step of a business process and the relationships between them.

[1449] "Waste" refers to unnecessary steps or duplication in business processes that hinder efficiency.

[1450] "Improvement points" are areas in a business process that require improvement in order to improve efficiency and quality.

[1451] An "improvement plan" is a specific proposal or method aimed at improving efficiency and quality in response to identified waste or areas for improvement.

[1452] A "report" is a document that includes information such as analysis results and improvement proposals, and is compiled in the form of text and charts.

[1453] An "autonomous machine" is a mechanical device that is designed to operate autonomously and perform a specific task or operation.

[1454] "Real-time" is a time concept that means data processing and analysis are carried out almost immediately.

[1455] "Visual display" means presenting analysis results and business models in a graphical format that is easy for people to understand.

[1456] "Immediate feedback" means immediately reflecting the results of data collection and analysis, and providing prompt notifications and suggestions for improvement to workers.

[1457] This invention is a system for efficiently managing and analyzing business processes within a factory. This system has the following main components and functions:

[1458] 1. System Configuration

[1459] Hardware:

[1460] Autonomous machines: Robots that move around the factory and collect the necessary data.

[1461] Server: A central processing unit that collects and analyzes data and generates reports.

[1462] Sensors: Various sensor devices mounted on autonomous machines to measure data.

[1463] software:

[1464] Natural language processing engine (spaCy): Analyzes collected text data and extracts key information.

[1465] Data analysis tools (PyPDF2, watchdog): Tools for analyzing PDF documents and monitoring the file system.

[1466] Graphical display tool (graphviz): A tool for visually displaying business process flow models.

[1467] 2. Data Collection

[1468] The server periodically retrieves new request data from the mail server, and autonomous machines in the factory use sensors to collect data in real time and send it to the server, ensuring that the latest information about business processes is always available.

[1469] 3. Data Analysis

[1470] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data. Through the analysis, key information such as "delivery date" and "person in charge" is extracted. This information forms the basis for the next step, business process flow modeling.

[1471] 4. Flow Modeling

[1472] The server generates a business process flow model based on the extracted key information. This flow model visually represents the business procedures and the relationships between each step, and clearly shows the data flow. A graphical display tool (e.g., graphviz) is used for display.

[1473] 5. Identifying waste and areas for improvement

[1474] AI analyzes the generated business process flow model and identifies unnecessary steps and gaps in the process. For example, it can identify cases where the same data is being entered multiple times across multiple departments, or where there are multiple approval steps that are delaying work. Waste and areas for improvement are analyzed with high precision using machine learning models.

[1475] 6. Proposal for improvement

[1476] AI proposes specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness. The proposals are organized in text and visual formats for easy understanding.

[1477] 7. Report Generation

[1478] The server generates a detailed report based on the improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The generated report is output in PDF or HTML format and submitted to the factory manager.

[1479] Specific examples

[1480] A concrete example is process improvement in a manufacturing plant. Autonomous machines collect data from the product line and send it to a server. Natural language processing reveals that there is a lot of overlapping data between "Production Line 1" and the "Quality Control Department." AI analyzes this and suggests an automated data entry system. The server compiles these suggestions into a report and presents it to the plant manager.

[1481] Example prompt sentence:

[1482] Input: Data from production line 1 to the quality control department. PDF data collected by robot scanning.

[1483] Output: A report containing a business process flow model, wasteful steps, and improvement suggestions.

[1484] The above are the main components and procedures for implementing the present invention, which can improve the efficiency and quality of work processes within a factory.

[1485] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1486] Step 1: Data collection

[1487] The server periodically polls the mail server to retrieve new request emails and database application emails. At the same time, autonomous machines move around the factory and use sensors to collect data in real time, which is then sent to the server.

[1488] Input: Request emails and data sent from each department within the factory, and real-time data from sensors.

[1489] Output: Request data and real-time data collected on the server.

[1490] Specific operation: The server obtains the latest data from the mail server and sensors and stores it in a database.

[1491] Step 2: Data analysis

[1492] The server sends the collected data to a natural language processing engine (e.g., spaCy), which analyzes the text data and extracts key information such as "delivery date" and "person in charge."

[1493] Input: Requested data and real-time data collected in step 1.

[1494] Output: Extracted key information (e.g., "Delivery Date", "Contact Person", etc.).

[1495] Specific operation: The server sends text data to the natural language processing engine, obtains the analysis results, and stores the key information in a database.

[1496] Step 3: Flow Modeling

[1497] The server generates a business process flow model based on the extracted key information, which visually represents the business procedures and the relationships between each step.

[1498] Input: The key information extracted in step 2.

[1499] Output: Business process flow model.

[1500] Specific operation: The server analyzes the key information and generates a flow model using a graphical display tool (e.g., graphviz).

[1501] Step 4: Identify waste and areas for improvement

[1502] The AI ​​on the server analyzes the generated business process flow model and identifies unnecessary steps and process gaps, such as when the same data is being entered multiple times across multiple departments.

[1503] Input: The business process flow model generated in step 3.

[1504] Output: Results identifying wasteful steps and gaps in the process.

[1505] How it works: The AI ​​on the server uses machine learning models to analyze the flow model and identify waste and areas for improvement.

[1506] Step 5: Propose improvements

[1507] AI generates specific improvement proposals for identified waste and improvement points. The proposals are presented as optimal solutions after conducting simulations to predict their effectiveness.

[1508] Input: Wasteful steps or process gaps identified in Step 4.

[1509] Output: Improvement suggestions (text and visual formats).

[1510] Specific operation: The AI ​​runs a simulation, generates improvement proposals, and sends them to the server.

[1511] Step 6: Generate reports

[1512] The server generates a detailed report based on the improvement proposals and business process flow model proposed by the AI, and the report is output in PDF or HTML format and submitted to the user.

[1513] Input: Improvement proposals and business process flow models generated in Step 5.

[1514] Output: Detailed report in PDF or HTML format.

[1515] Specific operation: The server integrates the improvement proposal and the flow model, generates a report using a report creation tool, and saves it in the specified format.

[1516] Step 7: Real-time feedback

[1517] The autonomous machines visually display the data they collect and provide immediate feedback to factory workers, allowing them to review and take action on suggested improvements in real time.

[1518] Input: Real-time data continuously obtained from step 1.

[1519] Output: Visual feedback and improvement suggestions for the worker.

[1520] Specific operation: The autonomous machine notifies the worker of the results of data analysis via a display and audio alert, prompting immediate action.

[1521] 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.

[1522] System Overview

[1523] This invention is a new system for streamlining business processes. It combines conventional business flow management with an emotion engine that analyzes user emotions to achieve more precise and effective business improvements. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. The system then analyzes the generated business process flow model to identify waste and areas for improvement. The emotion engine then recognizes user emotions and incorporates them into the business process flow model to generate more precise improvement proposals and output them as a report.

[1524] Program processing description

[1525] 1. Data Collection

[1526] Subject: Server

[1527] The server periodically retrieves new emails from the mail server, and database application forms and related documents from the file server. These data are temporarily stored in storage.

[1528] 2. Data Analysis

[1529] Subject: Server

[1530] The server sends the retrieved emails and documents to a natural language processing engine, which analyzes the text data. As a result of the analysis, key information important for business processing (e.g., "delivery date," "person in charge," and "content") is extracted.

[1531] 3. Flow Modeling

[1532] Subject: Server

[1533] The server generates a business process flow model based on the extracted key information. The generated model visually represents a series of business procedures and processes and is displayed in a flow design tool or dashboard.

[1534] 4. Emotion analysis

[1535] Subject: Emotion Engine

[1536] The emotion engine analyzes user emotions and uses that data to identify factors that affect the business process flow model. For example, it extracts emotional data from user emails and feedback and incorporates it into the business process model.

[1537] 5. Identifying waste and areas for improvement

[1538] Subject: AI

[1539] AI analyzes the generated business process flow model and sentiment data to detect wasteful steps and process gaps, thereby clearly indicating the identified wasteful and inefficient steps.

[1540] 6. Proposal for improvement

[1541] Subject: AI

[1542] The AI ​​generates specific improvement proposals based on the identified waste and areas for improvement, taking into account feedback based on emotional data to present optimal improvement proposals.

[1543] 7. Report Generation

[1544] Subject: Server

[1545] The server generates a detailed report based on the AI-generated improvement proposals and the business process flow model. This report includes specific improvement proposals for reducing waste and improving quality. The report is output in PDF or HTML format and provided to the user via their device.

[1546] Specific examples

[1547] Example: A new product development project

[1548] Data collection

[1549] The sales department sends an email requesting new product development.

[1550] The IT department submits the required database change request.

[1551] The marketing department sends out the survey data via email.

[1552] Data analysis

[1553] The server uses a natural language processing engine to extract information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the email.

[1554] Flow Modeling

[1555] The server generates and visualizes a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department.

[1556] Emotion analysis

[1557] The emotion engine analyzes emails and feedback from users (project managers) to detect pressure and stress levels.

[1558] Identifying waste and areas for improvement

[1559] The AI ​​pointed out that the same data was being entered multiple times across multiple departments and that there were multiple approval steps.

[1560] Proposal of improvement proposals

[1561] AI takes emotional data into account and suggests centralizing data entry and automating approval steps. For highly stressed employees, it also suggests allocating some of the tasks to other members.

[1562] Report Generation

[1563] The server generates a report containing specific improvement suggestions and submits it to the user in PDF format.

[1564] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[1565] The processing flow will be explained below.

[1566] Step 1:

[1567] Subject: Server

[1568] Specific operation: The server periodically accesses the mail server to retrieve new request emails and database application emails. The retrieved emails are saved in temporary storage. It also retrieves related documents such as database application forms from the file server or a specified folder. This is done using the file access API.

[1569] Step 2:

[1570] Subject: Server

[1571] Specific operation: The server sends the stored emails and documents to a natural language processing (NLP) engine, which analyzes the text data. The NLP engine tokenizes the text and extracts key information such as "delivery date," "person in charge," and "content." The extracted key information is saved in JSON format.

[1572] Step 3:

[1573] Subject: Server

[1574] Specific operation: The server generates a business process flow model based on the extracted key information. This model is a visual representation of a series of business procedures and processes, and is displayed in a business process design tool or dashboard. The model is then compared with an existing business process database to optimize the flow.

[1575] Step 4:

[1576] Subject: Emotion Engine

[1577] Specific operation: The emotion engine analyzes emails and feedback from users and extracts emotional data. For example, it uses text analysis to identify emotions such as "dissatisfaction," "stress," and "satisfaction" contained in user text. The extracted emotional data is incorporated into the business process flow model.

[1578] Step 5:

[1579] Subject: Server

[1580] Specific operation: The server uses AI to perform analysis based on a business process flow model that includes emotional data. The AI ​​identifies unnecessary steps and process gaps. This analysis also references past business data and statistical information.

[1581] Step 6:

[1582] Subject: AI

[1583] Specific operation: The AI ​​generates improvement proposals based on the business process flow model and emotion data. For example, it suggests distributing tasks to high-stress departments, centralizing data entry, automating procedures, etc. The improvement proposals are sent to the server in text and visual formats.

[1584] Step 7:

[1585] Subject: Server

[1586] Specific operation: The server integrates the AI-generated improvement proposals into the business process flow model and generates a detailed report. The report includes identified waste areas, improvement points, analysis results of emotion data, and proposed improvement proposals. The final report is output in PDF or HTML format and provided to the user.

[1587] Examples:

[1588] For new product development projects

[1589] Step 1:

[1590] The sales department sends an email requesting new product development.

[1591] The IT department stores the necessary database change request forms on a file server.

[1592] Step 2:

[1593] The server uses an NLP engine to extract keywords such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka" from the request email and application form.

[1594] Step 3:

[1595] The server generates a flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it on a dashboard.

[1596] Step 4:

[1597] The emotion engine analyzes feedback emails from users (staff) and extracts emotional data such as "high stress" and "dissatisfaction."

[1598] Step 5:

[1599] The server analyzes the flow model, which includes emotional data, and the AI ​​identifies unnecessary steps and inefficient processes.

[1600] Step 6:

[1601] The AI ​​takes emotional data into account and makes suggestions for distributing tasks, centralizing data entry, and automating tasks.

[1602] Step 7:

[1603] The server generates a report and provides it to the user in PDF format, which includes specific improvement suggestions, identified waste areas, and the results of the analysis of sentiment data.

[1604] The above is a specific embodiment for carrying out the present invention. By combining analysis by an emotion engine, it is possible to further improve the efficiency and quality of business processing.

[1605] Example 2

[1606] 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."

[1607] In modern business processes, traditional workflow management systems have improved efficiency in some respects, but they do not take into account the emotional burden and stress placed on users. Therefore, while improving the overall efficiency and quality of work, there is a need for systems that take into account the emotional state of users and appropriately allocate the workload. Furthermore, there is a need for systems that can automatically identify wasteful and inefficient steps and propose specific improvement proposals.

[1608] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1609] In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for identifying waste and areas for improvement based on the analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and areas for improvement, means for generating and outputting a report based on the improvement proposals and the business process flow model, means for analyzing user emotions, and means for integrating emotion analysis data into the business process flow model. This improves the efficiency and quality of business processes and enables appropriate workload allocation taking into account the emotional state of users.

[1610] "Request data" refers to necessary information and requirements related to business operations, and includes document data such as emails and application forms.

[1611] A "natural language processing engine" refers to a group of algorithms and programs that allow a computer to understand and analyze human language.

[1612] "Key information" refers to important data items in a business process, and includes, for example, "delivery date" and "person in charge."

[1613] A "business process flow model" is a model that visually represents a business process, and includes a diagrammatic representation of business procedures and process flows.

[1614] "Emotion analysis" refers to the process of analyzing a user's emotional state from text data and feedback, and assessing their psychological state, such as stress and satisfaction.

[1615] "Improvement proposals" refer to specific proposals and measures aimed at streamlining business processes and improving quality.

[1616] A "machine learning model" refers to a group of algorithms or programs that learn from large amounts of data and automatically analyze patterns and trends.

[1617] A "report" is a document that summarizes analysis results and improvement proposals, and is provided in PDF or HTML format.

[1618] "Emotion analysis data" refers to data relating to the user's emotional state obtained as a result of emotion analysis.

[1619] This invention is a system for streamlining business processes and improving business processes by taking into account the emotional state of users. This system combines multiple hardware and software components to collect and analyze request data, generate a business process flow model, identify waste and areas for improvement, and present improvement proposals that integrate user emotional data.

[1620] Hardware and Software Configuration

[1621] Hardware:

[1622] Server: Responsible for main processes such as data collection, analysis, flow modeling, and report generation.

[1623] Terminal: Serves as an interface for users to access and view the generated reports.

[1624] software:

[1625] Natural language processing engine: Analyzes requested data and extracts key information using Google Cloud Natural Language API, etc.

[1626] Emotion analysis engine: Using IBM Watson Tone Analyzer and other tools, analyzes the user's emotional state and generates numerical data.

[1627] Machine learning models: Used to analyze business process flow models and sentiment data to identify waste and areas for improvement.

[1628] Dashboard tools: Visualize business process flow models using tools such as Microsoft Power BI.

[1629] Program Processing Overview

[1630] The program of this system implements the following main functions:

[1631] 1. Data Collection:

[1632] The server periodically retrieves new emails from the mail server and stores them in storage. It also collects related documents such as database application forms from the file server and stores them in storage.

[1633] 2. Data Analysis:

[1634] The server sends the emails and documents stored in the storage to a natural language processing engine, which analyzes the text data. Important key information (e.g., "delivery date," "person in charge," and "content") is extracted and stored in a database.

[1635] 3. Flow Modeling:

[1636] The server generates a business process flow model based on the key information stored in the database. The generated model is visualized using a dashboard tool.

[1637] 4. Emotion analysis:

[1638] The emotion engine analyzes emails and feedback forms sent by users and generates numerical data representing the user's emotional state. This emotional data is sent to the server and integrated into the business process flow model.

[1639] 5. Identify waste and areas for improvement:

[1640] AI analyzes business process flow models and sentiment analysis data to identify unnecessary steps and inefficiencies.

[1641] 6. Proposal for improvement:

[1642] Based on the identified waste and areas for improvement, the AI ​​generates specific improvement proposals, taking into account emotional data and proposing things like workload and task reallocation.

[1643] 7. Report Generation:

[1644] The server creates a detailed report based on the generated improvement proposals and business process flow model. The report is output in PDF or HTML format and provided to the user via their terminal.

[1645] Specific examples

[1646] For new product development projects

[1647] Data collection: The server collects emails requesting new product development sent by the sales department and database change request forms sent by the IT department, and stores them in storage.

[1648] Data analysis: The server analyzes the request email, extracts key information such as "Delivery date: 2023-12-31" and "Person in charge: Tanaka", and stores it in a database.

[1649] Flow modeling: Based on the extracted key information, the server generates a business process flow model from the Sales Department → IT Department → Quality Control Department → Marketing Department, and visualizes it using a dashboard tool.

[1650] Sentiment analysis: The emotion engine analyzes emails and feedback sent by project managers and generates emotional data such as "high stress level."

[1651] Identifying waste and areas for improvement: AI analyzes workflow models and sentiment data to identify duplicate data entries across multiple departments and multiple approval steps.

[1652] Suggested improvements: AI can suggest improvements such as centralizing data entry, automating approval steps, or delegating specific tasks to other members.

[1653] Report generation: The server generates a detailed report based on the improvement proposal and provides it to the person in charge (Tanaka) via the terminal.

[1654] Example prompt sentence:

[1655] Please extract key information about the business flow from the following email. Email content: 'The sales department requests the start of the next new product development project as follows. The deadline is 2023-12-31, and the person in charge is Tanaka.'

[1656] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1657] Step 1:

[1658] The server periodically retrieves new emails from the mail server. The mail server connection information and a query to retrieve new emails are used as input. The server temporarily stores the retrieved emails in storage. It also collects database application forms and related documents from the file server and stores them in storage. This completes the collection of request data.

[1659] Step 2:

[1660] The server sends the emails and documents stored in storage to a natural language processing engine (e.g., Google Cloud Natural Language API). The stored emails and documents are used as input. The natural language processing engine analyzes the text data and extracts key information such as delivery date, person in charge, and content. The server stores the extracted key information in a database and records the analysis results in a log. This extracts the key information.

[1661] Step 3:

[1662] The server generates a business process flow model based on key information stored in the database. The key information is used as input. The server uses this key information to visualize the business flow step by step, creating a series of business procedures and processes. The generated business process flow model is visualized using a dashboard tool. This generates a business process flow model.

[1663] Step 4:

[1664] The emotion engine (e.g. IBM Watson Tone Analyzer) analyzes emails and feedback forms sent by users. The emails and feedback sent by users are used as input. The emotion engine analyzes the user's emotional state (e.g. stress, satisfaction, etc.) from this text data and generates numerical data. The emotion analysis data is sent to the server, which then analyzes the user's emotional state.

[1665] Step 5:

[1666] The AI ​​uses the business process flow model and sentiment analysis data provided by the server to identify wasteful steps and inefficient areas. The business process flow model and sentiment analysis data are used as input. The AI ​​performs analysis using a machine learning model, generates a report detailing the identified problems, and sends it to the server. This identifies waste and areas for improvement.

[1667] Step 6:

[1668] The AI ​​creates specific improvement proposals based on the identified waste and improvement points. The waste and improvement points are used as input. The AI ​​generates improvement proposals that include suggestions for centralizing data entry, automating approval steps, and reassigning tasks. Sentiment analysis data is also taken into account, and measures to reduce user stress are included. The improvement proposals are sent to the server. This generates specific improvement proposals.

[1669] Step 7:

[1670] The server creates a detailed report based on the improvement proposals provided by the AI. The improvement proposals and the business process flow model are used as input. The server generates a report that includes a visual representation of the business process flow model, detected problems, and specific improvement suggestions. The generated report is output in PDF or HTML format and provided to the user via their terminal. This completes the report generation process.

[1671] (Application example 2)

[1672] 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."

[1673] Conventional business process management systems have the problem that they are unable to take into account the emotions and stress levels of users when identifying wasteful work flows and areas for improvement, making it difficult to improve work efficiently. This problem is particularly important in brick-and-mortar stores, where the emotions and motivation of staff members directly affect work efficiency.

[1674] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting request data, means for analyzing the collected data using a natural language processing engine and extracting key information, means for generating a business process flow model based on the extracted key information, means for incorporating user emotion data into the generated business process flow model and performing emotion analysis, means for identifying waste and improvement points based on an analysis of the generated business process flow model, means for presenting improvement proposals for the identified waste and improvement points, and means for generating and outputting a report based on the improvement proposals and the business process flow model. This enables precise business improvement that takes user emotions into consideration.

[1675] "Request data" refers to data that includes information and requirements related to business processes.

[1676] A "natural language processing engine" is a software function that analyzes text data and extracts meaning and key information.

[1677] "Key information" is information that extracts important parameters and topics from the collected data.

[1678] A "business process flow model" is a model that visually and structurally represents business procedures and processes.

[1679] "Emotion analysis" is a method of converting user emotions into data and using the results to identify factors that affect business processes.

[1680] "Waste" refers to inefficient steps or unnecessary work in a business process.

[1681] "Improvement points" refer to areas that can be improved to make business processes more efficient.

[1682] "Improvement proposals" refer to specific proposals for eliminating waste and inefficiencies in business processes.

[1683] The "means for generating and outputting reports" is a function that creates a detailed report based on the generated business process flow model and improvement proposals, and provides it to the user.

[1684] "Emotion data" is data obtained by analyzing and quantifying the user's emotional state.

[1685] "Structured data" is data in which key information is organized and arranged according to a certain format.

[1686] A "machine learning model" is an algorithm that recognizes patterns based on data and automatically performs analysis and predictions.

[1687] System Overview

[1688] The present invention is a new system that combines the efficiency of business processes in brick-and-mortar stores with user emotion analysis. This system collects request data, analyzes the data using a natural language processing engine, and generates a business process flow model based on the extracted key information. Then, it analyzes user emotions using an emotion engine and incorporates them into the business process flow model to generate precise improvement proposals and output them as a report. Specific embodiments are described below.

[1689] Hardware and software used

[1690] Smartphones: Used as individual staff devices.

[1691] Emotion engine: Powered by Microsoft Azure Cognitive Services.

[1692] Natural language processing engine: Uses Google Cloud Natural Language API.

[1693] Database: Uses Firebase Realtime Database.

[1694] Flow Design Tool: A flow design dashboard powered by React.js.

[1695] Program processing

[1696] The server includes the following means:

[1697] 1. Data Collection Methods

[1698] The server collects business data from each device in the store. For example, it aggregates business data entered by staff on their smartphones and event data from sensors. This data is temporarily stored in a database.

[1699] 2. Natural Language Processing Methods

[1700] The collected data is sent to the server's natural language processing engine, where key information is extracted, such as "break time," "number of customer interactions," and "product replenishment work."

[1701] 3. Method for generating business process flow models

[1702] Based on the extracted key information, a business process flow model is generated on the server. This model visually represents business procedures and processes and can be viewed on a dashboard.

[1703] 4. Emotion analysis means

[1704] The server uses an emotion engine to analyze the emotional data of the staff, which is expressed as, for example, the staff's "stress level" or "motivation index."

[1705] 5. Identifying waste and areas for improvement

[1706] Based on the generated business process flow model and emotional data, AI identifies unnecessary steps and areas for improvement, focusing on analyzing business flows where the emotional data indicates high stress.

[1707] 6. Means for presenting improvement proposals

[1708] The server generates specific improvement proposals based on the identified waste and improvement points, such as centralizing data entry, automating approval steps, and redistributing tasks.

[1709] 7. Report Generation Methods

[1710] The server generates a detailed report based on the business process flow model and improvement proposals, and outputs it in PDF or HTML format. The report can be viewed on a smartphone or PC.

[1711] Specific examples

[1712] Example: Improving business processes in physical stores

[1713] In physical stores, staff record their daily work on their smartphones. For example, data such as "product inventory" and "customer service details" is entered. The data is stored in a Firebase database, and the server periodically retrieves it. A natural language processing engine extracts key information and generates a business process flow model. An emotion engine analyzes staff daily reports and feedback emails to detect stress levels. AI identifies unnecessary steps and areas for improvement, and proposes specific improvement proposals, including automating data entry and dividing up tasks. Finally, a detailed report is generated and provided to managers.

[1714] Prompt Sentence Examples

[1715] "We are developing a new operational improvement tool for our brick-and-mortar stores. This tool analyzes staff work processes and emotions and generates specific improvement proposals. Please explain the steps to perform the following operations.

[1716] 1. Collecting data from Firebase Realtime Database

[1717] 2. Obtaining sentiment scores using a sentiment analysis engine

[1718] 3. Creation and visualization of business flow models

[1719] 4. Preparation of a detailed report with improvement suggestions

[1720] The present invention enables precise business improvement that takes into account the user's emotions.

[1721] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1722] Step 1:

[1723] The server collects business data from each device in the physical store. Specifically, it aggregates business data entered by staff on their smartphones and event data from sensors in the store. The entered data is collected in file format or via API, and temporarily stored in the Firebase Realtime Database. This data becomes the input data for the next processing step.

[1724] Step 2:

[1725] The server retrieves the collected data from Firebase and sends it to a natural language processing engine (Google Cloud Natural Language API). At this time, business data in text format becomes the input data. The natural language processing engine analyzes this data and extracts key information important to the business process (for example, "break time," "number of customer interactions," "product replenishment work," etc.). The extracted key information is sent to the next step as output data.

[1726] Step 3:

[1727] The server generates a business process flow model based on the extracted key information. The input data is the key information extracted in the previous step, and the generated business process flow model is expressed in XML or JSON format. This model visually represents business procedures and processes, and is displayed on a flow design dashboard using React.js. The generated business process flow model becomes the output data.

[1728] Step 4:

[1729] The server uses an emotion engine (Microsoft Azure Cognitive Services) to analyze staff emotional data. The input data is staff daily reports and feedback emails. The emotion engine analyzes this text data and generates emotional scores such as "stress level" and "motivation index" as output data.

[1730] Step 5:

[1731] The server reanalyzes the business process model based on the generated business process flow model and emotion score. The input data are the business process flow model and emotion score, and the AI ​​(machine learning model) identifies wasteful steps and areas for improvement. For example, if a high stress level is detected in a specific business process, it suggests that the business steps are inefficient. A business process flow model with wasteful steps and areas for improvement marked is generated as output data.

[1732] Step 6:

[1733] The server generates specific improvement proposals based on the identified waste and improvement points. The input data is a business process flow model that includes wasteful steps and improvement points. The AI ​​generates specific improvement proposals, such as centralizing data entry, automating approval steps, and redistributing tasks. The generated improvement proposals are sent to the next step as output data.

[1734] Step 7:

[1735] The server generates a detailed report based on the business process flow model and improvement proposals. The input data are the improvement proposals and the business process flow model. The server formats this data into a document and creates a report in PDF or HTML format. The generated report is sent to the user's device as output data. The user can view the report on their smartphone or computer and use it as a guideline for specific business improvements.

[1736] Through the above steps, precise business improvement that takes into account the user's emotions is realized.

[1737] 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.

[1738] 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.

[1739] 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.

[1740] 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.

[1741] 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.

[1742] 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.

[1743] 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).

[1744] 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.

[1745] 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."

[1746] 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.

[1747] 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).

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] 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.

[1753] 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.

[1754] 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.

[1755] 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.

[1756] 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.

[1757] 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.

[1758] The following is further disclosed regarding the above embodiment.

[1759] (Claim 1)

[1760] a means for collecting requested data;

[1761] A means for analyzing the collected data using a natural language processing engine and extracting key information;

[1762] A means for generating a business process flow model based on the extracted key information;

[1763] A means for identifying waste and points for improvement based on an analysis of the generated business process flow model;

[1764] A means of proposing improvement proposals for identified waste and improvement points, ...

Claims

1. a means for collecting requested data; A means for analyzing the collected data using a natural language processing engine and extracting key information; A means for generating a business process flow model based on the extracted key information; A means for identifying waste and points for improvement based on an analysis of the generated business process flow model; A means of proposing improvement proposals for identified waste and improvement points, A means for generating and outputting reports based on improvement proposals and business process flow models; A system including:

2. 2. The system of claim 1, further comprising means for converting the key information into structured data.

3. The system according to claim 1 , further comprising means for analyzing waste and points for improvement using a machine learning model.

Images