system

Abstract

We provide a system for systematically managing business handover information, automatic knowledge accumulation, and new business proposals. [Solution] A system including a means for inputting business handover information, a means for analyzing the input business handover information and saving it in a database, a means for searching for and displaying the analyzed business handover information, a means for collecting feedback obtained during the business handover process and storing it in a database, a means for analyzing the stored data and updating a knowledge base, a means for automatically generating new business proposals based on the updated knowledge base, a means for notifying relevant parties of the generated new business proposals and receiving evaluations, and a means for analyzing the evaluations and improving the proposal algorithm and knowledge base.

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 the conventional business handover process, there were many problems due to the lack of handover information and lack of communication between multiple personnel. This made it difficult for new personnel to take over the business smoothly, hindering business efficiency and effective use of knowledge. Furthermore, there was no system that effectively utilized accumulated business knowledge to propose new business ventures. To solve these issues, a system for systematically managing business handover information and an automatic knowledge accumulation and new business proposal system was required. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for inputting task handover information; means for analyzing the input task handover information and saving it in a database; means for searching and displaying the analyzed task handover information; means for collecting feedback obtained during the task handover process and storing it in a database; means for analyzing the accumulated data and updating a knowledge base; means for automatically generating new business proposals based on the updated knowledge base; means for notifying relevant parties of the generated new business proposals and receiving their evaluations; and means for analyzing the evaluations and improving the proposal algorithm and knowledge base. This prevents information leaks and insufficient communication during task handover, enabling efficient handover. Furthermore, automating new business proposals based on accumulated business knowledge can promote effective knowledge utilization and business innovation.

[0006] "Business handover information" is a general term for information required when handing over business to the next person in charge, such as business content, procedures, important contact information, and related materials.

[0007] "Input means" refers to a device or interface that allows a user to input task handover information into the system, such as a keyboard, touch screen, or device including dedicated software.

[0008] "Means for analysis" refers to the system's function of using natural language processing technology or other data analysis technology to recognize the input business handover information as structured data and convert it into a format that can be stored in a database.

[0009] "Means of storage" refers to a database or storage system that can centrally manage and store analyzed business handover information, as well as the management software for such a system.

[0010] "Means for searching and displaying" refers to functions that include a search engine and a user interface that allow users to easily search for the necessary handover information and present it in a viewable format.

[0011] "Means for collecting feedback" refers to an interface that allows users to report any questions or improvements that arise during the course of their work to the system, as well as the corresponding data collection and storage functions.

[0012] "Means for analyzing data" refers to data mining techniques and machine learning algorithms that statistically analyze collected feedback and business data to extract useful insights and patterns.

[0013] "Means for updating the knowledge base" refers to a management system that improves and expands the existing knowledge database based on the results of the analysis and incorporates the latest information.

[0014] "Means for automatically generating new business proposals" refers to algorithms or software functions that use accumulated knowledge to automatically generate new business ideas or project proposals.

[0015] "Means for notifying stakeholders of proposals and receiving evaluations" refers to tools for distributing generated new business proposals to stakeholders via email or notification systems, and for collecting and managing subsequent feedback and evaluations.

[0016] "Means for improving the proposal algorithm and knowledge base" refers to the system's functions for continuously improving and updating the new business proposal generation algorithm and knowledge base based on evaluations and feedback from stakeholders. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The system of the present invention is configured around a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals.

[0039] 1. Business transfer intermediation

[0040] Entering transfer information

[0041] User: A new employee (Employee A) uses a terminal to input task handover information into the server to hand over his or her task to the next employee (Employee B). The input information includes the task content, specific procedures, important contact information, and related materials.

[0042] Analysis and storage of handover information

[0043] Server: Analyzes the received task handover information using natural language processing technology and converts it into structured data. This structured data is then stored in a database.

[0044] Information Access

[0045] User: Employee B, who will take over the work, logs in to the server using a terminal and searches and displays the saved handover information. The server displays the search results in an appropriate format so that Employee B can easily understand them.

[0046] Providing feedback

[0047] User: Enters any questions or suggestions for improvement that arise during work into the server via a terminal. This allows Employee B to carry out their work smoothly.

[0048] 2. Accumulation of business knowledge

[0049] Data organization

[0050] Server: Integrates and organizes the work handover information provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[0051] Knowledge Base Updates

[0052] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[0053] Auto-tagging

[0054] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[0055] 3. Generate new business proposals

[0056] Data analysis

[0057] Server: Uses machine learning algorithms to periodically analyze accumulated operational data, particularly to identify success stories and frequently occurring issues.

[0058] Generate new business proposals

[0059] Server: Based on the analysis results, the server automatically generates new business proposals by combining multiple business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[0060] Proposal notification and evaluation

[0061] Server: Notifies stakeholders of generated new business proposals and distributes them via email and notification systems.

[0062] User: The employee who receives the proposal checks the content on their device and provides feedback by rating and commenting. The rating is then stored in the database by the server.

[0063] Using Feedback

[0064] Server: Analyzes the feedback and ratings received and helps improve the proposed algorithm and knowledge base.

[0065] Specific examples

[0066] 1. Business transfer intermediation

[0067] User: Employee A (HR department staff) enters the "New Employee Orientation Procedures" into the server from a terminal.

[0068] Server: Analyzes using NLP technology and stores procedures and related materials in a database.

[0069] User: Employee B logs in, searches for "New Employee Orientation Procedures," and views it.

[0070] Users: Report any questions or improvements to the server via their devices and provide feedback.

[0071] 2. Accumulation of business knowledge

[0072] Server: The feedback provided by Employee A and Employee B is stored in a database, and the analysis results are added to the knowledge base.

[0073] 3. Generate new business proposals

[0074] Server: Regularly analyze data and propose new marketing strategies that combine "marketing success stories" and "customer abandonment analysis."

[0075] User: The employee who receives the proposal reviews it on their device and provides evaluation comments. The server uses this feedback to improve the proposal algorithm.

[0076] In this way, the system allows the server, terminals, and users to work together at each processing step, improving the efficiency of business handovers and automating new business proposals.

[0077] The processing flow will be explained below.

[0078] Business transfer intermediation

[0079] Step 1: Enter your transfer information

[0080] User: Employee A uses a terminal to enter the task handover information into the server. Specifically, he fills out an input form with the task content, procedures, important contact information, and related documents.

[0081] Step 2: Analyze the handover information

[0082] Server: Analyzes the received task handover information using natural language processing (NLP) technology. As a result of the analysis, the information is recognized as structured data and converted into a format that can be stored in a database.

[0083] Step 3: Save the transfer information

[0084] Server: Stores structured data in a database and organizes it into categories, allowing for consistent access and searching.

[0085] Step 4: Information Access

[0086] User: Employee B, the new employee, logs in to the server using a terminal and searches for the stored handover information. For example, he enters "New Employee Orientation Procedures" in the search field.

[0087] Server: Processes the search query, retrieves the relevant handover information from the database, and displays it on the device.

[0088] Step 5: Provide feedback

[0089] User: Employee B uses a terminal to report any questions or improvements that arise while performing his / her work to the server. Specifically, he / she fills in a feedback form.

[0090] Server: The provided feedback is stored in a database and used to improve future operations.

[0091] Accumulation of business knowledge

[0092] Step 1: Organize your data

[0093] Server: Integrates and organizes handover information and feedback provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[0094] Step 2: Update your knowledge base

[0095] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[0096] Step 3: Auto-tagging

[0097] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[0098] Knowledge integration and new business proposal generation

[0099] Step 1: Data analysis

[0100] Server: Uses machine learning algorithms to analyze accumulated operational data on a regular basis, particularly to identify success stories and frequently occurring issues.

[0101] Step 2: Generate a new business proposal

[0102] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[0103] Step 3: Proposal Notification

[0104] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[0105] Step 4: Collect ratings

[0106] User: The employee who receives the proposal checks the proposal on their device and enters their evaluation and comments as feedback into the server.

[0107] Server: The received feedback and ratings are stored in a database and used to improve the proposed algorithm and knowledge base.

[0108] Specific examples

[0109] 1. Enter and save transfer information

[0110] User: Employee A enters the "New Employee Orientation Procedures" on the terminal.

[0111] Server: Analyzes the information using NLP techniques and stores it in a database.

[0112] 2. Searching for and displaying information

[0113] User: Employee B searches for "New Employee Orientation Procedures" on his device.

[0114] Server: Retrieves relevant information from the database and displays it.

[0115] 3. New business proposal generation and evaluation

[0116] Server: Analyzes business data and generates new marketing strategies as proposals.

[0117] User: Receives suggestions and provides evaluation comments.

[0118] Server: Based on the feedback, improve the next proposed algorithm.

[0119] In this way, the entire system works together efficiently, streamlining business handovers and automating new business proposals.

[0120] Example 1

[0121] 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."

[0122] In modern companies, business handover is a very important process, but managing the information involved is complicated and time-consuming. Furthermore, creating new business proposals requires a lot of time and effort, making it difficult to efficiently utilize past knowledge and success stories. To address this situation, a system is needed that efficiently manages business handover information and automatically utilizes accumulated knowledge to streamline the creation of new business proposals.

[0123] 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.

[0124] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information using natural language processing technology and storing it in a database, means for searching for and displaying the analyzed task handover information using a search engine, means for collecting feedback obtained during the task handover process and storing it in a database, means for organizing and integrating the stored data and updating a knowledge base, means for automatically generating new business proposals using a machine learning algorithm based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, and means for analyzing the evaluations and improving the proposal algorithm and knowledge base. This enables efficient information management of task handovers and automatic generation of new business proposals.

[0125] "Business handover information" refers to information necessary when the current person in charge hands over the business to the next person in charge, and includes the business content, specific procedures, important contact information, related materials, etc.

[0126] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology that performs text analysis, entity extraction from language data, sentiment analysis, etc.

[0127] A "database" is a collection of data that is centrally managed and structured so that it can be easily accessed, searched, and updated.

[0128] A "search engine" is a system for efficiently searching information stored in a database, a technology that allows a search query to be used to quickly find relevant information.

[0129] "Feedback" is information that records questions, areas for improvement, suggestions, etc. that arise during the course of work and returns them to the next person in charge or to the system.

[0130] A "knowledge base" is a collection of knowledge that a system possesses, and is a structured database of information that includes success stories, efficient business procedures, and so on.

[0131] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and make predictions and judgments, and is a technology used to analyze big data and build predictive models.

[0132] A "new business proposal" refers to a new business plan or business idea that is constructed based on existing knowledge and data.

[0133] "Notification" is the act of sending information from the system to relevant parties, and is done via email or internal notification systems.

[0134] "Evaluation" refers to feedback provided by stakeholders on new business proposals received, and includes opinions and comments on the effectiveness of the proposal and areas for improvement.

[0135] The purpose of the system of this invention is to efficiently manage business handover information and automatically generate new business proposals. This system not only inputs, analyzes, saves, searches, and displays business handover information, but also accumulates feedback, updates the knowledge base, and automates the series of processes of generating, notifying, and evaluating new business proposals.

[0136] Enter and save business handover information

[0137] User: The person taking over the work (User A) uses their own terminal to access the server and enter details of the work, specific procedures, important contacts, and related materials. The terminal is a commonly used computing device that connects to the server through a browser or a dedicated application.

[0138] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy" or "BERT") and converted into structured data (such as JSON format). The analyzed data is stored in a database such as "MongoDB." For example, text-formatted business procedures are divided into steps and associated tags are added.

[0139] Search and display business handover information

[0140] User: The new person in charge (User B) logs in to the server from a terminal and sends a query to search for task handover information. A search engine such as "ElasticSearch (registered trademark)" is used for the search. The search results are displayed in an easy-to-understand HTML format. An example of a specific prompt is shown below.

[0141] "What are the new employee orientation procedures?"

[0142] "Find information on the latest marketing strategies."

[0143] Collecting and storing feedback

[0144] Users: If they have any questions or suggestions for improvement while performing their work, they can use the feedback form to send feedback to the server via their terminal. This feedback includes ratings and comments, and is saved in the database.

[0145] Knowledge Base Updates

[0146] Server: Automatically organizes and consolidates feedback and handover information provided by multiple users, eliminating redundant and duplicate information. This process uses data processing libraries such as "pandas." The knowledge base is updated based on the organized data. For example, the steps and key points of successful projects are added to "GraphDB."

[0147] Generate and notify new business proposals

[0148] Server: Based on the accumulated data, new business proposals are automatically generated using machine learning algorithms (e.g., Scikit-learn or Tensorflow®). The generated new business proposals are notified to relevant parties and distributed via email or an internal notification system (e.g., SendGrid).

[0149] User: The person in charge who receives the proposal checks the content on their device and provides feedback such as ratings and comments. The results are collected by the server and stored in the database.

[0150] Improvement of the proposed algorithm

[0151] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[0152] As described above, the interconnection of servers, terminals, and users enables efficient information management for business handovers and the automatic generation of new business proposals. This system improves the efficiency of business processes and enables the rapid development of new businesses.

[0153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0154] Step 1:

[0155] Entering business handover information

[0156] User: The person taking over the work (User A) accesses the server from their own terminal and enters the work handover information. The input form displayed on the terminal includes the work content, specific procedures, important contact information, related materials, etc. For example, the user fills in "New employee orientation procedures" in the input form. The entered information is sent to the server as an HTTP request.

[0157] Input: Job description, specific procedures, important contacts, related materials

[0158] Output: Structured task handover information sent to the server

[0159] Step 2:

[0160] Analysis and storage of handover information

[0161] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy"), and the text data is converted into structured data (such as JSON format). During the analysis process, keywords are extracted from the text and intent is understood. The analyzed data is stored in a database such as "MongoDB."

[0162] Input: Unstructured business handover information

[0163] Output: Structured business handover information (JSON format)

[0164] Step 3:

[0165] Information search and display

[0166] User: The next person in charge (User B) logs in to the server from a terminal and enters a query to search for the saved handover information. The server uses Elasticsearch to search and displays the results in HTML format. For example, if User B searches for "New Employee Orientation Procedures," the details are displayed.

[0167] Input: Search query (e.g., "new employee orientation procedures")

[0168] Output: Search results (displayed in HTML format)

[0169] Step 4:

[0170] Providing feedback

[0171] Users: If they have any questions or suggestions for improvement while performing their work, they can use their terminals to enter them into a feedback form and send it to the server. This information can be used to improve work. For example, a user might comment, "There is some material that should be added to the orientation procedures."

[0172] Input: Feedback content (text format)

[0173] Output: Feedback data sent to the server

[0174] Step 5:

[0175] Accumulating and organizing feedback

[0176] Server: The received feedback data is stored in a database. After that, multiple pieces of feedback are consolidated and organized, and redundant and duplicate information is removed. This is done using libraries such as "pandas" to build a consistent database.

[0177] Input: Feedback data (multiple inputs)

[0178] Output: Organized feedback data

[0179] Step 6:

[0180] Knowledge Base Updates

[0181] Server: Automatically updates the knowledge base based on organized data, including best practices and efficient business procedures. The information is stored in a GraphDB and made available as company-wide knowledge.

[0182] Input: Organized feedback data

[0183] Output: Updated knowledge base

[0184] Step 7:

[0185] Generate new business proposals

[0186] Server: Based on the updated knowledge base, the server automatically generates new business proposals using machine learning algorithms (e.g., Scikit-learn and TensorFlow). For example, it proposes new marketing strategies by combining marketing success stories with customer churn analysis.

[0187] Input: Updated Knowledge Base

[0188] Output: New business proposal (text format, etc.)

[0189] Step 8:

[0190] Proposal notification and evaluation

[0191] Server: Notifies the generated new business proposals to the relevant parties and distributes them via email or internal notification systems. The person in charge who receives the proposals can check the contents of the proposals on their terminals and provide evaluation comments as feedback.

[0192] Input: New business proposal

[0193] Output: Evaluation comments for the proposal

[0194] Step 9:

[0195] Improvement of the proposed algorithm

[0196] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[0197] Input: Feedback and Rating Comments

[0198] Output: Improved proposed algorithm and knowledge base

[0199] (Application example 1)

[0200] 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."

[0201] In modern brick-and-mortar store operations, efficient handover of operations and centralized knowledge management are important. However, conventional methods have had problems such as cumbersome collection and management of handover information and inefficient generation of new business proposals. Furthermore, there were also issues with insufficient sharing of feedback between staff and automatic generation of sales promotion plans based on accumulated knowledge.

[0202] 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.

[0203] In this invention, the server includes: means for inputting business handover information; means for analyzing the input business handover information and saving it in a database; means for searching for and displaying the analyzed business handover information; means for collecting feedback obtained during the business handover process and storing it in a database; means for analyzing the stored data and updating a knowledge base; means for automatically generating new business proposals based on the updated knowledge base; means for notifying relevant parties of the generated new business proposals and receiving their evaluations; means for analyzing the evaluations and improving the proposal algorithm and knowledge base; means for managing business information related to store operation and making it accessible via a smartphone during handover; means for building a knowledge base for store operation and automatically generating new sales promotion plans based on feedback; and means for evaluating the generated new proposals and collecting improvements. This improves the efficiency of business handover in physical stores, enables centralized management of the knowledge base, and enables automatic generation of new proposals based on feedback.

[0204] "Business handover information" refers to the information required for an employee to hand over their work to the next person in charge, including specific work content and procedures, important contact information, and related materials.

[0205] A "server" is a computer system for analyzing, storing, and managing data, and plays a role in centrally managing information that users can access.

[0206] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language (language used by humans on a daily basis), and can analyze the meaning of sentences and convert them into structured data.

[0207] A "machine learning algorithm" is an algorithm that finds patterns and rules based on large amounts of data and makes predictions and classifications.

[0208] A "database" is a system for efficiently storing, searching, and managing large amounts of information.

[0209] A "knowledge base" is a database that accumulates information and know-how about a specific field or business, and is used to improve business efficiency and automate operations.

[0210] A "new business proposal" is a new idea or plan for improving operations or business processes based on accumulated data and feedback.

[0211] "Feedback" refers to information that reports opinions and areas for improvement obtained during the course of business, and is used to improve the system and generate new proposals.

[0212] A "smartphone" is a mobile phone terminal equipped with advanced computing power and communication functions, and is capable of running a variety of applications.

[0213] "Store operations" refers to all operations related to running a store, such as managing a physical store, product display, inventory management, and sales promotion.

[0214] "Building a knowledge base" means accumulating and systematically storing business-related knowledge and know-how, and using that knowledge to make business improvements and proposals.

[0215] This invention is a system for efficiently managing business handover information in a physical store, building a knowledge base related to store management, and automatically generating new sales promotion plans based on feedback. This system is implemented using a server and user terminals (e.g., smartphones).

[0216] System Program

[0217] The system has a program with the following main components:

[0218] 1. A means of entering business handover information.

[0219] 2. A means of analyzing the entered business handover information and storing it in a database.

[0220] 3. A means for searching and displaying the analyzed business handover information.

[0221] 4. A means of collecting feedback obtained during the business handover process and storing it in a database.

[0222] 5. A means of analyzing accumulated data and updating the knowledge base.

[0223] 6. A means of automatically generating new business proposals based on the updated knowledge base.

[0224] 7. A means of informing stakeholders of generated new business proposals and receiving their evaluation.

[0225] 8. A means of analyzing the evaluation and improving the proposed algorithm and knowledge base.

[0226] 9. A means of managing business information related to store operations and making it accessible via smartphone when taking over.

[0227] 10. A means of building a knowledge base for store operations and automatically generating new promotional plans based on feedback.

[0228] 11. A means of evaluating new proposals generated and collecting suggestions for improvement.

[0229] Explanation of program processing

[0230] The server receives the task handover information entered by the user (store manager or staff member) using their smartphone. The server analyzes this information using natural language processing technology (for example, Python's NLP library), converts it into structured data, and stores it in a database. The user can then use their smartphone to search for and view the stored handover information.

[0231] Feedback is collected via smartphones, and when users enter questions or suggestions for improvement they have while performing their work, the server stores them in a database. The server periodically analyzes the accumulated feedback and data and updates the knowledge base. Machine learning algorithms (e.g., scikit-learn) are used to automatically generate new sales promotion plans and business improvement proposals.

[0232] The generated new business proposals are notified to the user, who can provide ratings and comments via their smartphone. The server analyzes this feedback and uses it to improve the proposal algorithm and knowledge base.

[0233] Specific examples

[0234] For example, a store manager can input new inventory management methods on their smartphone, and when staff review them, they can provide feedback such as "the order of products is unclear," allowing the system to automatically suggest new sales based on inventory shortages.

[0235] Examples of prompts include:

[0236] The new store manager has entered the information on inventory management and promotions. At the same time, the staff has provided feedback on the product arrangement. Based on this, please propose a new promotion plan.

[0237] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0238] Step 1:

[0239] The user inputs task handover information using a smartphone. The input information includes the task content, procedures, important contact information, and related materials. The input data is sent to the server.

[0240] Step 2:

[0241] The server analyzes the received task handover information using natural language processing technology (for example, a Python NLP library). The analyzed data is converted into structured data and stored in a database. The input is raw text data, and the output is structured data.

[0242] Step 3:

[0243] The user accesses the server using a smartphone and searches for the stored handover information. The server processes the search query and displays the appropriate handover information on the screen. The input is the search query, and the output is the formatted handover information.

[0244] Step 4:

[0245] Users can input any questions or improvements they have while working on their smartphones and send them as feedback to the server, which then stores the feedback in a database. The input is raw text feedback data, and the output is the feedback data stored in the database.

[0246] Step 5:

[0247] The server periodically analyzes the accumulated feedback and task handover information and updates the knowledge base. The analysis includes data cleansing and statistical techniques. The input is the accumulated data, and the output is an updated knowledge base.

[0248] Step 6:

[0249] The server automatically generates new business proposals using a machine learning algorithm (e.g., scikit-learn) based on the updated knowledge base. The input is the updated knowledge base, and the output is the new business proposal.

[0250] Step 7:

[0251] The generated new business proposal is notified to the relevant parties via smartphone or email. The user reviews the proposal and provides feedback such as ratings and comments. The input is the new business proposal, and the output is the ratings and comments.

[0252] Step 8:

[0253] The server analyzes the received ratings and comments and improves the proposed algorithm and knowledge base. The input is the ratings and comments, and the output is the improved algorithm and knowledge base.

[0254] 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.

[0255] The system of the present invention is composed mainly of a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals, and is further combined with an emotion engine that recognizes and analyzes user emotions.

[0256] 1. Business transfer intermediation

[0257] Entering transfer information

[0258] User: A new person in charge (Employee A) uses a terminal to input task handover information into the server to hand over the task to the next person in charge (Employee B). The input information includes the task content, procedures, important contact information, and related materials. During input, the emotion engine also analyzes the user's emotions and collects emotional data about the task.

[0259] Analysis and storage of handover information

[0260] Server: Along with the emotional data analyzed by the emotion engine, the task handover information is analyzed using natural language processing (NLP) technology and stored in a database as structured data.

[0261] Information Access

[0262] User: Employee B, the new person in charge, logs in to the server using a terminal and searches for the saved handover information. The server provides search results including emotional data, allowing Employee B to understand the handover information taking emotional aspects into account.

[0263] Providing feedback

[0264] User: Employee B reports any questions or areas for improvement that arise during the course of work, as well as his or her feelings at the time, to the server via his or her terminal.

[0265] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[0266] 2. Accumulation of business knowledge

[0267] Data organization

[0268] Server: Integrates and organizes task handover information, feedback, and sentiment data provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[0269] Knowledge Base Updates

[0270] Server: Automatically updates the knowledge base based on the organized data and sentiment data. For example, it adds sentiment data related to success stories and efficient business procedures to the knowledge base.

[0271] Auto-tagging

[0272] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[0273] Knowledge integration and new business proposal generation

[0274] Data analysis

[0275] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[0276] Generate new business proposals

[0277] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department" with "customer abandonment analysis" and related emotional data.

[0278] Proposal notification and evaluation

[0279] Server: Distributes generated new business proposals to stakeholders via email and notification systems. Uses an emotion engine to recognize users' reactions and ratings.

[0280] Collecting ratings

[0281] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[0282] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[0283] Specific examples

[0284] 1. Enter and save transfer information

[0285] User: Employee A enters the "New Employee Orientation Procedure" into the terminal, and their emotions at the time are also collected.

[0286] Server: Analyzes business information and emotion data using NLP technology and stores it in a database.

[0287] 2. Searching for and displaying information

[0288] User: Employee B searches for "New Employee Orientation Procedures."

[0289] Server: Retrieves related information along with emotion data from the database and displays it.

[0290] 3. New business proposal generation and evaluation

[0291] Server: Analyzes business and sentiment data and generates new marketing strategy proposals.

[0292] User: Receives suggestions and provides evaluation comments and sentiment data.

[0293] Server: Based on the feedback, improve the next proposed algorithm.

[0294] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[0295] The processing flow will be explained below.

[0296] Business transfer intermediation

[0297] Step 1: Enter your transfer information

[0298] User: Employee A uses a terminal to input task handover information into the server. The information to be input includes the task content, procedures, important contacts, and related materials. As the information is being input, the emotion engine analyzes the user's emotions in real time and collects emotional data.

[0299] Step 2: Analyze the handover information

[0300] Server: Analyzes the received task handover information and emotional data using natural language processing (NLP) technology. The task information is recognized as structured data and converted into a format that can be stored in a database together with the emotional data.

[0301] Step 3: Save handover information and emotion data

[0302] Server: Structured task handover information and emotion data are stored in a database and organized by category, allowing for consistent access and retrieval.

[0303] Step 4: Information Access

[0304] User: Employee B, the new employee, logs in to the server using a terminal and searches for relevant handover information, for example, "New Employee Orientation Procedures."

[0305] Server: Processes the search query, retrieves the relevant handover information and emotion data from the database, and displays them on the device in an appropriate format.

[0306] Step 5: Provide feedback

[0307] User: Employee B uses a terminal to report any questions or improvements that arise during work to the server. The emotion engine also analyzes the emotions expressed at the time.

[0308] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[0309] Accumulation of business knowledge

[0310] Step 1: Organize your data

[0311] Server: Integrates and organizes handover information, feedback, and sentiment data provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[0312] Step 2: Update your knowledge base

[0313] Server: Automatically updates the knowledge base based on the organized data. For example, it adds best practices, efficient business procedures, and related emotional data to the knowledge base.

[0314] Step 3: Auto-tagging

[0315] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[0316] Knowledge integration and new business proposal generation

[0317] Step 1: Data analysis

[0318] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[0319] Step 2: Generate a new business proposal

[0320] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department," "customer abandonment analysis," and related emotional data.

[0321] Step 3: Proposal Notification

[0322] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[0323] Step 4: Collect ratings

[0324] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[0325] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[0326] Specific examples

[0327] 1. Enter and save transfer information

[0328] User: Employee A enters the "New Employee Orientation Procedure" into the terminal. At that time, the emotion engine analyzes Employee A's emotions and captures them as data.

[0329] Server: Uses NLP technology to analyze business information and emotion data and store them in a database.

[0330] 2. Searching for and displaying information

[0331] User: Employee B searches for "New Employee Orientation Procedures."

[0332] Server: Retrieves related information along with emotion data from the database and displays it.

[0333] 3. New business proposal generation and evaluation

[0334] Server: Analyzes business and sentiment data and generates new marketing strategies as proposals.

[0335] User: Receives suggestions and provides evaluation comments and sentiment data.

[0336] Server: Based on the feedback, improve the next proposed algorithm.

[0337] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[0338] Example 2

[0339] 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."

[0340] Conventional business handover systems have basic functions such as inputting, analyzing, and saving business information, but they lack consideration for user emotions. This can lead to a lack of understanding of the handover information and inappropriate new business proposals. Furthermore, it is necessary to utilize emotion data to generate more effective and appropriate new business proposals.

[0341] 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.

[0342] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information and saving it in a database, means for searching for and displaying the analyzed task handover information, means for collecting feedback obtained during the task handover process and storing it in a database, means for analyzing the stored data and updating a knowledge base, means for automatically generating new business proposals based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, means for analyzing the evaluations and improving the proposal algorithm and the knowledge base, means for analyzing user emotions and collecting task handover information including emotion data, means for assisting in understanding the task handover information based on the emotion data, and means for optimizing the new business proposals based on the emotion data. This enables task handover and new business proposals that take user emotions into consideration.

[0343] "Business handover information" refers to information including business content, procedures, important contact information, and related materials, and refers to all information necessary for the handover of business between personnel.

[0344] "Natural language processing technology" is a technology that analyzes text data written in natural language and understands and processes its meaning and structure. Specifically, it includes tokenization, part-of-speech tagging, grammatical analysis, etc.

[0345] A "database" refers to a collection of data that is structured so that the stored information can be efficiently managed and searched, and includes relational databases and NoSQL databases.

[0346] "Emotional energy" refers to software and algorithms that analyze a user's emotional state and record it as a number or category.

[0347] "Emotional data" refers to data that quantifies or categorizes a user's emotional state and is collected using contextual analysis and facial recognition technology.

[0348] A "knowledge base" is a database that systematically compiles important information within an organization, such as business procedures and success stories.

[0349] A "new business proposal" is a proposal for a new business idea or strategy that is generated based on current business data and emotional data.

[0350] A "machine learning algorithm" is an algorithm that learns various patterns from large amounts of data and makes future predictions and classifications. Specifically, it includes neural networks and support vector machines.

[0351] "NLP" stands for natural language processing technology and refers to the technology of understanding and processing human language.

[0352] "User" refers to a member of an organization who uses the system, specifically a business person.

[0353] A "server" refers to a computer system that receives requests from users, performs the necessary processing, operates a database, and returns the results.

[0354] "Terminal" refers to the computer or device used by a user to input and view data.

[0355] The present invention is a system for analyzing and utilizing user emotions with the aim of efficiently managing business handover information and automatically generating new business proposals. Hereinafter, an embodiment of the present invention will be described in detail.

[0356] System configuration

[0357] This system consists of the following components:

[0358] 1. User terminal: A device used for inputting information, searching, and providing feedback. This includes PCs, smartphones, tablets, etc.

[0359] 2. Server: The main computer system that processes user requests, analyzes, stores, and retrieves data, and generates new business proposals.

[0360] 3. Database: A storage system for storing task handover information, feedback, and emotion data. A relational database or NoSQL database is used.

[0361] 4. Emotion Engine: It is an algorithmic software that analyzes user emotions and collects data as numbers and categories.

[0362] 5. Natural Language Processing (NLP): Text analysis technology using Python's NLTK and spaCy.

[0363] 6. Machine learning algorithms: Data analysis and new business proposal generation algorithms using scikit-learn and TensorFlow.

[0364] Basic Operation Procedure

[0365] 1. Enter business handover information

[0366] User: The new person in charge (Employee A) enters the details of the job, procedures, important contact information, and related documents on a terminal such as a PC. At this time, the emotion engine operates and simultaneously collects the user's emotional data.

[0367] Example: Employee A enters "New Employee Orientation Procedures" and records "Anxiety" as the emotion he felt at the time.

[0368] 2. Analysis and storage

[0369] Server: The server analyzes the input task handover information using natural language processing (NLP) technology and stores it in a database as structured data, along with emotional data.

[0370] Example: Using Python's NLTK library to tokenize business content and store it in a database.

[0371] 3. Search and Display

[0372] User: The next person in charge (Employee B) logs in to the server using a terminal and searches for the necessary business handover information.

[0373] Server: The server displays the analyzed task handover information along with emotion data based on the search query.

[0374] Example: When Employee B searches for "new employee orientation procedures," the server displays related information and emotion data for "anxiety."

[0375] 4. Providing Feedback

[0376] User: Employee B reports any questions, areas for improvement, or feelings that arise during work execution via the terminal.

[0377] Server: The server stores this feedback in a database and uses it to improve operations in the future.

[0378] Example: Employee B gives feedback that "orientation is progressing slowly" and records his / her emotion at that time as "irritation."

[0379] 5. Organizing data and updating the knowledge base

[0380] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, eliminating redundancies and duplications. Updates the knowledge base based on the organized data.

[0381] Example: Consolidating duplicate "orientation procedures" information and adding it to the knowledge base as one coherent procedure.

[0382] 6. Automatic categorization and tagging

[0383] Server: Uses automatic classification and tagging functions to assign relevant keywords and categories to business and emotional data.

[0384] Example: Add tags such as "New Employee Training" and "Initial Setup" to "Orientation Procedures."

[0385] 7. Business and Emotional Data Analysis

[0386] Server: Uses machine learning algorithms to analyze the accumulated data and detect success stories, frequently occurring challenges, and associated emotions.

[0387] Example: Using scikit-learn, we will associate "customer service procedures" with emotional data on "satisfaction" as a success story.

[0388] 8. Generate new business proposals

[0389] Server: Based on the analysis results, it combines different business knowledge and emotional data to automatically generate new business proposals.

[0390] Example: Propose a new marketing strategy based on success stories from the marketing department and emotional data on "satisfaction" in customer interactions.

[0391] 9. Notification and Evaluation of Proposals

[0392] Server: Notifies the generated new business proposal to the relevant parties and receives their evaluation.

[0393] User: The parties who receive the proposal evaluate the content and provide feedback along with sentiment data.

[0394] Example: Evaluate the proposal as "useful" and record the emotion as "satisfied."

[0395] 10. Collecting ratings and improving the algorithm

[0396] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[0397] Example: Optimize the next business proposal algorithm based on collected "satisfaction" emotion data.

[0398] Prompt Sentence Examples

[0399] Below is an example of a prompt sentence.

[0400] 1. "Please enter your new employee orientation procedures. Please feel free to write down your thoughts and feelings about the job."

[0401] 2. "Please create a procedure for handing over the work to the next person in charge. Please also include your current feelings and impressions."

[0402] 3. "Please review our proposed new marketing strategy and provide feedback and sentiment data."

[0403] The above is a detailed description of the embodiment of the present invention. By using this system, the process of business handover becomes more efficient and new business proposals are optimized by taking into account the user's feelings.

[0404] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0405] Step 1: Enter business handover information

[0406] User: The new employee (Employee A) enters the job description, procedures, important contact information, and related documents using a dedicated web form or software on a PC or other device. As the information is entered, the emotion engine is activated and the user's emotional data is collected at the same time.

[0407] Input: Job details, procedures, important contacts, related documents, emotional data (e.g., anxiety, satisfaction, etc.)

[0408] Output: Task handover information and emotion data are sent to the server.

[0409] Step 2: Analyze and save the transfer information

[0410] Server: The server performs natural language processing (NLP) on the received task handover information and emotion data using Python's NLTK library and spaCy, and stores the analysis results in a database as structured data.

[0411] Input: Business handover information, emotion data

[0412] Output: The analyzed business information and emotion data are saved in a database as structured data.

[0413] Specific operation: The server first performs tokenization and part-of-speech tagging, then performs context analysis, and then stores the analysis results in a database as JSON format data.

[0414] Step 3: Find and view information

[0415] User: The next person in charge (Employee B) uses a terminal to log in to the server and search for specific task handover information.

[0416] Server: The server receives the user's search query, retrieves relevant business information and emotion data from the database, and displays them.

[0417] Input: User's search query (e.g., "new employee orientation procedures")

[0418] Output: The relevant task handover information and emotion data are displayed.

[0419] Specific operation: The server generates an SQL query based on the user's search query, searches the database, and displays the retrieved data in HTML format.

[0420] Step 4: Provide feedback

[0421] User: Employee B inputs any questions or improvements that arise during the course of work, as well as his / her feelings, through the terminal and reports them to the server.

[0422] Server: Stores the provided feedback and emotion data in a database.

[0423] Input: Feedback content, emotional data (e.g., dissatisfaction, irritation, etc.)

[0424] Output: Feedback and emotion data are stored in a database.

[0425] What happens: The user fills out the feedback form and hits the submit button. The emotion engine is then run again to analyze the emotion, which is then stored in the database along with the feedback.

[0426] Step 5: Cleanse your data and update your knowledge base

[0427] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, removes redundancies and duplicates, and updates the knowledge base.

[0428] Input: Multiple task handover information, feedback, and emotion data

[0429] Output: A cleaned and updated knowledge base

[0430] What it does: The server periodically runs data cleaning scripts to remove redundant and duplicate data. The updated data is imported into the knowledge base software.

[0431] Step 6: Auto-classification and tagging

[0432] Server: The server uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data.

[0433] Input: Organized task handover information, emotional data

[0434] Output: Classified and tagged task handover information, emotion data

[0435] What it does: Classifies data using text classification algorithms (e.g., Naive Bayes or SVM) and automatically tags it with keywords and categories.

[0436] Step 7: Analyze business and sentiment data

[0437] Server: Uses machine learning algorithms (e.g., scikit-learn and TensorFlow) to analyze accumulated business and sentiment data and detect success stories and frequently occurring issues.

[0438] Input: Business handover information, emotion data

[0439] Outputs: Reports, success stories, challenges

[0440] What it does: The server periodically processes batches of data, applies analytics algorithms to the data, and generates reports that are displayed on the dashboard.

[0441] Step 8: Generate new business proposals

[0442] Server: Based on the analysis results, it automatically generates new business proposals by combining different business knowledge and emotional data.

[0443] Input: success stories, challenges, sentiment data

[0444] Output: New business proposal

[0445] How it works: Using a generative AI model (e.g., GPT-3 (registered trademark)), new business proposals are automatically generated. The generated proposals are then internally reviewed and optimized.

[0446] Step 9: Proposal notification and evaluation

[0447] Server: Distributes the generated new business proposals to relevant parties via email or notification systems (e.g., Slack or MICROSOFT (registered trademark) TEAMS (registered trademark)).

[0448] Users: The parties who receive the proposal evaluate the proposal and provide feedback along with sentiment data.

[0449] Input: New business proposal, evaluation feedback, sentiment data

[0450] Output: Evaluation results, feedback

[0451] Specific operation: The server sends emails using the SMTP protocol and sends real-time notifications using the notification system's API. Interested parties submit feedback using the evaluation form.

[0452] Step 10: Collecting ratings and improving the algorithm

[0453] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[0454] Input: Rating feedback, emotion data

[0455] Output: Improved algorithms and knowledge bases

[0456] What it does: The server uses a logging system to collect feedback data, which is used as training data for the machine learning model. It then retrains the model with new data to improve it.

[0457] (Application example 2)

[0458] 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."

[0459] The task handover process in modern factories often suffers from incomplete information transmission and worker emotional stress. Furthermore, the difficulty of properly collecting employee feedback and identifying areas for improvement can hinder improvements in production efficiency. Conventional systems are unable to collect and analyze emotional data in real time, identify worker stress points, and make immediate recommendations based on that data, limiting their ability to improve work efficiency and worker satisfaction. A new method is needed to solve this problem.

[0460] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0461] In this invention, the server includes a means for analyzing task handover information and emotion data and storing them in a database, a means for searching and displaying the analyzed task handover information and emotion data, and a means for collecting and analyzing emotion data in real time using an emotion engine. This not only enables efficient management of task handover information, but also enables real-time suggestions based on emotion data during work. This system reduces emotional stress for workers and improves work efficiency.

[0462] "Business handover information" refers to general information such as business content, procedures, important contacts, and related materials, and refers to detailed business data that will be useful to the next person in charge.

[0463] "Emotional data" refers to information that expresses a user's emotional state using numbers, tags, etc., and is data that analyzes and collects emotions such as stress, happiness, and dissatisfaction while working in real time.

[0464] An "emotion engine" is a technical means for recognizing and analyzing a user's emotions, and refers to a system that collects and analyzes emotional data in real time.

[0465] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and refers to a means of analyzing text data such as business handover information and storing it in a database.

[0466] "Machine learning algorithms" refer to mathematical models and statistical methods that learn patterns and relationships based on large amounts of data and make predictions and suggestions.

[0467] A "knowledge base" is a database that systematically accumulates the knowledge necessary to carry out business, and includes information such as business processes, success stories, and efficient procedures.

[0468] "New business proposals" refer to proposals that automatically generate new business strategies and improvement plans based on current business data and emotional data.

[0469] "Real-time suggestions" are suggestions that are instantly generated and actionable for ongoing tasks or situations, and include specific actions to improve work efficiency and worker satisfaction based on emotional data.

[0470] "Feedback" refers to reactions and opinions, including questions and areas for improvement that arise during the course of work, as well as emotions at the time.

[0471] "Suggestion Algorithm" refers to a mathematical and logical method for generating novel suggestions based on collected data and sentiment data.

[0472] The system of the present invention combines many elements to realize efficient management of business handover information and automatic generation of new business proposals. A specific embodiment of the system is shown below.

[0473] System Configuration

[0474] The system consists of the following main elements:

[0475] A terminal for inputting task handover information and emotion data

[0476] A server that analyzes input information and emotional data

[0477] Database for storing analysis results

[0478] A proposal generation system that uses emotion engines, natural language processing (NLP), and machine learning algorithms

[0479] Hardware and software used

[0480] Hardware: Factory robots, data collection sensors, terminals (PCs, tablets, smartphones)

[0481] Software: EmotionEngine (emotion analysis library), NLPProcessor (natural language processing library), ProposalGenerator (proposal generation mechanism), SQLite (database)

[0482] Program processing explanation

[0483] 1. Enter and save business handover information

[0484] A user uses a terminal to input task handover information and related emotional data, such as details of the tension felt during the initial setup of a new product line.

[0485] The device sends the input information to the server, which then uses the Emotion Engine to analyze the emotional data.Then, the task handover information and emotional data are analyzed by the NLP Processor and stored in a database.

[0486] 2. Searching for and displaying information

[0487] When a user searches for business information, the server retrieves the relevant business information and emotion data from the database and displays them. This allows the user to understand handover information and the emotions involved.

[0488] 3. Collecting and Analyzing Feedback

[0489] Users report any questions or improvements they have while working, as well as their feelings at the time, through their devices. The server collects this feedback and stores it in a database.

[0490] Furthermore, based on machine learning algorithms, the collected feedback data is analyzed and the knowledge base is updated.

[0491] 4. Automatic generation of new business proposals

[0492] The server automatically generates new business proposals using the Proposal Generator based on the accumulated business and emotion data. For example, it proposes reducing worker stress and improving production efficiency by introducing an automated system for the concentration process.

[0493] 5. Notification of proposals and collection of evaluations

[0494] The server notifies the generated new business proposals to the relevant parties and collects their evaluations and comments via their terminals. The collected evaluations are stored in a database and used to improve the proposal algorithm and knowledge base for future projects.

[0495] Specific examples

[0496] The robot uses an emotion engine to detect high stress levels among employees in the enrichment process and uses that data to suggest ways to automate the process.

[0497] Example prompts to input to the generative AI model

[0498] Emotional data: Stress,New proposal: Introducing an automated system for the concentration process is expected to reduce worker stress and improve production efficiency.

[0499] As described above, this system streamlines business handovers, automatically generates new business proposals, and also enables flexible responses that take emotional data into account.

[0500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0501] Step 1:

[0502] The user inputs task handover information and emotional data into the terminal. Specifically, the user enters the task content, procedures, important contact information, and related materials into the input fields of the terminal, and also selects or writes down the emotions felt at the time (e.g., tension, satisfaction, anxiety). The input data is immediately sent to the server.

[0503] Input: Business handover information, emotion data

[0504] Output: Task handover information and emotion data sent to the server

[0505] Step 2:

[0506] The server uses EmotionEngine to analyze the transmitted emotional data. Next, it uses NLPProcessor to analyze the task handover information using natural language processing technology and converts it into meaningful structured data. The server then stores this information in a database.

[0507] Input: Business handover information, emotion data

[0508] Output: Structured business data, emotion data (stored in a database)

[0509] Step 3:

[0510] The user uses the terminal to search for task handover information from the database, and the server retrieves the relevant task information and related emotion data from the database, formats it for display, and transmits it to the terminal.

[0511] Input: Search query

[0512] Output: Search results (business handover information, emotion data)

[0513] Step 4:

[0514] Users report any questions or improvements they have while working, as well as their feelings at the time, through their terminals. The server collects this feedback and stores it in a database.

[0515] Input: Feedback information, emotion data

[0516] Output: Collected feedback and sentiment data (stored in a database)

[0517] Step 5:

[0518] The server periodically analyzes the accumulated feedback and sentiment data, and uses machine learning algorithms to extract success stories, frequent issues, and their associated sentiment data to update the knowledge base.

[0519] Input: Accumulated feedback, emotional data

[0520] Output: Updated knowledge base

[0521] Step 6:

[0522] The server automatically generates new business proposals based on the updated knowledge base and emotion data. The generated proposals are notified to the relevant parties, and the proposal contents are displayed on their terminals.

[0523] Input: Updated knowledge base, emotion data

[0524] Output: New business proposal (displayed on the device)

[0525] Step 7:

[0526] The user reviews the generated suggestions on their device and enters their ratings and comments, along with their emotional data. The server collects this feedback and stores it in a database.

[0527] Input: Proposal ratings, comments, sentiment data

[0528] Output: Collected ratings, comments, and sentiment data (stored in a database)

[0529] Step 8:

[0530] The server analyzes the collected ratings and sentiment data and uses it to refine the proposed algorithm and knowledge base.

[0531] Input: Rating, emotion data

[0532] Output: Improved proposed algorithm, updated knowledge base

[0533] This series of processes ensures efficient business handover and new business proposals are generated taking into account emotional data.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] [Second embodiment]

[0538] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0539] 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.

[0540] 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).

[0541] 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.

[0542] 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.

[0543] 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).

[0544] 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.

[0545] 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.

[0546] 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.

[0547] 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.

[0548] In the smart glasses 214, 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.

[0549] 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."

[0550] The system of the present invention is configured around a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals.

[0551] 1. Business transfer intermediation

[0552] Entering transfer information

[0553] User: A new employee (Employee A) uses a terminal to input task handover information into the server to hand over his or her task to the next employee (Employee B). The input information includes the task content, specific procedures, important contact information, and related materials.

[0554] Analysis and storage of handover information

[0555] Server: Analyzes the received task handover information using natural language processing technology and converts it into structured data. This structured data is then stored in a database.

[0556] Information Access

[0557] User: Employee B, who will take over the work, logs in to the server using a terminal and searches and displays the saved handover information. The server displays the search results in an appropriate format so that Employee B can easily understand them.

[0558] Providing feedback

[0559] User: Enters any questions or suggestions for improvement that arise during work into the server via a terminal. This allows Employee B to carry out their work smoothly.

[0560] 2. Accumulation of business knowledge

[0561] Data organization

[0562] Server: Integrates and organizes the work handover information provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[0563] Knowledge Base Updates

[0564] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[0565] Auto-tagging

[0566] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[0567] 3. Generate new business proposals

[0568] Data analysis

[0569] Server: Uses machine learning algorithms to periodically analyze accumulated operational data, particularly to identify success stories and frequently occurring issues.

[0570] Generate new business proposals

[0571] Server: Based on the analysis results, the server automatically generates new business proposals by combining multiple business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[0572] Proposal notification and evaluation

[0573] Server: Notifies stakeholders of generated new business proposals and distributes them via email and notification systems.

[0574] User: The employee who receives the proposal checks the content on their device and provides feedback by rating and commenting. The rating is then stored in the database by the server.

[0575] Using Feedback

[0576] Server: Analyzes the feedback and ratings received and helps improve the proposed algorithm and knowledge base.

[0577] Specific examples

[0578] 1. Business transfer intermediation

[0579] User: Employee A (HR department staff) enters the "New Employee Orientation Procedures" into the server from a terminal.

[0580] Server: Analyzes using NLP technology and stores procedures and related materials in a database.

[0581] User: Employee B logs in, searches for "New Employee Orientation Procedures," and views it.

[0582] Users: Report any questions or improvements to the server via their devices and provide feedback.

[0583] 2. Accumulation of business knowledge

[0584] Server: The feedback provided by Employee A and Employee B is stored in a database, and the analysis results are added to the knowledge base.

[0585] 3. Generate new business proposals

[0586] Server: Regularly analyze data and propose new marketing strategies that combine "marketing success stories" and "customer abandonment analysis."

[0587] User: The employee who receives the proposal reviews it on their device and provides evaluation comments. The server uses this feedback to improve the proposal algorithm.

[0588] In this way, the system allows the server, terminals, and users to work together at each processing step, improving the efficiency of business handovers and automating new business proposals.

[0589] The processing flow will be explained below.

[0590] Business transfer intermediation

[0591] Step 1: Enter your transfer information

[0592] User: Employee A uses a terminal to enter the task handover information into the server. Specifically, he fills out an input form with the task content, procedures, important contact information, and related documents.

[0593] Step 2: Analyze the handover information

[0594] Server: Analyzes the received task handover information using natural language processing (NLP) technology. As a result of the analysis, the information is recognized as structured data and converted into a format that can be stored in a database.

[0595] Step 3: Save the transfer information

[0596] Server: Stores structured data in a database and organizes it into categories, allowing for consistent access and searching.

[0597] Step 4: Information Access

[0598] User: Employee B, the new employee, logs in to the server using a terminal and searches for the stored handover information. For example, he enters "New Employee Orientation Procedures" in the search field.

[0599] Server: Processes the search query, retrieves the relevant handover information from the database, and displays it on the device.

[0600] Step 5: Provide feedback

[0601] User: Employee B uses a terminal to report any questions or improvements that arise while performing his / her work to the server. Specifically, he / she fills in a feedback form.

[0602] Server: The provided feedback is stored in a database and used to improve future operations.

[0603] Accumulation of business knowledge

[0604] Step 1: Organize your data

[0605] Server: Integrates and organizes handover information and feedback provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[0606] Step 2: Update your knowledge base

[0607] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[0608] Step 3: Auto-tagging

[0609] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[0610] Knowledge integration and new business proposal generation

[0611] Step 1: Data analysis

[0612] Server: Uses machine learning algorithms to analyze accumulated operational data on a regular basis, particularly to identify success stories and frequently occurring issues.

[0613] Step 2: Generate a new business proposal

[0614] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[0615] Step 3: Proposal Notification

[0616] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[0617] Step 4: Collect ratings

[0618] User: The employee who receives the proposal checks the proposal on their device and enters their evaluation and comments as feedback into the server.

[0619] Server: The received feedback and ratings are stored in a database and used to improve the proposed algorithm and knowledge base.

[0620] Specific examples

[0621] 1. Enter and save transfer information

[0622] User: Employee A enters the "New Employee Orientation Procedures" on the terminal.

[0623] Server: Analyzes the information using NLP techniques and stores it in a database.

[0624] 2. Searching for and displaying information

[0625] User: Employee B searches for "New Employee Orientation Procedures" on his device.

[0626] Server: Retrieves relevant information from the database and displays it.

[0627] 3. New business proposal generation and evaluation

[0628] Server: Analyzes business data and generates new marketing strategies as proposals.

[0629] User: Receives suggestions and provides evaluation comments.

[0630] Server: Based on the feedback, improve the next proposed algorithm.

[0631] In this way, the entire system works together efficiently, streamlining business handovers and automating new business proposals.

[0632] Example 1

[0633] 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."

[0634] In modern companies, business handover is a very important process, but managing the information involved is complicated and time-consuming. Furthermore, creating new business proposals requires a lot of time and effort, making it difficult to efficiently utilize past knowledge and success stories. To address this situation, a system is needed that efficiently manages business handover information and automatically utilizes accumulated knowledge to streamline the creation of new business proposals.

[0635] 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.

[0636] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information using natural language processing technology and storing it in a database, means for searching for and displaying the analyzed task handover information using a search engine, means for collecting feedback obtained during the task handover process and storing it in a database, means for organizing and integrating the stored data and updating a knowledge base, means for automatically generating new business proposals using a machine learning algorithm based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, and means for analyzing the evaluations and improving the proposal algorithm and knowledge base. This enables efficient information management of task handovers and automatic generation of new business proposals.

[0637] "Business handover information" refers to information necessary when the current person in charge hands over the business to the next person in charge, and includes the business content, specific procedures, important contact information, related materials, etc.

[0638] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology that performs text analysis, entity extraction from language data, sentiment analysis, etc.

[0639] A "database" is a collection of data that is centrally managed and structured so that it can be easily accessed, searched, and updated.

[0640] A "search engine" is a system for efficiently searching information stored in a database, a technology that allows a search query to be used to quickly find relevant information.

[0641] "Feedback" is information that records questions, areas for improvement, suggestions, etc. that arise during the course of work and returns them to the next person in charge or to the system.

[0642] A "knowledge base" is a collection of knowledge that a system possesses, and is a structured database of information that includes success stories, efficient business procedures, and so on.

[0643] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and make predictions and judgments, and is a technology used to analyze big data and build predictive models.

[0644] A "new business proposal" refers to a new business plan or business idea that is constructed based on existing knowledge and data.

[0645] "Notification" is the act of sending information from the system to relevant parties, and is done via email or internal notification systems.

[0646] "Evaluation" refers to feedback provided by stakeholders on new business proposals received, and includes opinions and comments on the effectiveness of the proposal and areas for improvement.

[0647] The purpose of the system of this invention is to efficiently manage business handover information and automatically generate new business proposals. This system not only inputs, analyzes, saves, searches, and displays business handover information, but also accumulates feedback, updates the knowledge base, and automates the series of processes of generating, notifying, and evaluating new business proposals.

[0648] Enter and save business handover information

[0649] User: The person taking over the work (User A) uses their own terminal to access the server and enter details of the work, specific procedures, important contacts, and related materials. The terminal is a commonly used computing device that connects to the server through a browser or a dedicated application.

[0650] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy" or "BERT") and converted into structured data (such as JSON format). The analyzed data is stored in a database such as "MongoDB." For example, text-formatted business procedures are divided into steps and associated tags are added.

[0651] Search and display business handover information

[0652] User: The new person in charge (User B) logs in to the server from a terminal and sends a query to search for the task handover information. A search engine such as "Elasticsearch" is used for the search. The search results are displayed in an easy-to-understand HTML format. An example of a specific prompt is shown below.

[0653] "What are the new employee orientation procedures?"

[0654] "Find information on the latest marketing strategies."

[0655] Collecting and storing feedback

[0656] Users: If they have any questions or suggestions for improvement while performing their work, they can use the feedback form to send feedback to the server via their terminal. This feedback includes ratings and comments, and is saved in the database.

[0657] Knowledge Base Updates

[0658] Server: Automatically organizes and consolidates feedback and handover information provided by multiple users, eliminating redundant and duplicate information. This process uses data processing libraries such as "pandas." The knowledge base is updated based on the organized data. For example, the steps and key points of successful projects are added to "GraphDB."

[0659] Generate and notify new business proposals

[0660] Server: Based on the accumulated data, a machine learning algorithm (such as Scikit-learn or TensorFlow) is used to automatically generate new business proposals. The generated new business proposals are notified to relevant parties and distributed via email or an internal notification system (such as SendGrid).

[0661] User: The person in charge who receives the proposal checks the content on their device and provides feedback such as ratings and comments. The results are collected by the server and stored in the database.

[0662] Improvement of the proposed algorithm

[0663] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[0664] As described above, the interconnection of servers, terminals, and users enables efficient information management for business handovers and the automatic generation of new business proposals. This system improves the efficiency of business processes and enables the rapid development of new businesses.

[0665] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0666] Step 1:

[0667] Entering business handover information

[0668] User: The person taking over the work (User A) accesses the server from their own terminal and enters the work handover information. The input form displayed on the terminal includes the work content, specific procedures, important contact information, related materials, etc. For example, the user fills in "New employee orientation procedures" in the input form. The entered information is sent to the server as an HTTP request.

[0669] Input: Job description, specific procedures, important contacts, related materials

[0670] Output: Structured task handover information sent to the server

[0671] Step 2:

[0672] Analysis and storage of handover information

[0673] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy"), and the text data is converted into structured data (such as JSON format). During the analysis process, keywords are extracted from the text and intent is understood. The analyzed data is stored in a database such as "MongoDB."

[0674] Input: Unstructured business handover information

[0675] Output: Structured business handover information (JSON format)

[0676] Step 3:

[0677] Information search and display

[0678] User: The next person in charge (User B) logs in to the server from a terminal and enters a query to search for the saved handover information. The server uses Elasticsearch to search and displays the results in HTML format. For example, if User B searches for "New Employee Orientation Procedures," the details are displayed.

[0679] Input: Search query (e.g., "new employee orientation procedures")

[0680] Output: Search results (displayed in HTML format)

[0681] Step 4:

[0682] Providing feedback

[0683] Users: If they have any questions or suggestions for improvement while performing their work, they can use their terminals to enter them into a feedback form and send it to the server. This information can be used to improve work. For example, a user might comment, "There is some material that should be added to the orientation procedures."

[0684] Input: Feedback content (text format)

[0685] Output: Feedback data sent to the server

[0686] Step 5:

[0687] Accumulating and organizing feedback

[0688] Server: The received feedback data is stored in a database. After that, multiple pieces of feedback are consolidated and organized, and redundant and duplicate information is removed. This is done using libraries such as "pandas" to build a consistent database.

[0689] Input: Feedback data (multiple inputs)

[0690] Output: Organized feedback data

[0691] Step 6:

[0692] Knowledge Base Updates

[0693] Server: Automatically updates the knowledge base based on organized data, including best practices and efficient business procedures. The information is stored in a GraphDB and made available as company-wide knowledge.

[0694] Input: Organized feedback data

[0695] Output: Updated knowledge base

[0696] Step 7:

[0697] Generate new business proposals

[0698] Server: Based on the updated knowledge base, the server automatically generates new business proposals using machine learning algorithms (e.g., Scikit-learn and TensorFlow). For example, it proposes new marketing strategies by combining marketing success stories with customer churn analysis.

[0699] Input: Updated Knowledge Base

[0700] Output: New business proposal (text format, etc.)

[0701] Step 8:

[0702] Proposal notification and evaluation

[0703] Server: Notifies the generated new business proposals to the relevant parties and distributes them via email or internal notification systems. The person in charge who receives the proposals can check the contents of the proposals on their terminals and provide evaluation comments as feedback.

[0704] Input: New business proposal

[0705] Output: Evaluation comments for the proposal

[0706] Step 9:

[0707] Improvement of the proposed algorithm

[0708] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[0709] Input: Feedback and Rating Comments

[0710] Output: Improved proposed algorithm and knowledge base

[0711] (Application example 1)

[0712] 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."

[0713] In modern brick-and-mortar store operations, efficient handover of operations and centralized knowledge management are important. However, conventional methods have had problems such as cumbersome collection and management of handover information and inefficient generation of new business proposals. Furthermore, there were also issues with insufficient sharing of feedback between staff and automatic generation of sales promotion plans based on accumulated knowledge.

[0714] 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.

[0715] In this invention, the server includes: means for inputting business handover information; means for analyzing the input business handover information and saving it in a database; means for searching for and displaying the analyzed business handover information; means for collecting feedback obtained during the business handover process and storing it in a database; means for analyzing the stored data and updating a knowledge base; means for automatically generating new business proposals based on the updated knowledge base; means for notifying relevant parties of the generated new business proposals and receiving their evaluations; means for analyzing the evaluations and improving the proposal algorithm and knowledge base; means for managing business information related to store operation and making it accessible via a smartphone during handover; means for building a knowledge base for store operation and automatically generating new sales promotion plans based on feedback; and means for evaluating the generated new proposals and collecting improvements. This improves the efficiency of business handover in physical stores, enables centralized management of the knowledge base, and enables automatic generation of new proposals based on feedback.

[0716] "Business handover information" refers to the information required for an employee to hand over their work to the next person in charge, including specific work content and procedures, important contact information, and related materials.

[0717] A "server" is a computer system for analyzing, storing, and managing data, and plays a role in centrally managing information that users can access.

[0718] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language (language used by humans on a daily basis), and can analyze the meaning of sentences and convert them into structured data.

[0719] A "machine learning algorithm" is an algorithm that finds patterns and rules based on large amounts of data and makes predictions and classifications.

[0720] A "database" is a system for efficiently storing, searching, and managing large amounts of information.

[0721] A "knowledge base" is a database that accumulates information and know-how about a specific field or business, and is used to improve business efficiency and automate operations.

[0722] A "new business proposal" is a new idea or plan for improving operations or business processes based on accumulated data and feedback.

[0723] "Feedback" refers to information that reports opinions and areas for improvement obtained during the course of business, and is used to improve the system and generate new proposals.

[0724] A "smartphone" is a mobile phone terminal equipped with advanced computing power and communication functions, and is capable of running a variety of applications.

[0725] "Store operations" refers to all operations related to running a store, such as managing a physical store, product display, inventory management, and sales promotion.

[0726] "Building a knowledge base" means accumulating and systematically storing business-related knowledge and know-how, and using that knowledge to make business improvements and proposals.

[0727] This invention is a system for efficiently managing business handover information in a physical store, building a knowledge base related to store management, and automatically generating new sales promotion plans based on feedback. This system is implemented using a server and user terminals (e.g., smartphones).

[0728] System Program

[0729] The system has a program with the following main components:

[0730] 1. A means of entering business handover information.

[0731] 2. A means of analyzing the entered business handover information and storing it in a database.

[0732] 3. A means for searching and displaying the analyzed business handover information.

[0733] 4. A means of collecting feedback obtained during the business handover process and storing it in a database.

[0734] 5. A means of analyzing accumulated data and updating the knowledge base.

[0735] 6. A means of automatically generating new business proposals based on the updated knowledge base.

[0736] 7. A means of informing stakeholders of generated new business proposals and receiving their evaluation.

[0737] 8. A means of analyzing the evaluation and improving the proposed algorithm and knowledge base.

[0738] 9. A means of managing business information related to store operations and making it accessible via smartphone when taking over.

[0739] 10. A means of building a knowledge base for store operations and automatically generating new promotional plans based on feedback.

[0740] 11. A means of evaluating new proposals generated and collecting suggestions for improvement.

[0741] Explanation of program processing

[0742] The server receives the task handover information entered by the user (store manager or staff member) using their smartphone. The server analyzes this information using natural language processing technology (for example, Python's NLP library), converts it into structured data, and stores it in a database. The user can then use their smartphone to search for and view the stored handover information.

[0743] Feedback is collected via smartphones, and when users enter questions or suggestions for improvement they have while performing their work, the server stores them in a database. The server periodically analyzes the accumulated feedback and data and updates the knowledge base. Machine learning algorithms (e.g., scikit-learn) are used to automatically generate new sales promotion plans and business improvement proposals.

[0744] The generated new business proposals are notified to the user, who can provide ratings and comments via their smartphone. The server analyzes this feedback and uses it to improve the proposal algorithm and knowledge base.

[0745] Specific examples

[0746] For example, a store manager can input a new inventory management method on their smartphone, and when staff review it, they can provide feedback such as "the order of products is unclear," allowing the system to automatically suggest new sales based on inventory shortages.

[0747] Examples of prompts include:

[0748] The new store manager has entered the information on inventory management and sales promotions. At the same time, the staff has provided feedback on the product arrangement. Based on this, please propose a new sales promotion plan.

[0749] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0750] Step 1:

[0751] The user inputs task handover information using a smartphone. The input information includes the task content, procedures, important contact information, and related materials. The input data is sent to the server.

[0752] Step 2:

[0753] The server analyzes the received task handover information using natural language processing technology (for example, a Python NLP library). The analyzed data is converted into structured data and stored in a database. The input is raw text data, and the output is structured data.

[0754] Step 3:

[0755] The user accesses the server using a smartphone and searches for the stored handover information. The server processes the search query and displays the appropriate handover information on the screen. The input is the search query, and the output is the formatted handover information.

[0756] Step 4:

[0757] Users can input any questions or improvements they have while working on their smartphones and send them as feedback to the server, which then stores the feedback in a database. The input is raw text feedback data, and the output is the feedback data stored in the database.

[0758] Step 5:

[0759] The server periodically analyzes the accumulated feedback and task handover information and updates the knowledge base. The analysis includes data cleansing and statistical techniques. The input is the accumulated data, and the output is an updated knowledge base.

[0760] Step 6:

[0761] The server automatically generates new business proposals using a machine learning algorithm (e.g., scikit-learn) based on the updated knowledge base. The input is the updated knowledge base, and the output is the new business proposal.

[0762] Step 7:

[0763] The generated new business proposal is notified to the relevant parties via smartphone or email. The user reviews the proposal and provides feedback such as ratings and comments. The input is the new business proposal, and the output is the ratings and comments.

[0764] Step 8:

[0765] The server analyzes the received ratings and comments and improves the proposed algorithm and knowledge base. The input is the ratings and comments, and the output is the improved algorithm and knowledge base.

[0766] 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.

[0767] The system of the present invention is composed mainly of a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals, and is further combined with an emotion engine that recognizes and analyzes user emotions.

[0768] 1. Business transfer intermediation

[0769] Entering transfer information

[0770] User: A new person in charge (Employee A) uses a terminal to input task handover information into the server to hand over the task to the next person in charge (Employee B). The input information includes the task content, procedures, important contact information, and related materials. During input, the emotion engine also analyzes the user's emotions and collects emotional data about the task.

[0771] Analysis and storage of handover information

[0772] Server: Along with the emotional data analyzed by the emotion engine, the task handover information is analyzed using natural language processing (NLP) technology and stored in a database as structured data.

[0773] Information Access

[0774] User: Employee B, the new person in charge, logs in to the server using a terminal and searches for the saved handover information. The server provides search results including emotional data, allowing Employee B to understand the handover information taking emotional aspects into account.

[0775] Providing feedback

[0776] User: Employee B reports any questions or areas for improvement that arise during the course of work, as well as his or her feelings at the time, to the server via his or her terminal.

[0777] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[0778] 2. Accumulation of business knowledge

[0779] Data organization

[0780] Server: Integrates and organizes task handover information, feedback, and sentiment data provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[0781] Knowledge Base Updates

[0782] Server: Automatically updates the knowledge base based on the organized data and sentiment data. For example, it adds sentiment data related to success stories and efficient business procedures to the knowledge base.

[0783] Auto-tagging

[0784] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[0785] Knowledge integration and new business proposal generation

[0786] Data analysis

[0787] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[0788] Generate new business proposals

[0789] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department" with "customer abandonment analysis" and related emotional data.

[0790] Proposal notification and evaluation

[0791] Server: Distributes generated new business proposals to stakeholders via email and notification systems. Uses an emotion engine to recognize users' reactions and ratings.

[0792] Collecting ratings

[0793] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[0794] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[0795] Specific examples

[0796] 1. Enter and save transfer information

[0797] User: Employee A enters the "New Employee Orientation Procedure" into the terminal, and their emotions at the time are also collected.

[0798] Server: Analyzes business information and emotion data using NLP technology and stores it in a database.

[0799] 2. Searching for and displaying information

[0800] User: Employee B searches for "New Employee Orientation Procedures."

[0801] Server: Retrieves related information along with emotion data from the database and displays it.

[0802] 3. New business proposal generation and evaluation

[0803] Server: Analyzes business and sentiment data and generates new marketing strategy proposals.

[0804] User: Receives suggestions and provides evaluation comments and sentiment data.

[0805] Server: Based on the feedback, improve the next proposed algorithm.

[0806] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[0807] The processing flow will be explained below.

[0808] Business transfer intermediation

[0809] Step 1: Enter your transfer information

[0810] User: Employee A uses a terminal to input task handover information into the server. The information to be input includes the task content, procedures, important contacts, and related materials. As the information is being input, the emotion engine analyzes the user's emotions in real time and collects emotional data.

[0811] Step 2: Analyze the handover information

[0812] Server: Analyzes the received task handover information and emotional data using natural language processing (NLP) technology. The task information is recognized as structured data and converted into a format that can be stored in a database together with the emotional data.

[0813] Step 3: Save handover information and emotion data

[0814] Server: Structured task handover information and emotion data are stored in a database and organized by category, allowing for consistent access and retrieval.

[0815] Step 4: Information Access

[0816] User: Employee B, the new employee, logs in to the server using a terminal and searches for relevant handover information, for example, "New Employee Orientation Procedures."

[0817] Server: Processes the search query, retrieves the relevant handover information and emotion data from the database, and displays them on the device in an appropriate format.

[0818] Step 5: Provide feedback

[0819] User: Employee B uses a terminal to report any questions or improvements that arise during work to the server. The emotion engine also analyzes the emotions expressed at the time.

[0820] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[0821] Accumulation of business knowledge

[0822] Step 1: Organize your data

[0823] Server: Integrates and organizes handover information, feedback, and sentiment data provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[0824] Step 2: Update your knowledge base

[0825] Server: Automatically updates the knowledge base based on the organized data. For example, it adds best practices, efficient business procedures, and related emotional data to the knowledge base.

[0826] Step 3: Auto-tagging

[0827] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[0828] Knowledge integration and new business proposal generation

[0829] Step 1: Data analysis

[0830] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[0831] Step 2: Generate a new business proposal

[0832] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department," "customer abandonment analysis," and related emotional data.

[0833] Step 3: Proposal Notification

[0834] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[0835] Step 4: Collect ratings

[0836] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[0837] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[0838] Specific examples

[0839] 1. Enter and save transfer information

[0840] User: Employee A enters the "New Employee Orientation Procedure" into the terminal. At that time, the emotion engine analyzes Employee A's emotions and captures them as data.

[0841] Server: Uses NLP technology to analyze business information and emotion data and store them in a database.

[0842] 2. Searching for and displaying information

[0843] User: Employee B searches for "New Employee Orientation Procedures."

[0844] Server: Retrieves related information along with emotion data from the database and displays it.

[0845] 3. New business proposal generation and evaluation

[0846] Server: Analyzes business and sentiment data and generates new marketing strategies as proposals.

[0847] User: Receives suggestions and provides evaluation comments and sentiment data.

[0848] Server: Based on the feedback, improve the next proposed algorithm.

[0849] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[0850] Example 2

[0851] 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."

[0852] Conventional business handover systems have basic functions such as inputting, analyzing, and saving business information, but they lack consideration for user emotions. This can lead to a lack of understanding of the handover information and inappropriate new business proposals. Furthermore, it is necessary to utilize emotion data to generate more effective and appropriate new business proposals.

[0853] 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.

[0854] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information and saving it in a database, means for searching for and displaying the analyzed task handover information, means for collecting feedback obtained during the task handover process and storing it in a database, means for analyzing the stored data and updating a knowledge base, means for automatically generating new business proposals based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, means for analyzing the evaluations and improving the proposal algorithm and the knowledge base, means for analyzing user emotions and collecting task handover information including emotion data, means for assisting in understanding the task handover information based on the emotion data, and means for optimizing the new business proposals based on the emotion data. This enables task handover and new business proposals that take user emotions into consideration.

[0855] "Business handover information" refers to information including business content, procedures, important contact information, and related materials, and refers to all information necessary for the handover of business between personnel.

[0856] "Natural language processing technology" is a technology that analyzes text data written in natural language and understands and processes its meaning and structure. Specifically, it includes tokenization, part-of-speech tagging, grammatical analysis, etc.

[0857] A "database" refers to a collection of data that is structured so that the stored information can be efficiently managed and searched, and includes relational databases and NoSQL databases.

[0858] "Emotional energy" refers to software and algorithms that analyze a user's emotional state and record it as a number or category.

[0859] "Emotional data" refers to data that quantifies or categorizes a user's emotional state and is collected using contextual analysis and facial recognition technology.

[0860] A "knowledge base" is a database that systematically compiles important information within an organization, such as business procedures and success stories.

[0861] A "new business proposal" is a proposal for a new business idea or strategy that is generated based on current business data and emotional data.

[0862] A "machine learning algorithm" is an algorithm that learns various patterns from large amounts of data and makes future predictions and classifications. Specifically, it includes neural networks and support vector machines.

[0863] "NLP" stands for natural language processing technology and refers to the technology of understanding and processing human language.

[0864] "User" refers to a member of an organization who uses the system, specifically a business person.

[0865] A "server" refers to a computer system that receives requests from users, performs the necessary processing, operates a database, and returns the results.

[0866] "Terminal" refers to the computer or device used by a user to input and view data.

[0867] The present invention is a system for analyzing and utilizing user emotions with the aim of efficiently managing business handover information and automatically generating new business proposals. Hereinafter, an embodiment of the present invention will be described in detail.

[0868] System configuration

[0869] This system consists of the following components:

[0870] 1. User terminal: A device used for inputting information, searching, and providing feedback. This includes PCs, smartphones, tablets, etc.

[0871] 2. Server: The main computer system that processes user requests, analyzes, stores, and retrieves data, and generates new business proposals.

[0872] 3. Database: A storage system for storing task handover information, feedback, and emotion data. A relational database or NoSQL database is used.

[0873] 4. Emotion Engine: It is an algorithmic software that analyzes user emotions and collects data as numbers and categories.

[0874] 5. Natural Language Processing (NLP): Text analysis technology using Python's NLTK and spaCy.

[0875] 6. Machine learning algorithms: Data analysis and new business proposal generation algorithms using scikit-learn and TensorFlow.

[0876] Basic Operation Procedure

[0877] 1. Enter business handover information

[0878] User: The new person in charge (Employee A) enters the details of the job, procedures, important contact information, and related documents on a terminal such as a PC. At this time, the emotion engine operates and simultaneously collects the user's emotional data.

[0879] Example: Employee A enters "New Employee Orientation Procedures" and records "Anxiety" as the emotion he felt at the time.

[0880] 2. Analysis and storage

[0881] Server: The server analyzes the input task handover information using natural language processing (NLP) technology and stores it in a database as structured data, along with emotional data.

[0882] Example: Using Python's NLTK library to tokenize business content and store it in a database.

[0883] 3. Search and Display

[0884] User: The next person in charge (Employee B) logs in to the server using a terminal and searches for the necessary business handover information.

[0885] Server: The server displays the analyzed task handover information along with emotion data based on the search query.

[0886] Example: When Employee B searches for "new employee orientation procedures," the server displays related information and emotion data for "anxiety."

[0887] 4. Providing Feedback

[0888] User: Employee B reports any questions, areas for improvement, or feelings that arise during work execution via the terminal.

[0889] Server: The server stores this feedback in a database and uses it to improve operations in the future.

[0890] Example: Employee B gives feedback that "orientation is progressing slowly" and records his / her emotion at that time as "irritation."

[0891] 5. Organizing data and updating the knowledge base

[0892] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, eliminating redundancies and duplications. Updates the knowledge base based on the organized data.

[0893] Example: Consolidating duplicate "orientation procedures" information and adding it to the knowledge base as one coherent procedure.

[0894] 6. Automatic categorization and tagging

[0895] Server: Uses automatic classification and tagging functions to assign relevant keywords and categories to business and emotional data.

[0896] Example: Add tags such as "New Employee Training" and "Initial Setup" to "Orientation Procedures."

[0897] 7. Business and Emotional Data Analysis

[0898] Server: Uses machine learning algorithms to analyze the accumulated data and detect success stories, frequently occurring challenges, and associated emotions.

[0899] Example: Using scikit-learn, we will associate "customer service procedures" with emotional data on "satisfaction" as a success story.

[0900] 8. Generate new business proposals

[0901] Server: Based on the analysis results, it combines different business knowledge and emotional data to automatically generate new business proposals.

[0902] Example: Propose a new marketing strategy based on success stories from the marketing department and emotional data on "satisfaction" in customer interactions.

[0903] 9. Notification and Evaluation of Proposals

[0904] Server: Notifies the generated new business proposal to the relevant parties and receives their evaluation.

[0905] User: The parties who receive the proposal evaluate the content and provide feedback along with sentiment data.

[0906] Example: Evaluate the proposal as "useful" and record the emotion as "satisfied."

[0907] 10. Collecting ratings and improving the algorithm

[0908] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[0909] Example: Optimize the next business proposal algorithm based on collected "satisfaction" emotion data.

[0910] Prompt Sentence Examples

[0911] Below is an example of a prompt sentence.

[0912] 1. "Please enter your new employee orientation procedures. Please feel free to write down your thoughts and feelings about the job."

[0913] 2. "Please create a procedure for handing over the work to the next person in charge. Please also include your current feelings and impressions."

[0914] 3. "Please review our proposed new marketing strategy and provide feedback and sentiment data."

[0915] The above is a detailed description of the embodiment of the present invention. By using this system, the process of business handover becomes more efficient and new business proposals are optimized by taking into account the user's feelings.

[0916] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0917] Step 1: Enter business handover information

[0918] User: The new employee (Employee A) enters the job description, procedures, important contact information, and related documents using a dedicated web form or software on a PC or other device. As the information is entered, the emotion engine is activated and the user's emotional data is collected at the same time.

[0919] Input: Job details, procedures, important contacts, related documents, emotional data (e.g., anxiety, satisfaction, etc.)

[0920] Output: Task handover information and emotion data are sent to the server.

[0921] Step 2: Analyze and save the transfer information

[0922] Server: The server performs natural language processing (NLP) on the received task handover information and emotion data using Python's NLTK library and spaCy, and stores the analysis results in a database as structured data.

[0923] Input: Business handover information, emotion data

[0924] Output: The analyzed business information and emotion data are saved in a database as structured data.

[0925] Specific operation: The server first performs tokenization and part-of-speech tagging, then performs context analysis, and then stores the analysis results in a database as JSON format data.

[0926] Step 3: Find and view information

[0927] User: The next person in charge (Employee B) uses a terminal to log in to the server and search for specific task handover information.

[0928] Server: The server receives the user's search query, retrieves relevant business information and emotion data from the database, and displays them.

[0929] Input: User's search query (e.g., "new employee orientation procedures")

[0930] Output: The relevant task handover information and emotion data are displayed.

[0931] Specific operation: The server generates an SQL query based on the user's search query, searches the database, and displays the retrieved data in HTML format.

[0932] Step 4: Provide feedback

[0933] User: Employee B inputs any questions or improvements that arise during the course of work, as well as his / her feelings, through the terminal and reports them to the server.

[0934] Server: Stores the provided feedback and emotion data in a database.

[0935] Input: Feedback content, emotional data (e.g., dissatisfaction, irritation, etc.)

[0936] Output: Feedback and emotion data are stored in a database.

[0937] What happens: The user fills out the feedback form and hits the submit button. The emotion engine is then run again to analyze the emotion, which is then stored in the database along with the feedback.

[0938] Step 5: Cleanse your data and update your knowledge base

[0939] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, removes redundancies and duplicates, and updates the knowledge base.

[0940] Input: Multiple task handover information, feedback, and emotion data

[0941] Output: A cleaned and updated knowledge base

[0942] What it does: The server periodically runs data cleaning scripts to remove redundant and duplicate data. The updated data is imported into the knowledge base software.

[0943] Step 6: Auto-classification and tagging

[0944] Server: The server uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data.

[0945] Input: Organized task handover information, emotional data

[0946] Output: Classified and tagged task handover information, emotion data

[0947] What it does: Classifies data using text classification algorithms (e.g., Naive Bayes or SVM) and automatically tags it with keywords and categories.

[0948] Step 7: Analyze business and sentiment data

[0949] Server: Uses machine learning algorithms (e.g., scikit-learn and TensorFlow) to analyze accumulated business and sentiment data and detect success stories and frequently occurring issues.

[0950] Input: Business handover information, emotion data

[0951] Outputs: Reports, success stories, challenges

[0952] What it does: The server periodically processes batches of data, applies analytics algorithms to the data, and generates reports that are displayed on the dashboard.

[0953] Step 8: Generate new business proposals

[0954] Server: Based on the analysis results, it automatically generates new business proposals by combining different business knowledge and emotional data.

[0955] Input: success stories, challenges, sentiment data

[0956] Output: New business proposal

[0957] How it works: Using a generative AI model (e.g., GPT-3), new business proposals are automatically generated, and the generated proposals are then internally reviewed and optimized.

[0958] Step 9: Proposal notification and evaluation

[0959] Server: Distributes the generated new business proposals to relevant parties via email or notification systems (e.g., Slack or Microsoft Teams).

[0960] Users: The parties who receive the proposal evaluate the proposal and provide feedback along with sentiment data.

[0961] Input: New business proposal, evaluation feedback, sentiment data

[0962] Output: Evaluation results, feedback

[0963] Specific operation: The server sends emails using the SMTP protocol and sends real-time notifications using the notification system's API. Interested parties submit feedback using the evaluation form.

[0964] Step 10: Collecting ratings and improving the algorithm

[0965] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[0966] Input: Rating feedback, emotion data

[0967] Output: Improved algorithms and knowledge bases

[0968] What it does: The server uses a logging system to collect feedback data, which is used as training data for the machine learning model. It then retrains the model with new data to improve it.

[0969] (Application example 2)

[0970] 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."

[0971] The task handover process in modern factories often suffers from incomplete information transmission and worker emotional stress. Furthermore, the difficulty of properly collecting employee feedback and identifying areas for improvement can hinder improvements in production efficiency. Conventional systems are unable to collect and analyze emotional data in real time, identify worker stress points, and make immediate recommendations based on that data, limiting their ability to improve work efficiency and worker satisfaction. A new method is needed to solve this problem.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0973] In this invention, the server includes a means for analyzing task handover information and emotion data and storing them in a database, a means for searching and displaying the analyzed task handover information and emotion data, and a means for collecting and analyzing emotion data in real time using an emotion engine. This not only enables efficient management of task handover information, but also enables real-time suggestions based on emotion data during work. This system reduces emotional stress for workers and improves work efficiency.

[0974] "Business handover information" refers to general information such as business content, procedures, important contacts, and related materials, and refers to detailed business data that will be useful to the next person in charge.

[0975] "Emotional data" refers to information that expresses a user's emotional state using numbers, tags, etc., and is data that analyzes and collects emotions such as stress, happiness, and dissatisfaction while working in real time.

[0976] An "emotion engine" is a technical means for recognizing and analyzing a user's emotions, and refers to a system that collects and analyzes emotional data in real time.

[0977] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and refers to a means of analyzing text data such as business handover information and storing it in a database.

[0978] "Machine learning algorithms" refer to mathematical models and statistical methods that learn patterns and relationships based on large amounts of data and make predictions and suggestions.

[0979] A "knowledge base" is a database that systematically accumulates the knowledge necessary to carry out business, and includes information such as business processes, success stories, and efficient procedures.

[0980] "New business proposals" refer to proposals that automatically generate new business strategies and improvement plans based on current business data and emotional data.

[0981] "Real-time suggestions" are suggestions that are instantly generated and actionable for ongoing tasks or situations, and include specific actions to improve work efficiency and worker satisfaction based on emotional data.

[0982] "Feedback" refers to reactions and opinions, including questions and areas for improvement that arise during the course of work, as well as emotions at the time.

[0983] "Suggestion Algorithm" refers to a mathematical and logical method for generating novel suggestions based on collected data and sentiment data.

[0984] The system of the present invention combines many elements to realize efficient management of business handover information and automatic generation of new business proposals. A specific embodiment of the system is shown below.

[0985] System Configuration

[0986] The system consists of the following main elements:

[0987] A terminal for inputting task handover information and emotion data

[0988] A server that analyzes input information and emotional data

[0989] Database for storing analysis results

[0990] A proposal generation system that uses emotion engines, natural language processing (NLP), and machine learning algorithms

[0991] Hardware and software used

[0992] Hardware: Factory robots, data collection sensors, terminals (PCs, tablets, smartphones)

[0993] Software: EmotionEngine (emotion analysis library), NLPProcessor (natural language processing library), ProposalGenerator (proposal generation mechanism), SQLite (database)

[0994] Program processing explanation

[0995] 1. Enter and save business handover information

[0996] A user uses a terminal to input task handover information and related emotional data, such as details of the tension felt during the initial setup of a new product line.

[0997] The device sends the input information to the server, which then uses the Emotion Engine to analyze the emotional data.Then, the task handover information and emotional data are analyzed by the NLP Processor and stored in a database.

[0998] 2. Searching for and displaying information

[0999] When a user searches for business information, the server retrieves the relevant business information and emotion data from the database and displays them. This allows the user to understand handover information and the emotions involved.

[1000] 3. Collecting and Analyzing Feedback

[1001] Users report any questions or improvements they have while working, as well as their feelings at the time, through their devices. The server collects this feedback and stores it in a database.

[1002] Furthermore, based on machine learning algorithms, the collected feedback data is analyzed and the knowledge base is updated.

[1003] 4. Automatic generation of new business proposals

[1004] The server automatically generates new business proposals using the Proposal Generator based on the accumulated business and emotion data. For example, it proposes reducing worker stress and improving production efficiency by introducing an automated system for the concentration process.

[1005] 5. Notification of proposals and collection of evaluations

[1006] The server notifies the generated new business proposals to the relevant parties and collects their evaluations and comments via their terminals. The collected evaluations are stored in a database and used to improve the proposal algorithm and knowledge base for future projects.

[1007] Specific examples

[1008] The robot uses an emotion engine to detect high stress levels among employees in the enrichment process and uses that data to suggest ways to automate the process.

[1009] Example prompts to input to the generative AI model

[1010] Emotional data: Stress,New proposal: Introducing an automated system for the concentration process is expected to reduce worker stress and improve production efficiency.

[1011] As described above, this system streamlines business handovers, automatically generates new business proposals, and also enables flexible responses that take emotional data into account.

[1012] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1013] Step 1:

[1014] The user inputs task handover information and emotional data into the terminal. Specifically, the user enters the task content, procedures, important contact information, and related materials into the input fields of the terminal, and also selects or writes down the emotions felt at the time (e.g., tension, satisfaction, anxiety). The input data is immediately sent to the server.

[1015] Input: Business handover information, emotion data

[1016] Output: Task handover information and emotion data sent to the server

[1017] Step 2:

[1018] The server uses EmotionEngine to analyze the transmitted emotional data. Next, it uses NLPProcessor to analyze the task handover information using natural language processing technology and converts it into meaningful structured data. The server then stores this information in a database.

[1019] Input: Business handover information, emotion data

[1020] Output: Structured business data, emotion data (stored in a database)

[1021] Step 3:

[1022] The user uses the terminal to search for task handover information from the database, and the server retrieves the relevant task information and related emotion data from the database, formats it for display, and transmits it to the terminal.

[1023] Input: Search query

[1024] Output: Search results (business handover information, emotion data)

[1025] Step 4:

[1026] Users report any questions or improvements they have while working, as well as their feelings at the time, through their terminals. The server collects this feedback and stores it in a database.

[1027] Input: Feedback information, emotion data

[1028] Output: Collected feedback and sentiment data (stored in a database)

[1029] Step 5:

[1030] The server periodically analyzes the accumulated feedback and sentiment data, and uses machine learning algorithms to extract success stories, frequent issues, and their associated sentiment data to update the knowledge base.

[1031] Input: Accumulated feedback, emotional data

[1032] Output: Updated knowledge base

[1033] Step 6:

[1034] The server automatically generates new business proposals based on the updated knowledge base and emotion data. The generated proposals are notified to the relevant parties, and the proposal contents are displayed on their terminals.

[1035] Input: Updated knowledge base, emotion data

[1036] Output: New business proposal (displayed on the device)

[1037] Step 7:

[1038] The user reviews the generated suggestions on their device and enters their ratings and comments, along with their emotional data. The server collects this feedback and stores it in a database.

[1039] Input: Proposal ratings, comments, sentiment data

[1040] Output: Collected ratings, comments, and sentiment data (stored in a database)

[1041] Step 8:

[1042] The server analyzes the collected ratings and sentiment data and uses it to refine the proposed algorithm and knowledge base.

[1043] Input: Rating, emotion data

[1044] Output: Improved proposed algorithm, updated knowledge base

[1045] This series of processes ensures efficient business handover and new business proposals are generated taking into account emotional data.

[1046] 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.

[1047] 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.

[1048] 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.

[1049] [Third embodiment]

[1050] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1051] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1052] 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).

[1053] 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.

[1054] 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.

[1055] 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).

[1056] 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.

[1057] 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.

[1058] 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.

[1059] 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.

[1060] 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.

[1061] 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."

[1062] The system of the present invention is configured around a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals.

[1063] 1. Business transfer intermediation

[1064] Entering transfer information

[1065] User: A new employee (Employee A) uses a terminal to input task handover information into the server to hand over his or her task to the next employee (Employee B). The input information includes the task content, specific procedures, important contact information, and related materials.

[1066] Analysis and storage of handover information

[1067] Server: Analyzes the received task handover information using natural language processing technology and converts it into structured data. This structured data is then stored in a database.

[1068] Information Access

[1069] User: Employee B, who will take over the work, logs in to the server using a terminal and searches and displays the saved handover information. The server displays the search results in an appropriate format so that Employee B can easily understand them.

[1070] Providing feedback

[1071] User: Enters any questions or suggestions for improvement that arise during work into the server via a terminal. This allows Employee B to carry out their work smoothly.

[1072] 2. Accumulation of business knowledge

[1073] Data organization

[1074] Server: Integrates and organizes the work handover information provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[1075] Knowledge Base Updates

[1076] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[1077] Auto-tagging

[1078] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[1079] 3. Generate new business proposals

[1080] Data analysis

[1081] Server: Uses machine learning algorithms to periodically analyze accumulated operational data, particularly to identify success stories and frequently occurring issues.

[1082] Generate new business proposals

[1083] Server: Based on the analysis results, the server automatically generates new business proposals by combining multiple business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[1084] Proposal notification and evaluation

[1085] Server: Notifies stakeholders of generated new business proposals and distributes them via email and notification systems.

[1086] User: The employee who receives the proposal checks the content on their device and provides feedback by rating and commenting. The rating is then stored in the database by the server.

[1087] Using Feedback

[1088] Server: Analyzes the feedback and ratings received and helps improve the proposed algorithm and knowledge base.

[1089] Specific examples

[1090] 1. Business transfer intermediation

[1091] User: Employee A (HR department staff) enters the "New Employee Orientation Procedures" into the server from a terminal.

[1092] Server: Analyzes using NLP technology and stores procedures and related materials in a database.

[1093] User: Employee B logs in, searches for "New Employee Orientation Procedures," and views it.

[1094] Users: Report any questions or improvements to the server via their devices and provide feedback.

[1095] 2. Accumulation of business knowledge

[1096] Server: The feedback provided by Employee A and Employee B is stored in a database, and the analysis results are added to the knowledge base.

[1097] 3. Generate new business proposals

[1098] Server: Regularly analyze data and propose new marketing strategies that combine "marketing success stories" and "customer abandonment analysis."

[1099] User: The employee who receives the proposal reviews it on their device and provides evaluation comments. The server uses this feedback to improve the proposal algorithm.

[1100] In this way, the system allows the server, terminals, and users to work together at each processing step, improving the efficiency of business handovers and automating new business proposals.

[1101] The processing flow will be explained below.

[1102] Business transfer intermediation

[1103] Step 1: Enter your transfer information

[1104] User: Employee A uses a terminal to enter the task handover information into the server. Specifically, he fills out an input form with the task content, procedures, important contact information, and related documents.

[1105] Step 2: Analyze the handover information

[1106] Server: Analyzes the received task handover information using natural language processing (NLP) technology. As a result of the analysis, the information is recognized as structured data and converted into a format that can be stored in a database.

[1107] Step 3: Save the transfer information

[1108] Server: Stores structured data in a database and organizes it into categories, allowing for consistent access and searching.

[1109] Step 4: Information Access

[1110] User: Employee B, the new employee, logs in to the server using a terminal and searches for the stored handover information. For example, he enters "New Employee Orientation Procedures" in the search field.

[1111] Server: Processes the search query, retrieves the relevant handover information from the database, and displays it on the device.

[1112] Step 5: Provide feedback

[1113] User: Employee B uses a terminal to report any questions or improvements that arise while performing his / her work to the server. Specifically, he / she fills in a feedback form.

[1114] Server: The provided feedback is stored in a database and used to improve future operations.

[1115] Accumulation of business knowledge

[1116] Step 1: Organize your data

[1117] Server: Integrates and organizes handover information and feedback provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[1118] Step 2: Update your knowledge base

[1119] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[1120] Step 3: Auto-tagging

[1121] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[1122] Knowledge integration and new business proposal generation

[1123] Step 1: Data analysis

[1124] Server: Uses machine learning algorithms to analyze accumulated operational data on a regular basis, particularly to identify success stories and frequently occurring issues.

[1125] Step 2: Generate a new business proposal

[1126] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[1127] Step 3: Proposal Notification

[1128] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[1129] Step 4: Collect ratings

[1130] User: The employee who receives the proposal checks the proposal on their device and enters their evaluation and comments as feedback into the server.

[1131] Server: The received feedback and ratings are stored in a database and used to improve the proposed algorithm and knowledge base.

[1132] Specific examples

[1133] 1. Enter and save transfer information

[1134] User: Employee A enters the "New Employee Orientation Procedures" on the terminal.

[1135] Server: Analyzes the information using NLP techniques and stores it in a database.

[1136] 2. Searching for and displaying information

[1137] User: Employee B searches for "New Employee Orientation Procedures" on his device.

[1138] Server: Retrieves relevant information from the database and displays it.

[1139] 3. New business proposal generation and evaluation

[1140] Server: Analyzes business data and generates new marketing strategies as proposals.

[1141] User: Receives suggestions and provides evaluation comments.

[1142] Server: Based on the feedback, improve the next proposed algorithm.

[1143] In this way, the entire system works together efficiently, streamlining business handovers and automating new business proposals.

[1144] Example 1

[1145] 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."

[1146] In modern companies, business handover is a very important process, but managing the information involved is complicated and time-consuming. Furthermore, creating new business proposals requires a lot of time and effort, making it difficult to efficiently utilize past knowledge and success stories. To address this situation, a system is needed that efficiently manages business handover information and automatically utilizes accumulated knowledge to streamline the creation of new business proposals.

[1147] 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.

[1148] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information using natural language processing technology and storing it in a database, means for searching for and displaying the analyzed task handover information using a search engine, means for collecting feedback obtained during the task handover process and storing it in a database, means for organizing and integrating the stored data and updating a knowledge base, means for automatically generating new business proposals using a machine learning algorithm based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, and means for analyzing the evaluations and improving the proposal algorithm and knowledge base. This enables efficient information management of task handovers and automatic generation of new business proposals.

[1149] "Business handover information" refers to information necessary when the current person in charge hands over the business to the next person in charge, and includes the business content, specific procedures, important contact information, related materials, etc.

[1150] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology that performs text analysis, entity extraction from language data, sentiment analysis, etc.

[1151] A "database" is a collection of data that is centrally managed and structured so that it can be easily accessed, searched, and updated.

[1152] A "search engine" is a system for efficiently searching information stored in a database, a technology that allows a search query to be used to quickly find relevant information.

[1153] "Feedback" is information that records questions, areas for improvement, suggestions, etc. that arise during the course of work and returns them to the next person in charge or to the system.

[1154] A "knowledge base" is a collection of knowledge that a system possesses, and is a structured database of information that includes success stories, efficient business procedures, and so on.

[1155] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and make predictions and judgments, and is a technology used to analyze big data and build predictive models.

[1156] A "new business proposal" refers to a new business plan or business idea that is constructed based on existing knowledge and data.

[1157] "Notification" is the act of sending information from the system to relevant parties, and is done via email or internal notification systems.

[1158] "Evaluation" refers to feedback provided by stakeholders on new business proposals received, and includes opinions and comments on the effectiveness of the proposal and areas for improvement.

[1159] The purpose of the system of this invention is to efficiently manage business handover information and automatically generate new business proposals. This system not only inputs, analyzes, saves, searches, and displays business handover information, but also accumulates feedback, updates the knowledge base, and automates the series of processes of generating, notifying, and evaluating new business proposals.

[1160] Enter and save business handover information

[1161] User: The person taking over the work (User A) uses their own terminal to access the server and enter details of the work, specific procedures, important contacts, and related materials. The terminal is a commonly used computing device that connects to the server through a browser or a dedicated application.

[1162] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy" or "BERT") and converted into structured data (such as JSON format). The analyzed data is stored in a database such as "MongoDB." For example, text-formatted business procedures are divided into steps and associated tags are added.

[1163] Search and display business handover information

[1164] User: The new person in charge (User B) logs in to the server from a terminal and sends a query to search for the task handover information. A search engine such as "Elasticsearch" is used for the search. The search results are displayed in an easy-to-understand HTML format. An example of a specific prompt is shown below.

[1165] "What are the new employee orientation procedures?"

[1166] "Find information on the latest marketing strategies."

[1167] Collecting and storing feedback

[1168] Users: If they have any questions or suggestions for improvement while performing their work, they can use the feedback form to send feedback to the server via their terminal. This feedback includes ratings and comments, and is saved in the database.

[1169] Knowledge Base Updates

[1170] Server: Automatically organizes and consolidates feedback and handover information provided by multiple users, eliminating redundant and duplicate information. This process uses data processing libraries such as "pandas." The knowledge base is updated based on the organized data. For example, the steps and key points of successful projects are added to "GraphDB."

[1171] Generate and notify new business proposals

[1172] Server: Based on the accumulated data, a machine learning algorithm (such as Scikit-learn or TensorFlow) is used to automatically generate new business proposals. The generated new business proposals are notified to relevant parties and distributed via email or an internal notification system (such as SendGrid).

[1173] User: The person in charge who receives the proposal checks the content on their device and provides feedback such as ratings and comments. The results are collected by the server and stored in the database.

[1174] Improvement of the proposed algorithm

[1175] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[1176] As described above, the interconnection of servers, terminals, and users enables efficient information management for business handovers and the automatic generation of new business proposals. This system improves the efficiency of business processes and enables the rapid development of new businesses.

[1177] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1178] Step 1:

[1179] Entering business handover information

[1180] User: The person taking over the work (User A) accesses the server from their own terminal and enters the work handover information. The input form displayed on the terminal includes the work content, specific procedures, important contact information, related materials, etc. For example, the user fills in "New employee orientation procedures" in the input form. The entered information is sent to the server as an HTTP request.

[1181] Input: Job description, specific procedures, important contacts, related materials

[1182] Output: Structured task handover information sent to the server

[1183] Step 2:

[1184] Analysis and storage of handover information

[1185] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy"), and the text data is converted into structured data (such as JSON format). During the analysis process, keywords are extracted from the text and intent is understood. The analyzed data is stored in a database such as "MongoDB."

[1186] Input: Unstructured business handover information

[1187] Output: Structured business handover information (JSON format)

[1188] Step 3:

[1189] Information search and display

[1190] User: The next person in charge (User B) logs in to the server from a terminal and enters a query to search for the saved handover information. The server uses Elasticsearch to search and displays the results in HTML format. For example, if User B searches for "New Employee Orientation Procedures," the details are displayed.

[1191] Input: Search query (e.g., "new employee orientation procedures")

[1192] Output: Search results (displayed in HTML format)

[1193] Step 4:

[1194] Providing feedback

[1195] Users: If they have any questions or suggestions for improvement while performing their work, they can use their terminals to enter them into a feedback form and send it to the server. This information can be used to improve work. For example, a user might comment, "There is some material that should be added to the orientation procedures."

[1196] Input: Feedback content (text format)

[1197] Output: Feedback data sent to the server

[1198] Step 5:

[1199] Accumulating and organizing feedback

[1200] Server: The received feedback data is stored in a database. After that, multiple pieces of feedback are consolidated and organized, and redundant and duplicate information is removed. This is done using libraries such as "pandas" to build a consistent database.

[1201] Input: Feedback data (multiple inputs)

[1202] Output: Organized feedback data

[1203] Step 6:

[1204] Knowledge Base Updates

[1205] Server: Automatically updates the knowledge base based on organized data, including best practices and efficient business procedures. The information is stored in a GraphDB and made available as company-wide knowledge.

[1206] Input: Organized feedback data

[1207] Output: Updated knowledge base

[1208] Step 7:

[1209] Generate new business proposals

[1210] Server: Based on the updated knowledge base, the server automatically generates new business proposals using machine learning algorithms (e.g., Scikit-learn and TensorFlow). For example, it proposes new marketing strategies by combining marketing success stories with customer churn analysis.

[1211] Input: Updated Knowledge Base

[1212] Output: New business proposal (text format, etc.)

[1213] Step 8:

[1214] Proposal notification and evaluation

[1215] Server: Notifies the generated new business proposals to the relevant parties and distributes them via email or internal notification systems. The person in charge who receives the proposals can check the contents of the proposals on their terminals and provide evaluation comments as feedback.

[1216] Input: New business proposal

[1217] Output: Evaluation comments for the proposal

[1218] Step 9:

[1219] Improvement of the proposed algorithm

[1220] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[1221] Input: Feedback and Rating Comments

[1222] Output: Improved proposed algorithm and knowledge base

[1223] (Application example 1)

[1224] 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."

[1225] In modern brick-and-mortar store operations, efficient handover of operations and centralized knowledge management are important. However, conventional methods have had problems such as cumbersome collection and management of handover information and inefficient generation of new business proposals. Furthermore, there were also issues with insufficient sharing of feedback between staff and automatic generation of sales promotion plans based on accumulated knowledge.

[1226] 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.

[1227] In this invention, the server includes: means for inputting business handover information; means for analyzing the input business handover information and saving it in a database; means for searching for and displaying the analyzed business handover information; means for collecting feedback obtained during the business handover process and storing it in a database; means for analyzing the stored data and updating a knowledge base; means for automatically generating new business proposals based on the updated knowledge base; means for notifying relevant parties of the generated new business proposals and receiving their evaluations; means for analyzing the evaluations and improving the proposal algorithm and knowledge base; means for managing business information related to store operation and making it accessible via a smartphone during handover; means for building a knowledge base for store operation and automatically generating new sales promotion plans based on feedback; and means for evaluating the generated new proposals and collecting improvements. This improves the efficiency of business handover in physical stores, enables centralized management of the knowledge base, and enables automatic generation of new proposals based on feedback.

[1228] "Business handover information" refers to the information required for an employee to hand over their work to the next person in charge, including specific work content and procedures, important contact information, and related materials.

[1229] A "server" is a computer system for analyzing, storing, and managing data, and plays a role in centrally managing information that users can access.

[1230] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language (language used by humans on a daily basis), and can analyze the meaning of sentences and convert them into structured data.

[1231] A "machine learning algorithm" is an algorithm that finds patterns and rules based on large amounts of data and makes predictions and classifications.

[1232] A "database" is a system for efficiently storing, searching, and managing large amounts of information.

[1233] A "knowledge base" is a database that accumulates information and know-how about a specific field or business, and is used to improve business efficiency and automate operations.

[1234] A "new business proposal" is a new idea or plan for improving operations or business processes based on accumulated data and feedback.

[1235] "Feedback" refers to information that reports opinions and areas for improvement obtained during the course of business, and is used to improve the system and generate new proposals.

[1236] A "smartphone" is a mobile phone terminal equipped with advanced computing power and communication functions, and is capable of running a variety of applications.

[1237] "Store operations" refers to all operations related to running a store, such as managing a physical store, product display, inventory management, and sales promotion.

[1238] "Building a knowledge base" means accumulating and systematically storing business-related knowledge and know-how, and using that knowledge to make business improvements and proposals.

[1239] This invention is a system for efficiently managing business handover information in a physical store, building a knowledge base related to store management, and automatically generating new sales promotion plans based on feedback. This system is implemented using a server and user terminals (e.g., smartphones).

[1240] System Program

[1241] The system has a program with the following main components:

[1242] 1. A means of entering business handover information.

[1243] 2. A means of analyzing the entered business handover information and storing it in a database.

[1244] 3. A means for searching and displaying the analyzed business handover information.

[1245] 4. A means of collecting feedback obtained during the business handover process and storing it in a database.

[1246] 5. A means of analyzing accumulated data and updating the knowledge base.

[1247] 6. A means of automatically generating new business proposals based on the updated knowledge base.

[1248] 7. A means of informing stakeholders of generated new business proposals and receiving their evaluation.

[1249] 8. A means of analyzing the evaluation and improving the proposed algorithm and knowledge base.

[1250] 9. A means of managing business information related to store operations and making it accessible via smartphone when taking over.

[1251] 10. A means of building a knowledge base for store operations and automatically generating new promotional plans based on feedback.

[1252] 11. A means of evaluating new proposals generated and collecting suggestions for improvement.

[1253] Explanation of program processing

[1254] The server receives the task handover information entered by the user (store manager or staff member) using their smartphone. The server analyzes this information using natural language processing technology (for example, Python's NLP library), converts it into structured data, and stores it in a database. The user can then use their smartphone to search for and view the stored handover information.

[1255] Feedback is collected via smartphones, and when users enter questions or suggestions for improvement they have while performing their work, the server stores them in a database. The server periodically analyzes the accumulated feedback and data and updates the knowledge base. Machine learning algorithms (e.g., scikit-learn) are used to automatically generate new sales promotion plans and business improvement proposals.

[1256] The generated new business proposals are notified to the user, who can provide ratings and comments via their smartphone. The server analyzes this feedback and uses it to improve the proposal algorithm and knowledge base.

[1257] Specific examples

[1258] For example, a store manager can input a new inventory management method on their smartphone, and when staff review it, they can provide feedback such as "the order of products is unclear," allowing the system to automatically suggest new sales based on inventory shortages.

[1259] Examples of prompts include:

[1260] The new store manager has entered the information on inventory management and sales promotions. At the same time, the staff has provided feedback on the product arrangement. Based on this, please propose a new sales promotion plan.

[1261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1262] Step 1:

[1263] The user inputs task handover information using a smartphone. The input information includes the task content, procedures, important contact information, and related materials. The input data is sent to the server.

[1264] Step 2:

[1265] The server analyzes the received task handover information using natural language processing technology (for example, a Python NLP library). The analyzed data is converted into structured data and stored in a database. The input is raw text data, and the output is structured data.

[1266] Step 3:

[1267] The user accesses the server using a smartphone and searches for the stored handover information. The server processes the search query and displays the appropriate handover information on the screen. The input is the search query, and the output is the formatted handover information.

[1268] Step 4:

[1269] Users can input any questions or improvements they have while working on their smartphones and send them as feedback to the server, which then stores the feedback in a database. The input is raw text feedback data, and the output is the feedback data stored in the database.

[1270] Step 5:

[1271] The server periodically analyzes the accumulated feedback and task handover information and updates the knowledge base. The analysis includes data cleansing and statistical techniques. The input is the accumulated data, and the output is an updated knowledge base.

[1272] Step 6:

[1273] The server automatically generates new business proposals using a machine learning algorithm (e.g., scikit-learn) based on the updated knowledge base. The input is the updated knowledge base, and the output is the new business proposal.

[1274] Step 7:

[1275] The generated new business proposal is notified to the relevant parties via smartphone or email. The user reviews the proposal and provides feedback such as ratings and comments. The input is the new business proposal, and the output is the ratings and comments.

[1276] Step 8:

[1277] The server analyzes the received ratings and comments and improves the proposed algorithm and knowledge base. The input is the ratings and comments, and the output is the improved algorithm and knowledge base.

[1278] 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.

[1279] The system of the present invention is composed mainly of a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals, and is further combined with an emotion engine that recognizes and analyzes user emotions.

[1280] 1. Business transfer intermediation

[1281] Entering transfer information

[1282] User: A new person in charge (Employee A) uses a terminal to input task handover information into the server to hand over the task to the next person in charge (Employee B). The input information includes the task content, procedures, important contact information, and related materials. During input, the emotion engine also analyzes the user's emotions and collects emotional data about the task.

[1283] Analysis and storage of handover information

[1284] Server: Along with the emotional data analyzed by the emotion engine, the task handover information is analyzed using natural language processing (NLP) technology and stored in a database as structured data.

[1285] Information Access

[1286] User: Employee B, the new person in charge, logs in to the server using a terminal and searches for the saved handover information. The server provides search results including emotional data, allowing Employee B to understand the handover information taking emotional aspects into account.

[1287] Providing feedback

[1288] User: Employee B reports any questions or areas for improvement that arise during the course of work, as well as his or her feelings at the time, to the server via his or her terminal.

[1289] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[1290] 2. Accumulation of business knowledge

[1291] Data organization

[1292] Server: Integrates and organizes task handover information, feedback, and sentiment data provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[1293] Knowledge Base Updates

[1294] Server: Automatically updates the knowledge base based on the organized data and sentiment data. For example, it adds sentiment data related to success stories and efficient business procedures to the knowledge base.

[1295] Auto-tagging

[1296] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[1297] Knowledge integration and new business proposal generation

[1298] Data analysis

[1299] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[1300] Generate new business proposals

[1301] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department" with "customer abandonment analysis" and related emotional data.

[1302] Proposal notification and evaluation

[1303] Server: Distributes generated new business proposals to stakeholders via email and notification systems. Uses an emotion engine to recognize users' reactions and ratings.

[1304] Collecting ratings

[1305] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[1306] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[1307] Specific examples

[1308] 1. Enter and save transfer information

[1309] User: Employee A enters the "New Employee Orientation Procedure" into the terminal, and their emotions at the time are also collected.

[1310] Server: Analyzes business information and emotion data using NLP technology and stores it in a database.

[1311] 2. Searching for and displaying information

[1312] User: Employee B searches for "New Employee Orientation Procedures."

[1313] Server: Retrieves related information along with emotion data from the database and displays it.

[1314] 3. New business proposal generation and evaluation

[1315] Server: Analyzes business and sentiment data and generates new marketing strategy proposals.

[1316] User: Receives suggestions and provides evaluation comments and sentiment data.

[1317] Server: Based on the feedback, improve the next proposed algorithm.

[1318] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[1319] The processing flow will be explained below.

[1320] Business transfer intermediation

[1321] Step 1: Enter your transfer information

[1322] User: Employee A uses a terminal to input task handover information into the server. The information to be input includes the task content, procedures, important contacts, and related materials. As the information is being input, the emotion engine analyzes the user's emotions in real time and collects emotional data.

[1323] Step 2: Analyze the handover information

[1324] Server: Analyzes the received task handover information and emotional data using natural language processing (NLP) technology. The task information is recognized as structured data and converted into a format that can be stored in a database together with the emotional data.

[1325] Step 3: Save handover information and emotion data

[1326] Server: Structured task handover information and emotion data are stored in a database and organized by category, allowing for consistent access and retrieval.

[1327] Step 4: Information Access

[1328] User: Employee B, the new employee, logs in to the server using a terminal and searches for relevant handover information, for example, "New Employee Orientation Procedures."

[1329] Server: Processes the search query, retrieves the relevant handover information and emotion data from the database, and displays them on the device in an appropriate format.

[1330] Step 5: Provide feedback

[1331] User: Employee B uses a terminal to report any questions or improvements that arise during work to the server. The emotion engine also analyzes the emotions expressed at the time.

[1332] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[1333] Accumulation of business knowledge

[1334] Step 1: Organize your data

[1335] Server: Integrates and organizes handover information, feedback, and sentiment data provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[1336] Step 2: Update your knowledge base

[1337] Server: Automatically updates the knowledge base based on the organized data. For example, it adds best practices, efficient business procedures, and related emotional data to the knowledge base.

[1338] Step 3: Auto-tagging

[1339] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[1340] Knowledge integration and new business proposal generation

[1341] Step 1: Data analysis

[1342] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[1343] Step 2: Generate a new business proposal

[1344] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department," "customer abandonment analysis," and related emotional data.

[1345] Step 3: Proposal Notification

[1346] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[1347] Step 4: Collect ratings

[1348] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[1349] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[1350] Specific examples

[1351] 1. Enter and save transfer information

[1352] User: Employee A enters the "New Employee Orientation Procedure" into the terminal. At that time, the emotion engine analyzes Employee A's emotions and captures them as data.

[1353] Server: Uses NLP technology to analyze business information and emotion data and store them in a database.

[1354] 2. Searching for and displaying information

[1355] User: Employee B searches for "New Employee Orientation Procedures."

[1356] Server: Retrieves related information along with emotion data from the database and displays it.

[1357] 3. New business proposal generation and evaluation

[1358] Server: Analyzes business and sentiment data and generates new marketing strategies as proposals.

[1359] User: Receives suggestions and provides evaluation comments and sentiment data.

[1360] Server: Based on the feedback, improve the next proposed algorithm.

[1361] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[1362] Example 2

[1363] 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."

[1364] Conventional business handover systems have basic functions such as inputting, analyzing, and saving business information, but they lack consideration for user emotions. This can lead to a lack of understanding of the handover information and inappropriate new business proposals. Furthermore, it is necessary to utilize emotion data to generate more effective and appropriate new business proposals.

[1365] 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.

[1366] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information and saving it in a database, means for searching for and displaying the analyzed task handover information, means for collecting feedback obtained during the task handover process and storing it in a database, means for analyzing the stored data and updating a knowledge base, means for automatically generating new business proposals based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, means for analyzing the evaluations and improving the proposal algorithm and the knowledge base, means for analyzing user emotions and collecting task handover information including emotion data, means for assisting in understanding the task handover information based on the emotion data, and means for optimizing the new business proposals based on the emotion data. This enables task handover and new business proposals that take user emotions into consideration.

[1367] "Business handover information" refers to information including business content, procedures, important contact information, and related materials, and refers to all information necessary for the handover of business between personnel.

[1368] "Natural language processing technology" is a technology that analyzes text data written in natural language and understands and processes its meaning and structure. Specifically, it includes tokenization, part-of-speech tagging, grammatical analysis, etc.

[1369] A "database" refers to a collection of data that is structured so that the stored information can be efficiently managed and searched, and includes relational databases and NoSQL databases.

[1370] "Emotional energy" refers to software and algorithms that analyze a user's emotional state and record it as a number or category.

[1371] "Emotional data" refers to data that quantifies or categorizes a user's emotional state and is collected using contextual analysis and facial recognition technology.

[1372] A "knowledge base" is a database that systematically compiles important information within an organization, such as business procedures and success stories.

[1373] A "new business proposal" is a proposal for a new business idea or strategy that is generated based on current business data and emotional data.

[1374] A "machine learning algorithm" is an algorithm that learns various patterns from large amounts of data and makes future predictions and classifications. Specifically, it includes neural networks and support vector machines.

[1375] "NLP" stands for natural language processing technology and refers to the technology of understanding and processing human language.

[1376] "User" refers to a member of an organization who uses the system, specifically a business person.

[1377] A "server" refers to a computer system that receives requests from users, performs the necessary processing, operates a database, and returns the results.

[1378] "Terminal" refers to the computer or device used by a user to input and view data.

[1379] The present invention is a system for analyzing and utilizing user emotions with the aim of efficiently managing business handover information and automatically generating new business proposals. Hereinafter, an embodiment of the present invention will be described in detail.

[1380] System configuration

[1381] This system consists of the following components:

[1382] 1. User terminal: A device used for inputting information, searching, and providing feedback. This includes PCs, smartphones, tablets, etc.

[1383] 2. Server: The main computer system that processes user requests, analyzes, stores, and retrieves data, and generates new business proposals.

[1384] 3. Database: A storage system for storing task handover information, feedback, and emotion data. A relational database or NoSQL database is used.

[1385] 4. Emotion Engine: It is an algorithmic software that analyzes user emotions and collects data as numbers and categories.

[1386] 5. Natural Language Processing (NLP): Text analysis technology using Python's NLTK and spaCy.

[1387] 6. Machine learning algorithms: Data analysis and new business proposal generation algorithms using scikit-learn and TensorFlow.

[1388] Basic Operation Procedure

[1389] 1. Enter business handover information

[1390] User: The new person in charge (Employee A) enters the details of the job, procedures, important contact information, and related documents on a terminal such as a PC. At this time, the emotion engine operates and simultaneously collects the user's emotional data.

[1391] Example: Employee A enters "New Employee Orientation Procedures" and records "Anxiety" as the emotion he felt at the time.

[1392] 2. Analysis and storage

[1393] Server: The server analyzes the input task handover information using natural language processing (NLP) technology and stores it in a database as structured data, along with emotional data.

[1394] Example: Using Python's NLTK library to tokenize business content and store it in a database.

[1395] 3. Search and Display

[1396] User: The next person in charge (Employee B) logs in to the server using a terminal and searches for the necessary business handover information.

[1397] Server: The server displays the analyzed task handover information along with emotion data based on the search query.

[1398] Example: When Employee B searches for "new employee orientation procedures," the server displays related information and emotion data for "anxiety."

[1399] 4. Providing Feedback

[1400] User: Employee B reports any questions, areas for improvement, or feelings that arise during work execution via the terminal.

[1401] Server: The server stores this feedback in a database and uses it to improve operations in the future.

[1402] Example: Employee B gives feedback that "orientation is progressing slowly" and records his / her emotion at that time as "irritation."

[1403] 5. Organizing data and updating the knowledge base

[1404] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, eliminating redundancies and duplications. Updates the knowledge base based on the organized data.

[1405] Example: Consolidating duplicate "orientation procedures" information and adding it to the knowledge base as one coherent procedure.

[1406] 6. Automatic categorization and tagging

[1407] Server: Uses automatic classification and tagging functions to assign relevant keywords and categories to business and emotional data.

[1408] Example: Add tags such as "New Employee Training" and "Initial Setup" to "Orientation Procedures."

[1409] 7. Business and Emotional Data Analysis

[1410] Server: Uses machine learning algorithms to analyze the accumulated data and detect success stories, frequently occurring challenges, and associated emotions.

[1411] Example: Using scikit-learn, we will associate "customer service procedures" with emotional data on "satisfaction" as a success story.

[1412] 8. Generate new business proposals

[1413] Server: Based on the analysis results, it combines different business knowledge and emotional data to automatically generate new business proposals.

[1414] Example: Propose a new marketing strategy based on success stories from the marketing department and emotional data on "satisfaction" in customer interactions.

[1415] 9. Notification and Evaluation of Proposals

[1416] Server: Notifies the generated new business proposal to the relevant parties and receives their evaluation.

[1417] User: The parties who receive the proposal evaluate the content and provide feedback along with sentiment data.

[1418] Example: Evaluate the proposal as "useful" and record the emotion as "satisfied."

[1419] 10. Collecting ratings and improving the algorithm

[1420] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[1421] Example: Optimize the next business proposal algorithm based on collected "satisfaction" emotion data.

[1422] Prompt Sentence Examples

[1423] Below is an example of a prompt sentence.

[1424] 1. "Please enter your new employee orientation procedures. Please feel free to write down your thoughts and feelings about the job."

[1425] 2. "Please create a procedure for handing over the work to the next person in charge. Please also include your current feelings and impressions."

[1426] 3. "Please review our proposed new marketing strategy and provide feedback and sentiment data."

[1427] The above is a detailed description of the embodiment of the present invention. By using this system, the process of business handover becomes more efficient and new business proposals are optimized by taking into account the user's feelings.

[1428] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1429] Step 1: Enter business handover information

[1430] User: The new employee (Employee A) enters the job description, procedures, important contact information, and related documents using a dedicated web form or software on a PC or other device. As the information is entered, the emotion engine is activated and the user's emotional data is collected at the same time.

[1431] Input: Job details, procedures, important contacts, related documents, emotional data (e.g., anxiety, satisfaction, etc.)

[1432] Output: Task handover information and emotion data are sent to the server.

[1433] Step 2: Analyze and save the transfer information

[1434] Server: The server performs natural language processing (NLP) on the received task handover information and emotion data using Python's NLTK library and spaCy, and stores the analysis results in a database as structured data.

[1435] Input: Business handover information, emotion data

[1436] Output: The analyzed business information and emotion data are saved in a database as structured data.

[1437] Specific operation: The server first performs tokenization and part-of-speech tagging, then performs context analysis, and then stores the analysis results in a database as JSON format data.

[1438] Step 3: Find and view information

[1439] User: The next person in charge (Employee B) uses a terminal to log in to the server and search for specific task handover information.

[1440] Server: The server receives the user's search query, retrieves relevant business information and emotion data from the database, and displays them.

[1441] Input: User's search query (e.g., "new employee orientation procedures")

[1442] Output: The relevant task handover information and emotion data are displayed.

[1443] Specific operation: The server generates an SQL query based on the user's search query, searches the database, and displays the retrieved data in HTML format.

[1444] Step 4: Provide feedback

[1445] User: Employee B inputs any questions or improvements that arise during the course of work, as well as his / her feelings, through the terminal and reports them to the server.

[1446] Server: Stores the provided feedback and emotion data in a database.

[1447] Input: Feedback content, emotional data (e.g., dissatisfaction, irritation, etc.)

[1448] Output: Feedback and emotion data are stored in a database.

[1449] What happens: The user fills out the feedback form and hits the submit button. The emotion engine is then run again to analyze the emotion, which is then stored in the database along with the feedback.

[1450] Step 5: Cleanse your data and update your knowledge base

[1451] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, removes redundancies and duplicates, and updates the knowledge base.

[1452] Input: Multiple task handover information, feedback, and emotion data

[1453] Output: A cleaned and updated knowledge base

[1454] What it does: The server periodically runs data cleaning scripts to remove redundant and duplicate data. The updated data is imported into the knowledge base software.

[1455] Step 6: Auto-classification and tagging

[1456] Server: The server uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data.

[1457] Input: Organized task handover information, emotional data

[1458] Output: Classified and tagged task handover information, emotion data

[1459] What it does: Classifies data using text classification algorithms (e.g., Naive Bayes or SVM) and automatically tags it with keywords and categories.

[1460] Step 7: Analyze business and sentiment data

[1461] Server: Uses machine learning algorithms (e.g., scikit-learn and TensorFlow) to analyze accumulated business and sentiment data and detect success stories and frequently occurring issues.

[1462] Input: Business handover information, emotion data

[1463] Outputs: Reports, success stories, challenges

[1464] What it does: The server periodically processes batches of data, applies analytics algorithms to the data, and generates reports that are displayed on the dashboard.

[1465] Step 8: Generate new business proposals

[1466] Server: Based on the analysis results, it automatically generates new business proposals by combining different business knowledge and emotional data.

[1467] Input: success stories, challenges, sentiment data

[1468] Output: New business proposal

[1469] How it works: Using a generative AI model (e.g., GPT-3), new business proposals are automatically generated, and the generated proposals are then internally reviewed and optimized.

[1470] Step 9: Proposal notification and evaluation

[1471] Server: Distributes the generated new business proposals to relevant parties via email or notification systems (e.g., Slack or Microsoft Teams).

[1472] Users: The parties who receive the proposal evaluate the proposal and provide feedback along with sentiment data.

[1473] Input: New business proposal, evaluation feedback, sentiment data

[1474] Output: Evaluation results, feedback

[1475] Specific operation: The server sends emails using the SMTP protocol and sends real-time notifications using the notification system's API. Interested parties submit feedback using the evaluation form.

[1476] Step 10: Collecting ratings and improving the algorithm

[1477] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[1478] Input: Rating feedback, emotion data

[1479] Output: Improved algorithms and knowledge bases

[1480] What it does: The server uses a logging system to collect feedback data, which is used as training data for the machine learning model. It then retrains the model with new data to improve it.

[1481] (Application example 2)

[1482] 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."

[1483] The task handover process in modern factories often suffers from incomplete information transmission and worker emotional stress. Furthermore, the difficulty of properly collecting employee feedback and identifying areas for improvement can hinder improvements in production efficiency. Conventional systems are unable to collect and analyze emotional data in real time, identify worker stress points, and make immediate recommendations based on that data, limiting their ability to improve work efficiency and worker satisfaction. A new method is needed to solve this problem.

[1484] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1485] In this invention, the server includes a means for analyzing task handover information and emotion data and storing them in a database, a means for searching and displaying the analyzed task handover information and emotion data, and a means for collecting and analyzing emotion data in real time using an emotion engine. This not only enables efficient management of task handover information, but also enables real-time suggestions based on emotion data during work. This system reduces emotional stress for workers and improves work efficiency.

[1486] "Business handover information" refers to general information such as business content, procedures, important contacts, and related materials, and refers to detailed business data that will be useful to the next person in charge.

[1487] "Emotional data" refers to information that expresses a user's emotional state using numbers, tags, etc., and is data that analyzes and collects emotions such as stress, happiness, and dissatisfaction while working in real time.

[1488] An "emotion engine" is a technical means for recognizing and analyzing a user's emotions, and refers to a system that collects and analyzes emotional data in real time.

[1489] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, and refers to a means of analyzing text data such as business handover information and storing it in a database.

[1490] "Machine learning algorithms" refer to mathematical models and statistical methods that learn patterns and relationships based on large amounts of data and make predictions and suggestions.

[1491] A "knowledge base" is a database that systematically accumulates the knowledge necessary to carry out business, and includes information such as business processes, success stories, and efficient procedures.

[1492] "New business proposals" refer to proposals that automatically generate new business strategies and improvement plans based on current business data and emotional data.

[1493] "Real-time suggestions" are suggestions that are instantly generated and actionable for ongoing tasks or situations, and include specific actions to improve work efficiency and worker satisfaction based on emotional data.

[1494] "Feedback" refers to reactions and opinions, including questions and areas for improvement that arise during the course of work, as well as emotions at the time.

[1495] "Suggestion Algorithm" refers to a mathematical and logical method for generating novel suggestions based on collected data and sentiment data.

[1496] The system of the present invention combines many elements to realize efficient management of business handover information and automatic generation of new business proposals. A specific embodiment of the system is shown below.

[1497] System Configuration

[1498] The system consists of the following main elements:

[1499] A terminal for inputting task handover information and emotion data

[1500] A server that analyzes input information and emotional data

[1501] Database for storing analysis results

[1502] A proposal generation system that uses emotion engines, natural language processing (NLP), and machine learning algorithms

[1503] Hardware and software used

[1504] Hardware: Factory robots, data collection sensors, terminals (PCs, tablets, smartphones)

[1505] Software: EmotionEngine (emotion analysis library), NLPProcessor (natural language processing library), ProposalGenerator (proposal generation mechanism), SQLite (database)

[1506] Program processing explanation

[1507] 1. Enter and save business handover information

[1508] A user uses a terminal to input task handover information and related emotional data, such as details of the tension felt during the initial setup of a new product line.

[1509] The device sends the input information to the server, which then uses the Emotion Engine to analyze the emotional data.Then, the task handover information and emotional data are analyzed by the NLP Processor and stored in a database.

[1510] 2. Searching for and displaying information

[1511] When a user searches for business information, the server retrieves the relevant business information and emotion data from the database and displays them. This allows the user to understand handover information and the emotions involved.

[1512] 3. Collecting and Analyzing Feedback

[1513] Users report any questions or improvements they have while working, as well as their feelings at the time, through their devices. The server collects this feedback and stores it in a database.

[1514] Furthermore, based on machine learning algorithms, the collected feedback data is analyzed and the knowledge base is updated.

[1515] 4. Automatic generation of new business proposals

[1516] The server automatically generates new business proposals using the Proposal Generator based on the accumulated business and emotion data. For example, it proposes reducing worker stress and improving production efficiency by introducing an automated system for the concentration process.

[1517] 5. Notification of proposals and collection of evaluations

[1518] The server notifies the generated new business proposals to the relevant parties and collects their evaluations and comments via their terminals. The collected evaluations are stored in a database and used to improve the proposal algorithm and knowledge base for future projects.

[1519] Specific examples

[1520] The robot uses an emotion engine to detect high stress levels among employees in the enrichment process and uses that data to suggest ways to automate the process.

[1521] Example prompts to input to the generative AI model

[1522] Emotional data: Stress,New proposal: Introducing an automated system for the concentration process is expected to reduce worker stress and improve production efficiency.

[1523] As described above, this system streamlines business handovers, automatically generates new business proposals, and also enables flexible responses that take emotional data into account.

[1524] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1525] Step 1:

[1526] The user inputs task handover information and emotional data into the terminal. Specifically, the user enters the task content, procedures, important contact information, and related materials into the input fields of the terminal, and also selects or writes down the emotions felt at the time (e.g., tension, satisfaction, anxiety). The input data is immediately sent to the server.

[1527] Input: Business handover information, emotion data

[1528] Output: Task handover information and emotion data sent to the server

[1529] Step 2:

[1530] The server uses EmotionEngine to analyze the transmitted emotional data. Next, it uses NLPProcessor to analyze the task handover information using natural language processing technology and converts it into meaningful structured data. The server then stores this information in a database.

[1531] Input: Business handover information, emotion data

[1532] Output: Structured business data, emotion data (stored in a database)

[1533] Step 3:

[1534] The user uses the terminal to search for task handover information from the database, and the server retrieves the relevant task information and related emotion data from the database, formats it for display, and transmits it to the terminal.

[1535] Input: Search query

[1536] Output: Search results (business handover information, emotion data)

[1537] Step 4:

[1538] Users report any questions or improvements they have while working, as well as their feelings at the time, through their terminals. The server collects this feedback and stores it in a database.

[1539] Input: Feedback information, emotion data

[1540] Output: Collected feedback and sentiment data (stored in a database)

[1541] Step 5:

[1542] The server periodically analyzes the accumulated feedback and sentiment data, and uses machine learning algorithms to extract success stories, frequent issues, and their associated sentiment data to update the knowledge base.

[1543] Input: Accumulated feedback, emotional data

[1544] Output: Updated knowledge base

[1545] Step 6:

[1546] The server automatically generates new business proposals based on the updated knowledge base and emotion data. The generated proposals are notified to the relevant parties, and the proposal contents are displayed on their terminals.

[1547] Input: Updated knowledge base, emotion data

[1548] Output: New business proposal (displayed on the device)

[1549] Step 7:

[1550] The user reviews the generated suggestions on their device and enters their ratings and comments, along with their emotional data. The server collects this feedback and stores it in a database.

[1551] Input: Proposal ratings, comments, sentiment data

[1552] Output: Collected ratings, comments, and sentiment data (stored in a database)

[1553] Step 8:

[1554] The server analyzes the collected ratings and sentiment data and uses it to refine the proposed algorithm and knowledge base.

[1555] Input: Rating, emotion data

[1556] Output: Improved proposed algorithm, updated knowledge base

[1557] This series of processes ensures efficient business handover and new business proposals are generated taking into account emotional data.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] [Fourth embodiment]

[1562] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1563] 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.

[1564] 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).

[1565] 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.

[1566] 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.

[1567] 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).

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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."

[1575] The system of the present invention is configured around a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals.

[1576] 1. Business transfer intermediation

[1577] Entering transfer information

[1578] User: A new employee (Employee A) uses a terminal to input task handover information into the server to hand over his or her task to the next employee (Employee B). The input information includes the task content, specific procedures, important contact information, and related materials.

[1579] Analysis and storage of handover information

[1580] Server: Analyzes the received task handover information using natural language processing technology and converts it into structured data. This structured data is then stored in a database.

[1581] Information Access

[1582] User: Employee B, who will take over the work, logs in to the server using a terminal and searches and displays the saved handover information. The server displays the search results in an appropriate format so that Employee B can easily understand them.

[1583] Providing feedback

[1584] User: Enters any questions or suggestions for improvement that arise during work into the server via a terminal. This allows Employee B to carry out their work smoothly.

[1585] 2. Accumulation of business knowledge

[1586] Data organization

[1587] Server: Integrates and organizes the work handover information provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[1588] Knowledge Base Updates

[1589] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[1590] Auto-tagging

[1591] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[1592] 3. Generate new business proposals

[1593] Data analysis

[1594] Server: Uses machine learning algorithms to periodically analyze accumulated operational data, particularly to identify success stories and frequently occurring issues.

[1595] Generate new business proposals

[1596] Server: Based on the analysis results, the server automatically generates new business proposals by combining multiple business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[1597] Proposal notification and evaluation

[1598] Server: Notifies stakeholders of generated new business proposals and distributes them via email and notification systems.

[1599] User: The employee who receives the proposal checks the content on their device and provides feedback by rating and commenting. The rating is then stored in the database by the server.

[1600] Using Feedback

[1601] Server: Analyzes the feedback and ratings received and helps improve the proposed algorithm and knowledge base.

[1602] Specific examples

[1603] 1. Business transfer intermediation

[1604] User: Employee A (HR department staff) enters the "New Employee Orientation Procedures" into the server from a terminal.

[1605] Server: Analyzes using NLP technology and stores procedures and related materials in a database.

[1606] User: Employee B logs in, searches for "New Employee Orientation Procedures," and views it.

[1607] Users: Report any questions or improvements to the server via their devices and provide feedback.

[1608] 2. Accumulation of business knowledge

[1609] Server: The feedback provided by Employee A and Employee B is stored in a database, and the analysis results are added to the knowledge base.

[1610] 3. Generate new business proposals

[1611] Server: Regularly analyze data and propose new marketing strategies that combine "marketing success stories" and "customer abandonment analysis."

[1612] User: The employee who receives the proposal reviews it on their device and provides evaluation comments. The server uses this feedback to improve the proposal algorithm.

[1613] In this way, the system allows the server, terminals, and users to work together at each processing step, improving the efficiency of business handovers and automating new business proposals.

[1614] The processing flow will be explained below.

[1615] Business transfer intermediation

[1616] Step 1: Enter your transfer information

[1617] User: Employee A uses a terminal to enter the task handover information into the server. Specifically, he fills out an input form with the task content, procedures, important contact information, and related documents.

[1618] Step 2: Analyze the handover information

[1619] Server: Analyzes the received task handover information using natural language processing (NLP) technology. As a result of the analysis, the information is recognized as structured data and converted into a format that can be stored in a database.

[1620] Step 3: Save the transfer information

[1621] Server: Stores structured data in a database and organizes it into categories, allowing for consistent access and searching.

[1622] Step 4: Information Access

[1623] User: Employee B, the new employee, logs in to the server using a terminal and searches for the stored handover information. For example, he enters "New Employee Orientation Procedures" in the search field.

[1624] Server: Processes the search query, retrieves the relevant handover information from the database, and displays it on the device.

[1625] Step 5: Provide feedback

[1626] User: Employee B uses a terminal to report any questions or improvements that arise while performing his / her work to the server. Specifically, he / she fills in a feedback form.

[1627] Server: The provided feedback is stored in a database and used to improve future operations.

[1628] Accumulation of business knowledge

[1629] Step 1: Organize your data

[1630] Server: Integrates and organizes handover information and feedback provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[1631] Step 2: Update your knowledge base

[1632] Server: Automatically updates the knowledge base based on organized data, for example by adding best practices and efficient business procedures to the knowledge base.

[1633] Step 3: Auto-tagging

[1634] Server: Use automatic classification and tagging to assign relevant keywords and categories to business data, helping users quickly find the information they need.

[1635] Knowledge integration and new business proposal generation

[1636] Step 1: Data analysis

[1637] Server: Uses machine learning algorithms to analyze accumulated operational data on a regular basis, particularly to identify success stories and frequently occurring issues.

[1638] Step 2: Generate a new business proposal

[1639] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge. For example, it proposes a new marketing strategy by combining "success stories from the marketing department" and "customer defection analysis."

[1640] Step 3: Proposal Notification

[1641] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[1642] Step 4: Collect ratings

[1643] User: The employee who receives the proposal checks the proposal on their device and enters their evaluation and comments as feedback into the server.

[1644] Server: The received feedback and ratings are stored in a database and used to improve the proposed algorithm and knowledge base.

[1645] Specific examples

[1646] 1. Enter and save transfer information

[1647] User: Employee A enters the "New Employee Orientation Procedures" on the terminal.

[1648] Server: Analyzes the information using NLP techniques and stores it in a database.

[1649] 2. Searching for and displaying information

[1650] User: Employee B searches for "New Employee Orientation Procedures" on his device.

[1651] Server: Retrieves relevant information from the database and displays it.

[1652] 3. New business proposal generation and evaluation

[1653] Server: Analyzes business data and generates new marketing strategies as proposals.

[1654] User: Receives suggestions and provides evaluation comments.

[1655] Server: Based on the feedback, improve the next proposed algorithm.

[1656] In this way, the entire system works together efficiently, streamlining business handovers and automating new business proposals.

[1657] Example 1

[1658] 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."

[1659] In modern companies, business handover is a very important process, but managing the information involved is complicated and time-consuming. Furthermore, creating new business proposals requires a lot of time and effort, making it difficult to efficiently utilize past knowledge and success stories. To address this situation, a system is needed that efficiently manages business handover information and automatically utilizes accumulated knowledge to streamline the creation of new business proposals.

[1660] 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.

[1661] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information using natural language processing technology and storing it in a database, means for searching for and displaying the analyzed task handover information using a search engine, means for collecting feedback obtained during the task handover process and storing it in a database, means for organizing and integrating the stored data and updating a knowledge base, means for automatically generating new business proposals using a machine learning algorithm based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, and means for analyzing the evaluations and improving the proposal algorithm and knowledge base. This enables efficient information management of task handovers and automatic generation of new business proposals.

[1662] "Business handover information" refers to information necessary when the current person in charge hands over the business to the next person in charge, and includes the business content, specific procedures, important contact information, related materials, etc.

[1663] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and is a technology that performs text analysis, entity extraction from language data, sentiment analysis, etc.

[1664] A "database" is a collection of data that is centrally managed and structured so that it can be easily accessed, searched, and updated.

[1665] A "search engine" is a system for efficiently searching information stored in a database, a technology that allows a search query to be used to quickly find relevant information.

[1666] "Feedback" is information that records questions, areas for improvement, suggestions, etc. that arise during the course of work and returns them to the next person in charge or to the system.

[1667] A "knowledge base" is a collection of knowledge that a system possesses, and is a structured database of information that includes success stories, efficient business procedures, and so on.

[1668] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and make predictions and judgments, and is a technology used to analyze big data and build predictive models.

[1669] A "new business proposal" refers to a new business plan or business idea that is constructed based on existing knowledge and data.

[1670] "Notification" is the act of sending information from the system to relevant parties, and is done via email or internal notification systems.

[1671] "Evaluation" refers to feedback provided by stakeholders on new business proposals received, and includes opinions and comments on the effectiveness of the proposal and areas for improvement.

[1672] The purpose of the system of this invention is to efficiently manage business handover information and automatically generate new business proposals. This system not only inputs, analyzes, saves, searches, and displays business handover information, but also accumulates feedback, updates the knowledge base, and automates the series of processes of generating, notifying, and evaluating new business proposals.

[1673] Enter and save business handover information

[1674] User: The person taking over the work (User A) uses their own terminal to access the server and enter details of the work, specific procedures, important contacts, and related materials. The terminal is a commonly used computing device that connects to the server through a browser or a dedicated application.

[1675] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy" or "BERT") and converted into structured data (such as JSON format). The analyzed data is stored in a database such as "MongoDB." For example, text-formatted business procedures are divided into steps and associated tags are added.

[1676] Search and display business handover information

[1677] User: The new person in charge (User B) logs in to the server from a terminal and sends a query to search for the task handover information. A search engine such as "Elasticsearch" is used for the search. The search results are displayed in an easy-to-understand HTML format. An example of a specific prompt is shown below.

[1678] "What are the new employee orientation procedures?"

[1679] "Find information on the latest marketing strategies."

[1680] Collecting and storing feedback

[1681] Users: If they have any questions or suggestions for improvement while performing their work, they can use the feedback form to send feedback to the server via their terminal. This feedback includes ratings and comments, and is saved in the database.

[1682] Knowledge Base Updates

[1683] Server: Automatically organizes and consolidates feedback and handover information provided by multiple users, eliminating redundant and duplicate information. This process uses data processing libraries such as "pandas." The knowledge base is updated based on the organized data. For example, the steps and key points of successful projects are added to "GraphDB."

[1684] Generate and notify new business proposals

[1685] Server: Based on the accumulated data, a machine learning algorithm (such as Scikit-learn or TensorFlow) is used to automatically generate new business proposals. The generated new business proposals are notified to relevant parties and distributed via email or an internal notification system (such as SendGrid).

[1686] User: The person in charge who receives the proposal checks the content on their device and provides feedback such as ratings and comments. The results are collected by the server and stored in the database.

[1687] Improvement of the proposed algorithm

[1688] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[1689] As described above, the interconnection of servers, terminals, and users enables efficient information management for business handovers and the automatic generation of new business proposals. This system improves the efficiency of business processes and enables the rapid development of new businesses.

[1690] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1691] Step 1:

[1692] Entering business handover information

[1693] User: The person taking over the work (User A) accesses the server from their own terminal and enters the work handover information. The input form displayed on the terminal includes the work content, specific procedures, important contact information, related materials, etc. For example, the user fills in "New employee orientation procedures" in the input form. The entered information is sent to the server as an HTTP request.

[1694] Input: Job description, specific procedures, important contacts, related materials

[1695] Output: Structured task handover information sent to the server

[1696] Step 2:

[1697] Analysis and storage of handover information

[1698] Server: The received task handover information is analyzed using natural language processing technology (such as "spaCy"), and the text data is converted into structured data (such as JSON format). During the analysis process, keywords are extracted from the text and intent is understood. The analyzed data is stored in a database such as "MongoDB."

[1699] Input: Unstructured business handover information

[1700] Output: Structured business handover information (JSON format)

[1701] Step 3:

[1702] Information search and display

[1703] User: The next person in charge (User B) logs in to the server from a terminal and enters a query to search for the saved handover information. The server uses Elasticsearch to search and displays the results in HTML format. For example, if User B searches for "New Employee Orientation Procedures," the details are displayed.

[1704] Input: Search query (e.g., "new employee orientation procedures")

[1705] Output: Search results (displayed in HTML format)

[1706] Step 4:

[1707] Providing feedback

[1708] Users: If they have any questions or suggestions for improvement while performing their work, they can use their terminals to enter them into a feedback form and send it to the server. This information can be used to improve work. For example, a user might comment, "There is some material that should be added to the orientation procedures."

[1709] Input: Feedback content (text format)

[1710] Output: Feedback data sent to the server

[1711] Step 5:

[1712] Accumulating and organizing feedback

[1713] Server: The received feedback data is stored in a database. After that, multiple pieces of feedback are consolidated and organized, and redundant and duplicate information is removed. This is done using libraries such as "pandas" to build a consistent database.

[1714] Input: Feedback data (multiple inputs)

[1715] Output: Organized feedback data

[1716] Step 6:

[1717] Knowledge Base Updates

[1718] Server: Automatically updates the knowledge base based on organized data, including best practices and efficient business procedures. The information is stored in a GraphDB and made available as company-wide knowledge.

[1719] Input: Organized feedback data

[1720] Output: Updated knowledge base

[1721] Step 7:

[1722] Generate new business proposals

[1723] Server: Based on the updated knowledge base, the server automatically generates new business proposals using machine learning algorithms (e.g., Scikit-learn and TensorFlow). For example, it proposes new marketing strategies by combining marketing success stories with customer churn analysis.

[1724] Input: Updated Knowledge Base

[1725] Output: New business proposal (text format, etc.)

[1726] Step 8:

[1727] Proposal notification and evaluation

[1728] Server: Notifies the generated new business proposals to the relevant parties and distributes them via email or internal notification systems. The person in charge who receives the proposals can check the contents of the proposals on their terminals and provide evaluation comments as feedback.

[1729] Input: New business proposal

[1730] Output: Evaluation comments for the proposal

[1731] Step 9:

[1732] Improvement of the proposed algorithm

[1733] Server: Analyzes the feedback and ratings received and uses them to improve the suggestion algorithm and knowledge base. This feedback loop improves the accuracy of the system's suggestions.

[1734] Input: Feedback and Rating Comments

[1735] Output: Improved proposed algorithm and knowledge base

[1736] (Application example 1)

[1737] 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."

[1738] In modern brick-and-mortar store operations, efficient handover of operations and centralized knowledge management are important. However, conventional methods have had problems such as cumbersome collection and management of handover information and inefficient generation of new business proposals. Furthermore, there were also issues with insufficient sharing of feedback between staff and automatic generation of sales promotion plans based on accumulated knowledge.

[1739] 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.

[1740] In this invention, the server includes: means for inputting business handover information; means for analyzing the input business handover information and saving it in a database; means for searching for and displaying the analyzed business handover information; means for collecting feedback obtained during the business handover process and storing it in a database; means for analyzing the stored data and updating a knowledge base; means for automatically generating new business proposals based on the updated knowledge base; means for notifying relevant parties of the generated new business proposals and receiving their evaluations; means for analyzing the evaluations and improving the proposal algorithm and knowledge base; means for managing business information related to store operation and making it accessible via a smartphone during handover; means for building a knowledge base for store operation and automatically generating new sales promotion plans based on feedback; and means for evaluating the generated new proposals and collecting improvements. This improves the efficiency of business handover in physical stores, enables centralized management of the knowledge base, and enables automatic generation of new proposals based on feedback.

[1741] "Business handover information" refers to the information required for an employee to hand over their work to the next person in charge, including specific work content and procedures, important contact information, and related materials.

[1742] A "server" is a computer system for analyzing, storing, and managing data, and plays a role in centrally managing information that users can access.

[1743] "Natural language processing technology" is a technology that allows computers to understand, analyze, and generate natural language (language used by humans on a daily basis), and can analyze the meaning of sentences and convert them into structured data.

[1744] A "machine learning algorithm" is an algorithm that finds patterns and rules based on large amounts of data and makes predictions and classifications.

[1745] A "database" is a system for efficiently storing, searching, and managing large amounts of information.

[1746] A "knowledge base" is a database that accumulates information and know-how about a specific field or business, and is used to improve business efficiency and automate operations.

[1747] A "new business proposal" is a new idea or plan for improving operations or business processes based on accumulated data and feedback.

[1748] "Feedback" refers to information that reports opinions and areas for improvement obtained during the course of business, and is used to improve the system and generate new proposals.

[1749] A "smartphone" is a mobile phone terminal equipped with advanced computing power and communication functions, and is capable of running a variety of applications.

[1750] "Store operations" refers to all operations related to running a store, such as managing a physical store, product display, inventory management, and sales promotion.

[1751] "Building a knowledge base" means accumulating and systematically storing business-related knowledge and know-how, and using that knowledge to make business improvements and proposals.

[1752] This invention is a system for efficiently managing business handover information in a physical store, building a knowledge base related to store management, and automatically generating new sales promotion plans based on feedback. This system is implemented using a server and user terminals (e.g., smartphones).

[1753] System Program

[1754] The system has a program with the following main components:

[1755] 1. A means of entering business handover information.

[1756] 2. A means of analyzing the entered business handover information and storing it in a database.

[1757] 3. A means for searching and displaying the analyzed business handover information.

[1758] 4. A means of collecting feedback obtained during the business handover process and storing it in a database.

[1759] 5. A means of analyzing accumulated data and updating the knowledge base.

[1760] 6. A means of automatically generating new business proposals based on the updated knowledge base.

[1761] 7. A means of informing stakeholders of generated new business proposals and receiving their evaluation.

[1762] 8. A means of analyzing the evaluation and improving the proposed algorithm and knowledge base.

[1763] 9. A means of managing business information related to store operations and making it accessible via smartphone when taking over.

[1764] 10. A means of building a knowledge base for store operations and automatically generating new promotional plans based on feedback.

[1765] 11. A means of evaluating new proposals generated and collecting suggestions for improvement.

[1766] Explanation of program processing

[1767] The server receives the task handover information entered by the user (store manager or staff member) using their smartphone. The server analyzes this information using natural language processing technology (for example, Python's NLP library), converts it into structured data, and stores it in a database. The user can then use their smartphone to search for and view the stored handover information.

[1768] Feedback is collected via smartphones, and when users enter questions or suggestions for improvement they have while performing their work, the server stores them in a database. The server periodically analyzes the accumulated feedback and data and updates the knowledge base. Machine learning algorithms (e.g., scikit-learn) are used to automatically generate new sales promotion plans and business improvement proposals.

[1769] The generated new business proposals are notified to the user, who can provide ratings and comments via their smartphone. The server analyzes this feedback and uses it to improve the proposal algorithm and knowledge base.

[1770] Specific examples

[1771] For example, a store manager can input a new inventory management method on their smartphone, and when staff review it, they can provide feedback such as "the order of products is unclear," allowing the system to automatically suggest new sales based on inventory shortages.

[1772] Examples of prompts include:

[1773] The new store manager has entered the information on inventory management and sales promotions. At the same time, the staff has provided feedback on the product arrangement. Based on this, please propose a new sales promotion plan.

[1774] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1775] Step 1:

[1776] The user inputs task handover information using a smartphone. The input information includes the task content, procedures, important contact information, and related materials. The input data is sent to the server.

[1777] Step 2:

[1778] The server analyzes the received task handover information using natural language processing technology (for example, a Python NLP library). The analyzed data is converted into structured data and stored in a database. The input is raw text data, and the output is structured data.

[1779] Step 3:

[1780] The user accesses the server using a smartphone and searches for the stored handover information. The server processes the search query and displays the appropriate handover information on the screen. The input is the search query, and the output is the formatted handover information.

[1781] Step 4:

[1782] Users can input any questions or improvements they have while working on their smartphones and send them as feedback to the server, which then stores the feedback in a database. The input is raw text feedback data, and the output is the feedback data stored in the database.

[1783] Step 5:

[1784] The server periodically analyzes the accumulated feedback and task handover information and updates the knowledge base. The analysis includes data cleansing and statistical techniques. The input is the accumulated data, and the output is an updated knowledge base.

[1785] Step 6:

[1786] The server automatically generates new business proposals using a machine learning algorithm (e.g., scikit-learn) based on the updated knowledge base. The input is the updated knowledge base, and the output is the new business proposal.

[1787] Step 7:

[1788] The generated new business proposal is notified to the relevant parties via smartphone or email. The user reviews the proposal and provides feedback such as ratings and comments. The input is the new business proposal, and the output is the ratings and comments.

[1789] Step 8:

[1790] The server analyzes the received ratings and comments and improves the proposed algorithm and knowledge base. The input is the ratings and comments, and the output is the improved algorithm and knowledge base.

[1791] 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.

[1792] The system of the present invention is composed mainly of a multi-functional program that enables efficient management of business handover information and automatic generation of new business proposals, and is further combined with an emotion engine that recognizes and analyzes user emotions.

[1793] 1. Business transfer intermediation

[1794] Entering transfer information

[1795] User: A new person in charge (Employee A) uses a terminal to input task handover information into the server to hand over the task to the next person in charge (Employee B). The input information includes the task content, procedures, important contact information, and related materials. During input, the emotion engine also analyzes the user's emotions and collects emotional data about the task.

[1796] Analysis and storage of handover information

[1797] Server: Along with the emotional data analyzed by the emotion engine, the task handover information is analyzed using natural language processing (NLP) technology and stored in a database as structured data.

[1798] Information Access

[1799] User: Employee B, the new person in charge, logs in to the server using a terminal and searches for the saved handover information. The server provides search results including emotional data, allowing Employee B to understand the handover information taking emotional aspects into account.

[1800] Providing feedback

[1801] User: Employee B reports any questions or areas for improvement that arise during the course of work, as well as his or her feelings at the time, to the server via his or her terminal.

[1802] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[1803] 2. Accumulation of business knowledge

[1804] Data organization

[1805] Server: Integrates and organizes task handover information, feedback, and sentiment data provided by multiple employees, and removes redundant and duplicate information, creating a consistent database.

[1806] Knowledge Base Updates

[1807] Server: Automatically updates the knowledge base based on the organized data and sentiment data. For example, it adds sentiment data related to success stories and efficient business procedures to the knowledge base.

[1808] Auto-tagging

[1809] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[1810] Knowledge integration and new business proposal generation

[1811] Data analysis

[1812] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[1813] Generate new business proposals

[1814] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department" with "customer abandonment analysis" and related emotional data.

[1815] Proposal notification and evaluation

[1816] Server: Distributes generated new business proposals to stakeholders via email and notification systems. Uses an emotion engine to recognize users' reactions and ratings.

[1817] Collecting ratings

[1818] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[1819] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[1820] Specific examples

[1821] 1. Enter and save transfer information

[1822] User: Employee A enters the "New Employee Orientation Procedure" into the terminal, and their emotions at the time are also collected.

[1823] Server: Analyzes business information and emotion data using NLP technology and stores it in a database.

[1824] 2. Searching for and displaying information

[1825] User: Employee B searches for "New Employee Orientation Procedures."

[1826] Server: Retrieves related information along with emotion data from the database and displays it.

[1827] 3. New business proposal generation and evaluation

[1828] Server: Analyzes business and sentiment data and generates new marketing strategy proposals.

[1829] User: Receives suggestions and provides evaluation comments and sentiment data.

[1830] Server: Based on the feedback, improve the next proposed algorithm.

[1831] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[1832] The processing flow will be explained below.

[1833] Business transfer intermediation

[1834] Step 1: Enter your transfer information

[1835] User: Employee A uses a terminal to input task handover information into the server. The information to be input includes the task content, procedures, important contacts, and related materials. As the information is being input, the emotion engine analyzes the user's emotions in real time and collects emotional data.

[1836] Step 2: Analyze the handover information

[1837] Server: Analyzes the received task handover information and emotional data using natural language processing (NLP) technology. The task information is recognized as structured data and converted into a format that can be stored in a database together with the emotional data.

[1838] Step 3: Save handover information and emotion data

[1839] Server: Structured task handover information and emotion data are stored in a database and organized by category, allowing for consistent access and retrieval.

[1840] Step 4: Information Access

[1841] User: Employee B, the new employee, logs in to the server using a terminal and searches for relevant handover information, for example, "New Employee Orientation Procedures."

[1842] Server: Processes the search query, retrieves the relevant handover information and emotion data from the database, and displays them on the device in an appropriate format.

[1843] Step 5: Provide feedback

[1844] User: Employee B uses a terminal to report any questions or improvements that arise during work to the server. The emotion engine also analyzes the emotions expressed at the time.

[1845] Server: The provided feedback and sentiment data are stored in a database to help improve operations in the future.

[1846] Accumulation of business knowledge

[1847] Step 1: Organize your data

[1848] Server: Integrates and organizes handover information, feedback, and sentiment data provided by multiple employees for consistency, removes redundant and duplicate information, and stores the data in a consistent format.

[1849] Step 2: Update your knowledge base

[1850] Server: Automatically updates the knowledge base based on the organized data. For example, it adds best practices, efficient business procedures, and related emotional data to the knowledge base.

[1851] Step 3: Auto-tagging

[1852] Server: Uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data, helping users quickly find the information they need.

[1853] Knowledge integration and new business proposal generation

[1854] Step 1: Data analysis

[1855] Server: Uses machine learning algorithms to analyze regularly accumulated business and sentiment data, particularly to detect success stories, frequently occurring challenges, and the associated sentiment.

[1856] Step 2: Generate a new business proposal

[1857] Server: Based on the analysis results, the server automatically generates new business proposals by combining different business knowledge and emotional data. For example, it proposes new marketing strategies by combining "success stories from the marketing department," "customer abandonment analysis," and related emotional data.

[1858] Step 3: Proposal Notification

[1859] Server: Distributes generated new business proposals to relevant parties via email and notification systems.

[1860] Step 4: Collect ratings

[1861] User: The employee who receives the proposal checks the content of the proposal on their device and inputs emotional data along with their rating and comments into the server as feedback.

[1862] Server: The received feedback, ratings, and sentiment data are stored in a database and used to refine the proposed algorithm and knowledge base.

[1863] Specific examples

[1864] 1. Enter and save transfer information

[1865] User: Employee A enters the "New Employee Orientation Procedure" into the terminal. At that time, the emotion engine analyzes Employee A's emotions and captures them as data.

[1866] Server: Uses NLP technology to analyze business information and emotion data and store them in a database.

[1867] 2. Searching for and displaying information

[1868] User: Employee B searches for "New Employee Orientation Procedures."

[1869] Server: Retrieves related information along with emotion data from the database and displays it.

[1870] 3. New business proposal generation and evaluation

[1871] Server: Analyzes business and sentiment data and generates new marketing strategies as proposals.

[1872] User: Receives suggestions and provides evaluation comments and sentiment data.

[1873] Server: Based on the feedback, improve the next proposed algorithm.

[1874] In this way, the entire system will work together efficiently, not only making business handovers more efficient and automating new business proposals, but also enabling flexible responses that take user emotions into consideration.

[1875] Example 2

[1876] 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."

[1877] Conventional business handover systems have basic functions such as inputting, analyzing, and saving business information, but they lack consideration for user emotions. This can lead to a lack of understanding of the handover information and inappropriate new business proposals. Furthermore, it is necessary to utilize emotion data to generate more effective and appropriate new business proposals.

[1878] 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.

[1879] In this invention, the server includes means for inputting task handover information, means for analyzing the input task handover information and saving it in a database, means for searching for and displaying the analyzed task handover information, means for collecting feedback obtained during the task handover process and storing it in a database, means for analyzing the stored data and updating a knowledge base, means for automatically generating new business proposals based on the updated knowledge base, means for notifying relevant parties of the generated new business proposals and receiving their evaluations, means for analyzing the evaluations and improving the proposal algorithm and the knowledge base, means for analyzing user emotions and collecting task handover information including emotion data, means for assisting in understanding the task handover information based on the emotion data, and means for optimizing the new business proposals based on the emotion data. This enables task handover and new business proposals that take user emotions into consideration.

[1880] "Business handover information" refers to information including business content, procedures, important contact information, and related materials, and refers to all information necessary for the handover of business between personnel.

[1881] "Natural language processing technology" is a technology that analyzes text data written in natural language and understands and processes its meaning and structure. Specifically, it includes tokenization, part-of-speech tagging, grammatical analysis, etc.

[1882] A "database" refers to a collection of data that is structured so that the stored information can be efficiently managed and searched, and includes relational databases and NoSQL databases.

[1883] "Emotional energy" refers to software and algorithms that analyze a user's emotional state and record it as a number or category.

[1884] "Emotional data" refers to data that quantifies or categorizes a user's emotional state and is collected using contextual analysis and facial recognition technology.

[1885] A "knowledge base" is a database that systematically compiles important information within an organization, such as business procedures and success stories.

[1886] A "new business proposal" is a proposal for a new business idea or strategy that is generated based on current business data and emotional data.

[1887] A "machine learning algorithm" is an algorithm that learns various patterns from large amounts of data and makes future predictions and classifications. Specifically, it includes neural networks and support vector machines.

[1888] "NLP" stands for natural language processing technology and refers to the technology of understanding and processing human language.

[1889] "User" refers to a member of an organization who uses the system, specifically a business person.

[1890] A "server" refers to a computer system that receives requests from users, performs the necessary processing, operates a database, and returns the results.

[1891] "Terminal" refers to the computer or device used by a user to input and view data.

[1892] The present invention is a system for analyzing and utilizing user emotions with the aim of efficiently managing business handover information and automatically generating new business proposals. Hereinafter, an embodiment of the present invention will be described in detail.

[1893] System configuration

[1894] This system consists of the following components:

[1895] 1. User terminal: A device used for inputting information, searching, and providing feedback. This includes PCs, smartphones, tablets, etc.

[1896] 2. Server: The main computer system that processes user requests, analyzes, stores, and retrieves data, and generates new business proposals.

[1897] 3. Database: A storage system for storing task handover information, feedback, and emotion data. A relational database or NoSQL database is used.

[1898] 4. Emotion Engine: It is an algorithmic software that analyzes user emotions and collects data as numbers and categories.

[1899] 5. Natural Language Processing (NLP): Text analysis technology using Python's NLTK and spaCy.

[1900] 6. Machine learning algorithms: Data analysis and new business proposal generation algorithms using scikit-learn and TensorFlow.

[1901] Basic Operation Procedure

[1902] 1. Enter business handover information

[1903] User: The new person in charge (Employee A) enters the details of the job, procedures, important contact information, and related documents on a terminal such as a PC. At this time, the emotion engine operates and simultaneously collects the user's emotional data.

[1904] Example: Employee A enters "New Employee Orientation Procedures" and records "Anxiety" as the emotion he felt at the time.

[1905] 2. Analysis and storage

[1906] Server: The server analyzes the input task handover information using natural language processing (NLP) technology and stores it in a database as structured data, along with emotional data.

[1907] Example: Using Python's NLTK library to tokenize business content and store it in a database.

[1908] 3. Search and Display

[1909] User: The next person in charge (Employee B) logs in to the server using a terminal and searches for the necessary business handover information.

[1910] Server: The server displays the analyzed task handover information along with emotion data based on the search query.

[1911] Example: When Employee B searches for "new employee orientation procedures," the server displays related information and emotion data for "anxiety."

[1912] 4. Providing Feedback

[1913] User: Employee B reports any questions, areas for improvement, or feelings that arise during work execution via the terminal.

[1914] Server: The server stores this feedback in a database and uses it to improve operations in the future.

[1915] Example: Employee B gives feedback that "orientation is progressing slowly" and records his / her emotion at that time as "irritation."

[1916] 5. Organizing data and updating the knowledge base

[1917] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, eliminating redundancies and duplications. Updates the knowledge base based on the organized data.

[1918] Example: Consolidating duplicate "orientation procedures" information and adding it to the knowledge base as one coherent procedure.

[1919] 6. Automatic categorization and tagging

[1920] Server: Uses automatic classification and tagging functions to assign relevant keywords and categories to business and emotional data.

[1921] Example: Add tags such as "New Employee Training" and "Initial Setup" to "Orientation Procedures."

[1922] 7. Business and Emotional Data Analysis

[1923] Server: Uses machine learning algorithms to analyze the accumulated data and detect success stories, frequently occurring challenges, and associated emotions.

[1924] Example: Using scikit-learn, we will associate "customer service procedures" with emotional data on "satisfaction" as a success story.

[1925] 8. Generate new business proposals

[1926] Server: Based on the analysis results, it combines different business knowledge and emotional data to automatically generate new business proposals.

[1927] Example: Propose a new marketing strategy based on success stories from the marketing department and emotional data on "satisfaction" in customer interactions.

[1928] 9. Notification and Evaluation of Proposals

[1929] Server: Notifies the generated new business proposal to the relevant parties and receives their evaluation.

[1930] User: The parties who receive the proposal evaluate the content and provide feedback along with sentiment data.

[1931] Example: Evaluate the proposal as "useful" and record the emotion as "satisfied."

[1932] 10. Collecting ratings and improving the algorithm

[1933] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[1934] Example: Optimize the next business proposal algorithm based on collected "satisfaction" emotion data.

[1935] Prompt Sentence Examples

[1936] Below is an example of a prompt sentence.

[1937] 1. "Please enter your new employee orientation procedures. Please feel free to write down your thoughts and feelings about the job."

[1938] 2. "Please create a procedure for handing over the work to the next person in charge. Please also include your current feelings and impressions."

[1939] 3. "Please review our proposed new marketing strategy and provide feedback and sentiment data."

[1940] The above is a detailed description of the embodiment of the present invention. By using this system, the process of business handover becomes more efficient and new business proposals are optimized by taking into account the user's feelings.

[1941] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1942] Step 1: Enter business handover information

[1943] User: The new employee (Employee A) enters the job description, procedures, important contact information, and related documents using a dedicated web form or software on a PC or other device. As the information is entered, the emotion engine is activated and the user's emotional data is collected at the same time.

[1944] Input: Job details, procedures, important contacts, related documents, emotional data (e.g., anxiety, satisfaction, etc.)

[1945] Output: Task handover information and emotion data are sent to the server.

[1946] Step 2: Analyze and save the transfer information

[1947] Server: The server performs natural language processing (NLP) on the received task handover information and emotion data using Python's NLTK library and spaCy, and stores the analysis results in a database as structured data.

[1948] Input: Business handover information, emotion data

[1949] Output: The analyzed business information and emotion data are saved in a database as structured data.

[1950] Specific operation: The server first performs tokenization and part-of-speech tagging, then performs context analysis, and then stores the analysis results in a database as JSON format data.

[1951] Step 3: Find and view information

[1952] User: The next person in charge (Employee B) uses a terminal to log in to the server and search for specific task handover information.

[1953] Server: The server receives the user's search query, retrieves relevant business information and emotion data from the database, and displays them.

[1954] Input: User's search query (e.g., "new employee orientation procedures")

[1955] Output: The relevant task handover information and emotion data are displayed.

[1956] Specific operation: The server generates an SQL query based on the user's search query, searches the database, and displays the retrieved data in HTML format.

[1957] Step 4: Provide feedback

[1958] User: Employee B inputs any questions or improvements that arise during the course of work, as well as his / her feelings, through the terminal and reports them to the server.

[1959] Server: Stores the provided feedback and emotion data in a database.

[1960] Input: Feedback content, emotional data (e.g., dissatisfaction, irritation, etc.)

[1961] Output: Feedback and emotion data are stored in a database.

[1962] What happens: The user fills out the feedback form and hits the submit button. The emotion engine is then run again to analyze the emotion, which is then stored in the database along with the feedback.

[1963] Step 5: Cleanse your data and update your knowledge base

[1964] Server: Integrates and organizes task handover information, feedback, and sentiment data collected from multiple users, removes redundancies and duplicates, and updates the knowledge base.

[1965] Input: Multiple task handover information, feedback, and emotion data

[1966] Output: A cleaned and updated knowledge base

[1967] What it does: The server periodically runs data cleaning scripts to remove redundant and duplicate data. The updated data is imported into the knowledge base software.

[1968] Step 6: Auto-classification and tagging

[1969] Server: The server uses automatic classification and tagging to assign relevant keywords and categories to business and sentiment data.

[1970] Input: Organized task handover information, emotional data

[1971] Output: Classified and tagged task handover information, emotion data

[1972] What it does: Classifies data using text classification algorithms (e.g., Naive Bayes or SVM) and automatically tags it with keywords and categories.

[1973] Step 7: Analyze business and sentiment data

[1974] Server: Uses machine learning algorithms (e.g., scikit-learn and TensorFlow) to analyze accumulated business and sentiment data and detect success stories and frequently occurring issues.

[1975] Input: Business handover information, emotion data

[1976] Outputs: Reports, success stories, challenges

[1977] What it does: The server periodically processes batches of data, applies analytics algorithms to the data, and generates reports that are displayed on the dashboard.

[1978] Step 8: Generate new business proposals

[1979] Server: Based on the analysis results, it automatically generates new business proposals by combining different business knowledge and emotional data.

[1980] Input: success stories, challenges, sentiment data

[1981] Output: New business proposal

[1982] How it works: Using a generative AI model (e.g., GPT-3), new business proposals are automatically generated, and the generated proposals are then internally reviewed and optimized.

[1983] Step 9: Proposal notification and evaluation

[1984] Server: Distributes the generated new business proposals to relevant parties via email or notification systems (e.g., Slack or Microsoft Teams).

[1985] Users: The parties who receive the proposal evaluate the proposal and provide feedback along with sentiment data.

[1986] Input: New business proposal, evaluation feedback, sentiment data

[1987] Output: Evaluation results, feedback

[1988] Specific operation: The server sends emails using the SMTP protocol and sends real-time notifications using the notification system's API. Interested parties submit feedback using the evaluation form.

[1989] Step 10: Collecting ratings and improving the algorithm

[1990] Server: Improves the proposed algorithm and knowledge base based on the received feedback, ratings, and sentiment data.

[1991] Input: Rating feedback, emotion data

[1992] Output: Improved algorithms and knowledge bases

[1993] What it does: The server uses a logging system to collect feedback data, which is used as training data for the machine learning model. It then retrains the model with new data to improve it.

[1994] (Application example 2)

[1995] 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."

[1996] The task handover process in modern factories often suffers from incomplete information transmission and worker emotional stress. Furthermore, the difficulty of properly collecting employee feedback and identifying areas for improvement can hinder improvements in production efficiency. Conventional systems are unable to collect and analyze emotional data in real time, identify worker stress points, and make immediate recommendations base...

Claims

1. A means for inputting business handover information; A means for analyzing the input business handover information and storing it in a database; A means for searching and displaying the analyzed business handover information; A means of collecting feedback obtained during the business handover process and storing it in a database; a means of analyzing the accumulated data and updating the knowledge base; A means for automatically generating new business proposals based on the updated knowledge base; A means for notifying stakeholders of the generated new business proposals and receiving their evaluations; A means to analyze the evaluation and improve the proposed algorithms and knowledge base; A system including:

2. The system of claim 1 , wherein the task handover information is analyzed using natural language processing technology.

3. The system of claim 1 , wherein the system automatically generates new business proposals using machine learning algorithms.

Images