system

Abstract

We provide the system. [Solution] A method for automatically generating proposals suitable for current business projects by collecting past proposal examples and proposal data, analyzing them based on machine learning algorithms, and A method for presenting a proposal template to the user and automatically customizing the template based on the information entered, A means of presenting automatically generated suggestions to the user and allowing the user to input corrections or additional information, A method for automatically suggesting countermeasures for complaints by searching a database of past complaint handling cases, A method for creating a database of the skills and experience of internal employees, and for searching for and suggesting the most suitable candidates, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In a modern corporate environment, there is a strong demand for the efficiency of business processes and the proper sharing of knowledge. Furthermore, since it is also important to respond quickly and appropriately to claims from customers and to identify the optimal consultation sources within the company, it is necessary to comprehensively solve these problems. However, with the current systems and processes, past case information and claim cases cannot be effectively utilized, and a lot of wasted time and labor are often spent manually. Therefore, there is a need to develop a new system that realizes the efficiency of business, the quick response to claims, and the optimization of internal consultation sources. 【Means for Solving the Problems】 【0005】 This invention provides a system that automatically generates proposals suitable for current business cases by collecting past proposal examples and proposal data and analyzing them based on machine learning algorithms. Furthermore, it presents proposal templates to the user and automatically customizes the templates based on the information entered by the user, supporting efficient proposal creation. In addition, this system searches a database of past complaint handling cases and quickly provides the optimal response to complaints. Moreover, it has a function to database the skills and experience of internal employees, search for the most suitable candidate, and propose them to the user. By searching the internal skills database based on the content the user wants to consult and presenting a list of the most suitable person, it improves the efficiency of operations. 【0006】 "Past proposal examples" refers to specific examples and achievements related to proposal activities conducted in the past. 【0007】 "Proposal data" refers to the information contained in an already created proposal and its structured record. 【0008】 A "machine learning algorithm" refers to a computational procedure that analyzes large amounts of data, automatically learns patterns and regularities, and makes predictions and decisions about the future. 【0009】 A "user" refers to someone who uses the system to perform tasks such as information retrieval, proposal creation, and consultation. 【0010】 A "template" refers to a standard form used to organize and describe information in a specific way, such as in a proposal or report. 【0011】 "Complaint handling case examples" refer to information that records past responses to customer complaints and requests, as well as the events themselves. 【0012】 A "database" refers to an electronic collection of data and information that is systematically stored and made searchable and usable. 【0013】 A "skills database" refers to a specific information system that compiles information on an employee's skills and experience, and uses it for searching and matching purposes. 【0014】 A "candidate for person in charge" refers to an employee who is proposed as being suitable for handling specific tasks or matters requiring consultation. [Brief explanation of the drawing] 【0015】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined. 【Mode for Carrying Out the Invention】 【0016】 Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0017】 First, the terms used in the following description will be explained. 【0018】 In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc. 【0019】 In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0020】 In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc. 【0021】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0022】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0023】 [First Embodiment] 【0024】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0025】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0026】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0027】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0028】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0029】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0030】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0031】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0032】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0033】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0034】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0035】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0036】 This system is an AI-assisted platform designed to improve operational efficiency and knowledge sharing within companies, as well as to expedite complaint handling and optimize consultations. The specific implementation details are described below. 【0037】 First, the server collects past proposal examples and proposal data accumulated within the company. This data is then analyzed using machine learning algorithms to extract success factors and customer response patterns for each project. Using these analysis results, the server automatically generates proposal content and structure suitable for the current project. 【0038】 The terminal provides the user with a proposal template and prompts them to enter basic information. The user can then customize the template by combining the information they enter with automated suggestions provided by the server. This process allows the user to create proposals efficiently and effectively. 【0039】 In handling complaints, the server searches a database for past complaint handling cases. It has the functionality to analyze solutions to similar complaints and suggest the most appropriate course of action. Users can receive this information in real time through their terminals, enabling rapid complaint resolution. After a complaint is resolved, users provide feedback to the system as learning data by entering it into their terminals. 【0040】 To optimize the consultation process, the server utilizes the company's skills database to search for the most suitable candidates. When a user enters their consultation request, a list of candidates is provided based on their relevant skills and past experience. This information is displayed to the user on their device, allowing them to select a consultant and begin communication as needed. 【0041】 As a concrete example, consider a scenario where a user creates a proposal for a new product. By entering basic product information into the terminal, a draft proposal is automatically generated based on analysis results from the server. The user reviews this draft and finalizes it as the final proposal. Another concrete example of handling complaints is that for customer complaints that occur at night, a quick response can be obtained through the terminal's chatbot function. This allows the user to resolve problems quickly. 【0042】 The following describes the processing flow. 【0043】 Step 1: 【0044】 The server collects past proposal examples and proposal data from the company's database. This includes successful proposal details and the history of similar projects, preparing the data for analysis. 【0045】 Step 2: 【0046】 The server analyzes the collected data using machine learning algorithms. This analysis extracts commonalities and success factors from successful proposals, and identifies the elements and structure of those proposals. 【0047】 Step 3: 【0048】 The terminal displays a standard proposal template to the user. This template shows the basic structure of a proposal, and the user can enter the necessary information. 【0049】 Step 4: 【0050】 The user enters basic information necessary for creating a proposal (e.g., product name, target audience, expected results, etc.) into the terminal. The system then collects information relevant to the specific project. 【0051】 Step 5: 【0052】 The server automatically generates a proposal by combining the user's input information with the analysis results obtained in step 2. The generated proposal is then customized and incorporated into a proposal template. 【0053】 Step 6: 【0054】 The terminal presents the user with a customized draft proposal. The user can review this draft proposal and enter any necessary modifications or additions. 【0055】 Step 7: 【0056】 After the user completes the revisions, the terminal saves the finalized proposal, and the system records this information in the proposal database for use in future proposal generation. 【0057】 This process will streamline business processes and expedite proposal creation. 【0058】 (Example 1) 【0059】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0060】 The aim is to streamline operations and improve workflow by accelerating information processing to improve efficiency and facilitate proper knowledge sharing within companies, and by automating the rapid implementation of issues and the selection of the most suitable personnel. 【0061】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0062】 This invention includes a server that collects past information examples and document data, analyzes them based on a data processing algorithm, and automatically generates information suitable for current business operations; a server that presents document templates to users and automatically customizes the templates based on the input data; and a server that presents the automatically generated information content to users and allows users to input corrections and additional information. This improves the efficiency of operations within a company and enables the sharing of appropriate knowledge and information. 【0063】 "Information case data" refers to data on cases such as proposals and complaint handling that a company or organization has accumulated in the past. 【0064】 "Document data" refers to all data, including various forms of document information created within a company, such as proposals, reports, and complaint handling records. 【0065】 A "data processing algorithm" is a set of computational procedures for analyzing and processing digital information, and in this context, it specifically refers to data analysis methods that utilize machine learning. 【0066】 "Job description" refers to information about the business processes a company performs on a daily basis and the projects it is responsible for. 【0067】 "Information generation" means constructing new insights and proposals obtained through data processing. 【0068】 A "document template" refers to a pre-formatted document design that is prepared in advance for use as a template for proposals, reports, and other documents. 【0069】 "User" refers to an individual or member of an organization who operates or utilizes the system to perform their duties. 【0070】 "Automatically customizing templates" means dynamically changing the suggested content and document layout based on user input. 【0071】 "Information content" refers to a series of data, including data obtained through analysis and information generation, as well as proposals and solutions. 【0072】 "Problem-solving" refers to a series of processes in which a company finds and implements appropriate solutions to problems and challenges it faces. 【0073】 "Person in charge" refers to the individual responsible for implementing a specific task, project, or countermeasure. 【0074】 This invention provides an AI-assisted platform for improving operational efficiency within a company. Specifically, it includes functions for automatically generating proposals by collecting and analyzing past information, case studies, and document data; providing users with proposal templates and automatically customizing them; and presenting solutions to challenges. Furthermore, it also includes a function to identify the most suitable personnel candidates by utilizing a knowledge database of personnel within the organization. 【0075】 The server collects information case studies and document data from database management systems such as MySQL® and PostgreSQL. Python machine learning libraries (e.g., scikit-learn and TENSORFLOW®) are used for data processing. This allows the server to analyze success factors based on past data and generate proposals suitable for the current project. The algorithms used in the generation process may include classification and regression analysis. 【0076】 The terminal provides the user with a document template through an interface using HTML and JavaScript (registered trademark). The user then inputs basic information and customizes the template. Automatically generated suggestions from the server are helpful during the customization process. 【0077】 In the complaint handling function, the server rapidly searches past cases using technologies such as ElasticSearch (registered trademark), generates countermeasures from the analysis results, and presents them to the user via the terminal. This function enables quick and accurate problem resolution. After the problem is resolved, the user inputs feedback, which the server stores as training data. 【0078】 To optimize the consultation process, the server uses a skills database to search for the most suitable consultant. Based on the user's input, it evaluates relevant skills and past experience, and presents appropriate candidates on the user's device. The user can then select a consultant based on this information and begin the necessary consultation. 【0079】 As a concrete example, consider a scenario where a user is creating a proposal for a new product. After entering basic product information into the terminal, the server automatically generates a draft proposal based on the analysis results. The user then uses this draft to complete the final proposal. Another concrete example of handling complaints is the ability to instantly obtain solutions to complaints that arise during the night via the terminal's interface, enabling appropriate action. A prompt message such as, "I want to create a proposal for a new product's promotion strategy. Please provide an automatically generated template based on past success stories," allows the user to efficiently carry out their work. 【0080】 Thus, this system utilizes AI technology to streamline operations and supports rapid response and optimal knowledge transfer. 【0081】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0082】 Step 1: 【0083】 The server collects historical information, case studies, and document data from the company's internal database. Database connection information is used as input. After data collection, data analysis begins using a Python machine learning library. Specifically, past success factors are extracted using a classification algorithm, and case studies of complaint handling are analyzed. The output is analysis results that serve as material for generating proposals suitable for current business operations. 【0084】 Step 2: 【0085】 The terminal provides the user with a document template. The input includes basic information defined by the user. The user then inputs the necessary information through the interface based on the provided template. Based on this input, the template is automatically customized. The output is the first draft of the customized proposal. 【0086】 Step 3: 【0087】 The server automatically generates detailed proposal content using a generative AI model based on input data received from the user and an initial draft template. User data and template information are used as input. Data processing is performed by the generative AI model, and the proposal content is automatically customized. The server returns a completed draft proposal as output. 【0088】 Step 4: 【0089】 The terminal presents the user with a draft proposal sent from the server. The user reviews this draft and inputs any necessary revisions or additional information through the interface. Input actions include pointing and clicking on the areas that need revision. The output is the revised and completed proposal by the user. 【0090】 Step 5: 【0091】 The server searches for complaint handling cases and suggests solutions based on new complaint information entered by the user. The input includes detailed complaint information provided by the user. Data processing utilizes similarity searches with past data and an automated recommendation engine. The output is the recommended solution. 【0092】 Step 6: 【0093】 The server utilizes the organization's skills database to search for the most suitable representative based on the user's inquiry. Input requires information on the inquiry and expected skills. Data processing includes skill matrix matching. The output is a list of potential representatives, presented to the user via a terminal. 【0094】 This process allows organizations to efficiently prepare proposals and handle complaints, and to quickly find the most suitable consultant. 【0095】 (Application Example 1) 【0096】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0097】 Traditional business processes presented challenges due to the significant time and effort required for tasks such as proposal writing, complaint handling, and selecting the most suitable personnel. Logistics centers, in particular, demanded optimized delivery routes and rapid complaint resolution, but lacked the systems necessary to efficiently perform these tasks. Furthermore, effectively utilizing feedback within these processes and incorporating it into system improvements proved difficult. 【0098】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0099】 In this invention, the server includes means for collecting past business cases and analyzing them with an algorithm, means for presenting proposal templates to individuals and automatically adapting them, and means for individuals to modify or add to the generated proposals. This enables the suggestion of efficient delivery routes, the presentation of complaint solutions, and the selection of the most suitable personnel. 【0100】 "Business case studies" refer to a collection of specific information and data related to past work and projects within a company. 【0101】 An "algorithm" is a set of procedures or calculation methods for solving a problem, and is particularly used in machine learning to analyze patterns in data. 【0102】 A "proposal template" provides the basic structure and format for creating business proposals and plans. 【0103】 "Individuals" refers to those who use this system to create proposals or handle complaints, and generally includes employees or staff. 【0104】 A "delivery route" refers to the path or method by which goods or items are transported from their origin to their destination. 【0105】 "Complaint resolution" refers to methods and means for appropriately responding to and resolving customer complaints and problem reports. 【0106】 A "person in charge" refers to a staff member or individual who is responsible for carrying out a specific task or project. 【0107】 To implement this invention, a system is primarily required that involves a server, a terminal, and a user. 【0108】 The server collects past business case data from a database within the company and analyzes this data using machine learning algorithms (such as Python's scikit-learn). This analysis automatically generates proposals optimized for ongoing business operations. This process involves data preprocessing and feature extraction, and the development of optimized proposals using a generative AI model (e.g., GPT-3®). 【0109】 The device provides the user with a generated suggestion template and features a UI that allows the user to directly input or modify information. This interface is designed for ease of use using React Native. It also displays the generated suggestion content and offers the flexibility to add comments or make modifications to it. 【0110】 Users review the generated suggestions through the terminal interface and input corrections or additional information as needed. This feedback is returned to the server, and the system uses this information to make even more accurate suggestions. In the event of a complaint, users can easily receive solutions on their terminal. The server has a database of past complaint handling cases, allowing it to quickly suggest the best solution from similar cases. 【0111】 As a concrete example, consider a case where a product is not delivered on schedule. The user can quickly receive solutions based on similar past cases via their device. An example of a prompt message in this case would be: "Please suggest the best alternative route to resolve the delay in this delivery route. Please summarize the analysis results based on similar past cases." 【0112】 Thus, this invention streamlines business processes and provides comprehensive support from proposal creation to handling customer complaints. 【0113】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0114】 Step 1: 【0115】 The server collects past business case data from the company's database. The collected data includes proposal content, complaint handling examples, and skill information of the individuals involved. This data is used to identify patterns in business operations and successful cases in complaint handling. 【0116】 Step 2: 【0117】 The server analyzes the collected data using a machine learning algorithm (using Python's scikit-learn) and automatically generates proposals that are suitable for current business projects. The input data includes past business cases, and the output is an optimized proposal template. This process involves data preprocessing, feature selection, and model application, and generates the document using a generative AI model (e.g., GPT-3). 【0118】 Step 3: 【0119】 The terminal provides the user with an automatically generated proposal template and displays an interface that allows the user to directly input and edit information. The input at this stage consists of the user's modifications and additions, and the output is the final, customized proposal. The user's actions include adjusting input values ​​and adding comments. 【0120】 Step 4: 【0121】 The server records the generated proposals and user feedback, storing them as training data for future analysis. This input feedback helps the system make more accurate proposals in subsequent analyses. The output is an updated proposal analysis model. The server performs this process automatically, improving the quality of future proposals. 【0122】 Step 5: 【0123】 When a claim arises, the server searches its database and extracts the best solution from similar past claim handling cases. Based on the input claim information, the output is a list of recommended solutions. The server generates this list and transfers it to the terminal in real time. 【0124】 Step 6: 【0125】 Users quickly handle complaints through their terminals based on the solutions presented. Inputs include the results of implementing the selected solution and any new feedback, while output confirms the completion of the complaint resolution. Users proceed through this process, making adjustments as needed. 【0126】 This type of system processing leads to increased efficiency in business operations. 【0127】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0128】 This invention aims to enable more humane and accurate responses by combining an emotion engine with an AI-based business efficiency system to analyze the user's emotional state. This system analyzes the user's emotions in real time and provides suggestions, complaint handling, and even suggests internal contacts for consultation based on the results. 【0129】 First, the server uses machine learning algorithms to analyze past proposal examples and proposal data to generate proposals tailored to the current project. Additionally, an emotion engine built into the server analyzes the user's emotional state based on their input. For example, if the user is feeling stressed, the tone of the proposal can be adjusted to be more encouraging. 【0130】 In handling complaints, the terminal uses an emotion engine to analyze the emotional elements of user complaints and feedback, and the server automatically proposes emotionally sensitive solutions based on the analysis results. This allows for faster and more effective complaint resolution, thereby improving customer satisfaction. 【0131】 Furthermore, when suggesting internal contacts, the server selects the most appropriate person from the database based on the user's emotional state. For example, if the user is feeling stressed, a person skilled in comfortable communication will be suggested first. 【0132】 For example, when a user creates a proposal for a new project, the emotion engine on the device analyzes the user's input and incorporates necessary adjustments into the proposal. This process enables the user to create an accurate proposal that takes their own emotions into account. Furthermore, in the event of a complaint, the device's emotion analysis provides flexible solutions tailored to the customer's frustration, which can be used to quickly resolve the problem. 【0133】 In this way, by incorporating an emotion engine, this system improves the quality and efficiency of work and supports a more human-centered way of working. 【0134】 The following describes the processing flow. 【0135】 Step 1: 【0136】 Users input information into a terminal for creating proposals and handling complaints. This information includes details about the case and data indicating their current emotional state. 【0137】 Step 2: 【0138】 The device sends the input data to an emotion engine, which analyzes the user's emotional state in real time. The analysis results include emotional information such as whether the user is nervous, happy, or stressed. 【0139】 Step 3: 【0140】 The server uses machine learning algorithms to analyze past proposal examples and proposal data based on the analyzed sentiment data, and automatically generates proposals suitable for the current business project. During this process, the tone and style of the proposal are adjusted to match the user's emotional state. 【0141】 Step 4: 【0142】 The server searches a database of complaint handling cases and automatically suggests the optimal complaint handling solution, taking into account the user's emotions. This suggestion is based on the results of emotion analysis, providing a more flexible and empathetic approach. 【0143】 Step 5: 【0144】 The terminal automatically generates proposals and complaint handling strategies and presents them to the user. The user reviews these and enters any necessary corrections or additional information. 【0145】 Step 6: 【0146】 The server saves user-submitted revised proposals and countermeasures, accumulating them as training data for the emotion engine. This improves the system's accuracy and allows for better application to future proposals and countermeasures. 【0147】 This approach allows the system to consider user emotions and provide more humane and effective business support. 【0148】 (Example 2) 【0149】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0150】 Conventional business support systems have a problem in that, while automating business efficiency improvements, they have difficulty considering emotional factors in their suggestions and responses, resulting in a lack of human involvement. As a result, users cannot receive appropriate support that takes their emotional state into account, and countermeasures become uniform, which can lead to a lack of improvement in customer satisfaction and the quality of work. 【0151】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0152】 This invention includes a server that collects past business cases and business data, analyzes them based on a data analysis algorithm, and automatically generates proposals suitable for current business operations; a server that uses an emotion analysis system to analyze the user's emotional state and adjusts proposals based on that emotional state; and a server that stores the abilities and experience of personnel within the organization as data, searches for and proposes the most suitable candidate. This enables flexible and accurate proposals and responses that take into account the user's emotional state, thereby improving the efficiency and quality of operations. 【0153】 A "data analysis algorithm" is a computational method used to analyze past business cases and business data to identify specific patterns and relationships. 【0154】 An "emotion analysis system" is a mechanism that automatically analyzes the user's emotional state based on their input and makes appropriate suggestions and adjustments based on that analysis. 【0155】 A "data storage device" is a system that retains business-related information and the skills and experience of personnel within an organization over the long term, making it searchable and usable as needed. 【0156】 "Automatic proposal generation" is a process that automatically creates proposals suitable for current operations based on past business data. 【0157】 "Responsible person selection" is the process of using the organization's internal talent database to find the most suitable person for the user's needs and circumstances. 【0158】 In this invention, a server, terminal, and user collaborate to build a system that improves work efficiency. The server plays a central role in collecting past work cases and data and performing analysis using data analysis algorithms. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used for data analysis. In addition, an emotion analysis system is incorporated to analyze the user's emotional state from input data. Natural language processing technology is applied to the emotion analysis to automatically extract emotions from text. 【0159】 The terminal functions as an interface for receiving data input from users. When users input work-related information or feedback into the terminal, that information is sent to the server. Based on the sentiment analysis results, templates are automatically adjusted and suggestions are automatically generated as needed. 【0160】 Users can review suggestions presented by the system via their terminal and input any necessary modifications or additional information. This interaction enables more personalized business suggestions and complaint handling. 【0161】 As a concrete example, consider a scenario where a proposal for a new product is created. In this case, the server analyzes past proposal examples and analyzes the user's emotions from their input data. For example, if the user is feeling stressed, the proposal can be structured with an encouraging tone. This adjustment helps in the process where the server-generated proposal is presented to the user through their terminal, and the user completes the proposal based on it. 【0162】 An example of a prompt message would be, "Analyze the user's emotions in the new project proposal and generate feedback for the proposal." This invention aims not only to improve work efficiency but also to enable flexible responses that take user emotions into account, thereby enhancing customer satisfaction. 【0163】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0164】 Step 1: 【0165】 Users input work-related information and feedback into the terminal. The terminal collects this input data and sends it to the server. The input data includes comments and questions in text format. Specifically, the terminal receives input through the user interface, converts it into a processable format, and prepares it for transfer to the server. 【0166】 Step 2: 【0167】 The server receives data sent from the terminal. Here, an emotion analysis system is used to analyze the data and identify the user's emotional state. Specifically, natural language processing techniques are used to analyze what emotions the writer of the input text is expressing (e.g., joy, anger, anxiety). The input is the user's text data, and the output is the analyzed emotional state. 【0168】 Step 3: 【0169】 The server uses the results of sentiment analysis to process past business data and proposal examples with a data analysis algorithm, automatically generating proposals suitable for the current situation. In this process, a machine learning framework is utilized to evaluate the correlation between the input information and past data. The output is a proposal optimized for the user's situation. Specifically, the server searches a database of past examples and generates proposals while comparing them with similar cases. 【0170】 Step 4: 【0171】 The generated suggestions are adjusted in tone according to the user's emotional state. For example, if the user is showing signs of stress, the server adjusts the suggestions to include encouraging elements. The input is the analysis results and generated suggestions, and the output is the adjusted suggestions. 【0172】 Step 5: 【0173】 The terminal presents the user with a refined proposal sent from the server. The user can review it and add their own comments as needed. Specifically, the terminal displays the received data on the screen and provides an editable interface for the user. The input is the refined proposal, and the output is the final proposal including the user's feedback. 【0174】 Step 6: 【0175】 The server receives user feedback, stores it in a database, and uses it as training data for future AI models. This allows the system to make increasingly sophisticated and adaptive suggestions over time. Specifically, the server analyzes the received feedback and integrates it into the database. The input is user feedback, and the output is updated training data. 【0176】 (Application Example 2) 【0177】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0178】 In modern customer service and business proposals, accurately understanding the user's emotions and responding quickly and effectively is essential. However, conventional systems often failed to analyze emotions, resulting in purely mechanical responses. This led to decreased customer satisfaction and a lack of improvement in the quality of proposals. This invention aims to simultaneously achieve empathetic customer service and improved quality of business proposals. 【0179】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0180】 This invention includes a server that collects past proposal examples and proposal document data, analyzes them based on machine learning techniques, and automatically generates proposals suitable for current business cases; a server that analyzes the user's emotional state in real time and optimizes business responses in a human-like manner based on the analysis results; and a server that analyzes emotions in customer interactions and proposes customer service methods corresponding to specific emotional states. This enables accurate business proposals that take the user's emotions into consideration and achieves higher customer satisfaction. 【0181】 "Example proposals" refer to past business proposals and serve as the basic data for the system to generate new proposals. 【0182】 "Machine learning techniques" are technologies that use large amounts of data to improve algorithms and make predictions and decisions, and are applied to proposals and sentiment analysis. 【0183】 "Emotional state" refers to the psychological state of the user or customer, and is classified into elements such as anger, happiness, and surprise. 【0184】 "Analysis results" refer to the outcomes obtained after analysis based on data and input information, and are used to optimize business operations. 【0185】 A "business case" refers to a specific task or project related to a particular business, and is the subject of the system's proposal generation process. 【0186】 "Automatic generation" is a term that refers to the process by which a system creates proposals and countermeasures based on a specific algorithm without human intervention. 【0187】 "Customer satisfaction" is an indicator that shows the degree of customer satisfaction with the services and responses provided, and is a measure of business success. 【0188】 A "proposal document template" is a standard document template used when submitting a proposal, and its format is automatically adjusted based on the input information. 【0189】 "Optimization" refers to refining methods and processes to obtain the best possible results under certain conditions, and is a means of maximizing the efficiency and effectiveness of operations. 【0190】 The "analysis mechanism" refers to the devices or programs installed within the system to analyze the input data, and is the part responsible for processing emotions and suggested content. 【0191】 To realize the embodiments of this invention, a system consisting of a server, a terminal, and a user is constructed. The server collects proposal examples and proposal document data and analyzes them using machine learning techniques. Specifically, it utilizes machine learning models from cloud service providers (e.g., Microsoft® Azure®) to generate proposals suitable for current business operations in real time based on historical data. 【0192】 The terminal acts as an interface with the user and is intended for use on smart devices. It utilizes a real-time analysis engine to analyze the user's emotional state based on the input information provided. Furthermore, it analyzes data collected through the device's built-in camera or microphone, and displays information that prompts business suggestions and customer service based on the analysis results. 【0193】 As a concrete example, consider a scenario where a user is handling customer service. If the user detects customer frustration through their terminal, the server uses a machine learning model based on the sentiment analysis results to generate encouraging suggestions and immediately present actionable solutions on the terminal. This enables the user to respond quickly and effectively, thereby improving customer satisfaction. 【0194】 Examples of prompt statements include the following: 【0195】 "Customer facial expressions and emotional scores: 【0196】 Anger: 0.7 【0197】 Happiness: 0.1 【0198】 Surprise: 0.1 【0199】 Sadness: 0.1 【0200】 Based on this emotional data, please suggest an appropriate customer service style. 【0201】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0202】 Step 1: 【0203】 The server collects past proposal examples and proposal document data from a database. This database contains historical information on business proposals and customer interactions. The server collects this information as input and analyzes it using machine learning algorithms to generate proposals suitable for the current business case. The output is a list of recommended proposals. 【0204】 Step 2: 【0205】 The device operates on a smart device and acquires input information from the user. This input information is collected as audio and image data through the device's camera and microphone. The device uses a real-time analysis engine to analyze this data for emotional content. From the data acquired as input, it outputs an analysis result representing the user's emotional state. This output includes emotional scores such as anger and happiness. 【0206】 Step 3: 【0207】 The server receives the results of the emotion analysis sent from the terminal. Given an emotion score as input, the server compares this with an existing database of countermeasures used in the analysis and outputs appropriate work responses and customer service methods. This generates countermeasures and styles of encouragement tailored to specific emotional states, which are then sent to the terminal. 【0208】 Step 4: 【0209】 The terminal visually or audibly presents the user with suggestions and customer service methods provided by the server. Specifically, information guiding the user to the optimal action is displayed via the display or speaker. The output in this step consists of concrete action suggestions that the user can easily implement. 【0210】 The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data. 【0211】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0212】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0213】 [Second Embodiment] 【0214】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0215】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0216】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0217】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0218】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0219】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0220】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0221】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0222】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0223】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0224】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0225】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0226】 This system is an AI-assisted platform designed to improve operational efficiency and knowledge sharing within companies, as well as to expedite complaint handling and optimize consultations. The specific implementation details are described below. 【0227】 First, the server collects past proposal examples and proposal data accumulated within the company. This data is then analyzed using machine learning algorithms to extract success factors and customer response patterns for each project. Using these analysis results, the server automatically generates proposal content and structure suitable for the current project. 【0228】 The terminal provides the user with a proposal template and prompts them to enter basic information. The user can then customize the template by combining the information they enter with automated suggestions provided by the server. This process allows the user to create proposals efficiently and effectively. 【0229】 In handling complaints, the server searches a database for past complaint handling cases. It has the functionality to analyze solutions to similar complaints and suggest the most appropriate course of action. Users can receive this information in real time through their terminals, enabling rapid complaint resolution. After a complaint is resolved, users provide feedback to the system as learning data by entering it into their terminals. 【0230】 To optimize the consultation process, the server utilizes the company's skills database to search for the most suitable candidates. When a user enters their consultation request, a list of candidates is provided based on their relevant skills and past experience. This information is displayed to the user on their device, allowing them to select a consultant and begin communication as needed. 【0231】 As a concrete example, consider a scenario where a user creates a proposal for a new product. By entering basic product information into the terminal, a draft proposal is automatically generated based on analysis results from the server. The user reviews this draft and finalizes it as the final proposal. Another concrete example of handling complaints is that for customer complaints that occur at night, a quick response can be obtained through the terminal's chatbot function. This allows the user to resolve problems quickly. 【0232】 The following describes the processing flow. 【0233】 Step 1: 【0234】 The server collects past proposal examples and proposal data from the company's database. This includes successful proposal details and the history of similar projects, preparing the data for analysis. 【0235】 Step 2: 【0236】 The server analyzes the collected data using machine learning algorithms. This analysis extracts commonalities and success factors from successful proposals, and identifies the elements and structure of those proposals. 【0237】 Step 3: 【0238】 The terminal displays a standard proposal template to the user. This template shows the basic structure of a proposal, and the user can enter the necessary information. 【0239】 Step 4: 【0240】 The user enters basic information necessary for creating a proposal (e.g., product name, target audience, expected results, etc.) into the terminal. The system then collects information relevant to the specific project. 【0241】 Step 5: 【0242】 The server automatically generates a proposal by combining the user's input information with the analysis results obtained in step 2. The generated proposal is then customized and incorporated into a proposal template. 【0243】 Step 6: 【0244】 The terminal presents the user with a customized draft proposal. The user can review this draft proposal and enter any necessary modifications or additions. 【0245】 Step 7: 【0246】 After the user completes the revisions, the terminal saves the finalized proposal, and the system records this information in the proposal database for use in future proposal generation. 【0247】 This process will streamline business processes and expedite proposal creation. 【0248】 (Example 1) 【0249】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0250】 The aim is to streamline operations and improve workflow by accelerating information processing to improve efficiency and facilitate proper knowledge sharing within companies, and by automating the rapid implementation of issues and the selection of the most suitable personnel. 【0251】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0252】 This invention includes a server that collects past information examples and document data, analyzes them based on a data processing algorithm, and automatically generates information suitable for current business operations; a server that presents document templates to users and automatically customizes the templates based on the input data; and a server that presents the automatically generated information content to users and allows users to input corrections and additional information. This improves the efficiency of operations within a company and enables the sharing of appropriate knowledge and information. 【0253】 "Information case data" refers to data on cases such as proposals and complaint handling that a company or organization has accumulated in the past. 【0254】 "Document data" refers to all data, including various forms of document information created within a company, such as proposals, reports, and complaint handling records. 【0255】 A "data processing algorithm" is a set of computational procedures for analyzing and processing digital information, and in this context, it specifically refers to data analysis methods that utilize machine learning. 【0256】 "Job description" refers to information about the business processes a company performs on a daily basis and the projects it is responsible for. 【0257】 "Information generation" means constructing new insights and proposals obtained through data processing. 【0258】 A "document template" refers to a pre-formatted document design that is prepared in advance for use as a template for proposals, reports, and other documents. 【0259】 "User" refers to an individual or member of an organization who operates or utilizes the system to perform their duties. 【0260】 "Automatically customizing templates" means dynamically changing the suggested content and document layout based on user input. 【0261】 "Information content" refers to a series of data, including data obtained through analysis and information generation, as well as proposals and solutions. 【0262】 "Problem-solving" refers to a series of processes in which a company finds and implements appropriate solutions to problems and challenges it faces. 【0263】 "Person in charge" refers to the individual responsible for implementing a specific task, project, or countermeasure. 【0264】 This invention provides an AI-assisted platform for improving operational efficiency within a company. Specifically, it includes functions for automatically generating proposals by collecting and analyzing past information, case studies, and document data; providing users with proposal templates and automatically customizing them; and presenting solutions to challenges. Furthermore, it also includes a function to identify the most suitable personnel candidates by utilizing a knowledge database of personnel within the organization. 【0265】 The server collects information, case studies, and document data from database management systems such as MySQL and PostgreSQL. Python machine learning libraries (e.g., scikit-learn and TensorFlow) are used for data processing. This allows the server to analyze success factors based on past data and generate proposals suitable for the current project. The algorithms used in the generation process may include classification and regression analysis. 【0266】 The terminal provides the user with a document template through an interface using HTML and JavaScript. The user then inputs basic information and customizes the template. Automatically generated suggestions from the server are helpful during the customization process. 【0267】 In the complaint handling function, the server rapidly searches past cases using technologies such as Elasticsearch, generates countermeasures from the analysis results, and presents them to the user via the terminal. This function enables quick and accurate problem resolution. After the problem is resolved, the user inputs feedback, which the server stores as training data. 【0268】 To optimize the consultation process, the server uses a skills database to search for the most suitable consultant. Based on the user's input, it evaluates relevant skills and past experience, and presents appropriate candidates on the user's device. The user can then select a consultant based on this information and begin the necessary consultation. 【0269】 As a concrete example, consider a scenario where a user is creating a proposal for a new product. After entering basic product information into the terminal, the server automatically generates a draft proposal based on the analysis results. The user then uses this draft to complete the final proposal. Another concrete example of handling complaints is the ability to instantly obtain solutions to complaints that arise during the night via the terminal's interface, enabling appropriate action. A prompt message such as, "I want to create a proposal for a new product's promotion strategy. Please provide an automatically generated template based on past success stories," allows the user to efficiently carry out their work. 【0270】 Thus, this system utilizes AI technology to streamline operations and supports rapid response and optimal knowledge transfer. 【0271】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0272】 Step 1: 【0273】 The server collects historical information, case studies, and document data from the company's internal database. Database connection information is used as input. After data collection, data analysis begins using a Python machine learning library. Specifically, past success factors are extracted using a classification algorithm, and case studies of complaint handling are analyzed. The output is analysis results that serve as material for generating proposals suitable for current business operations. 【0274】 Step 2: 【0275】 The terminal provides the user with a document template. The input includes basic information defined by the user. The user then inputs the necessary information through the interface based on the provided template. Based on this input, the template is automatically customized. The output is the first draft of the customized proposal. 【0276】 Step 3: 【0277】 Based on the input data received from the user and the draft template, the server automatically generates detailed proposal content using a generative AI model. The user's data and template information are used as input. Data processing is executed by the generative AI model, and the proposal content is automatically customized. As output, a completed proposal draft is returned from the server. 【0278】 Step 4: 【0279】 The terminal presents the proposal draft sent from the server to the user. The user checks this draft and inputs any necessary corrections or additional information through the interface. The input operation includes clicking on the points for correction. The output is the proposal document revised and completed by the user. 【0280】 Step 5: 【0281】 The server searches for claim response cases and presents countermeasures based on the new claim information input by the user. The input includes the detailed information of the claims provided by the user. Similarity search with past data and an automatic recommendation engine are used for data processing. The output is the recommended countermeasures. 【0282】 Step 6: 【0283】 The server utilizes the skill database within the organization to search for the most suitable person in charge based on the user's consultation content. As input, the consultation content and the expected skill information are required. Data calculation includes matching processing of the skill matrix. The output is a list of candidate persons in charge, which is presented to the user through the terminal. 【0284】 Through this processing flow, the organization can efficiently create proposal documents and handle claims, and quickly find the most suitable consultation source. 【0285】 (Application Example 1) 【0286】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal". 【0287】 In the conventional business process, there were problems such as the creation of proposal documents, claim handling, and selection of the most suitable person in charge, which required a lot of effort and time. Especially in the logistics center, optimization of the delivery route and prompt response to claims were required, but there was a lack of a system for efficiently performing these tasks. Also, it was a difficult problem to effectively utilize feedback in these processes and reflect it in the improvement of the system. 【0288】 The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0289】 In this invention, the server includes means for collecting past business cases and analyzing them with an algorithm, means for presenting a proposal template to an individual and automatically adapting it, and means for allowing an individual to modify and add to the generated proposal. As a result, it becomes possible to propose an efficient delivery route, present a claim solution, and select the most suitable person in charge. 【0290】 A "business case" is a collection of specific information and data related to past operations and projects within a company. 【0291】 An "algorithm" is a set of procedures and calculation methods for problem-solving, and is particularly used for analyzing data patterns in machine learning. 【0292】 A "proposal template" provides the basic structure and format when creating a business proposal document or a plan document. 【0293】 An "individual" refers to a person who creates a proposal document or handles a claim using this system, and generally involves human resources such as employees and staff. 【0294】 A "delivery route" refers to the path or method by which goods or items are transported from their origin to their destination. 【0295】 "Complaint resolution" refers to methods and means for appropriately responding to and resolving customer complaints and problem reports. 【0296】 A "person in charge" refers to a staff member or individual who is responsible for carrying out a specific task or project. 【0297】 To implement this invention, a system is primarily required that involves a server, a terminal, and a user. 【0298】 The server collects past business case data from a database within the company and analyzes this data using machine learning algorithms (such as Python's scikit-learn). This analysis automatically generates proposals optimized for ongoing business operations. This process involves data preprocessing and feature extraction, and the development of optimized proposals using a generative AI model (e.g., GPT-3). 【0299】 The device provides the user with a generated suggestion template and features a UI that allows the user to directly input or modify information. This interface is designed for ease of use using React Native. It also displays the generated suggestion content and offers the flexibility to add comments or make modifications to it. 【0300】 Users review the generated suggestions through the terminal interface and input corrections or additional information as needed. This feedback is returned to the server, and the system uses this information to make even more accurate suggestions. In the event of a complaint, users can easily receive solutions on their terminal. The server has a database of past complaint handling cases, allowing it to quickly suggest the best solution from similar cases. 【0301】 As a specific example, consider a case where a certain product is not delivered as scheduled. Through the terminal, the user can quickly receive solutions based on similar past cases. An example of a prompt sentence in this case is: "Please propose the optimal alternative route to resolve the delay in this delivery route. Summarize the analysis results based on similar past cases." 【0302】 Thus, this invention improves the business process and comprehensively supports from proposal creation to claim handling. 【0303】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0304】 Step 1: 【0305】 The server collects past business case data within the company from the database. The collected data includes proposal content, claim handling cases, and role player skill information. By leveraging this data, patterns of business content and successful cases in claim handling are grasped. 【0306】 Step 2: 【0307】 The server analyzes the collected data using a machine learning algorithm (using scikit - learn of Python) and automatically generates proposal content suitable for the current business case. The input data includes past cases of the business, and what is output is a prototype of an optimized proposal. In this process, pre - processing of data, selection of features, application of the model are performed, and a document is generated using a generative AI model (e.g., GPT - 3). 【0308】 Step 3: 【0309】 The terminal provides the user with an automatically generated proposal template and displays an interface that allows the user to directly input and edit information. The input at this stage consists of the user's modifications and additions, and the output is the final, customized proposal. The user's actions include adjusting input values ​​and adding comments. 【0310】 Step 4: 【0311】 The server records the generated proposals and user feedback, storing them as training data for future analysis. This input feedback helps the system make more accurate proposals in subsequent analyses. The output is an updated proposal analysis model. The server performs this process automatically, improving the quality of future proposals. 【0312】 Step 5: 【0313】 When a claim arises, the server searches its database and extracts the best solution from similar past claim handling cases. Based on the input claim information, the output is a list of recommended solutions. The server generates this list and transfers it to the terminal in real time. 【0314】 Step 6: 【0315】 Users quickly handle complaints through their terminals based on the solutions presented. Inputs include the results of implementing the selected solution and any new feedback, while output confirms the completion of the complaint resolution. Users proceed through this process, making adjustments as needed. 【0316】 This type of system processing leads to increased efficiency in business operations. 【0317】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0318】 This invention aims to enable more humane and accurate responses by combining an emotion engine with an AI-based business efficiency system to analyze the user's emotional state. This system analyzes the user's emotions in real time and provides suggestions, complaint handling, and even suggests internal contacts for consultation based on the results. 【0319】 First, the server uses machine learning algorithms to analyze past proposal examples and proposal data to generate proposals tailored to the current project. Additionally, an emotion engine built into the server analyzes the user's emotional state based on their input. For example, if the user is feeling stressed, the tone of the proposal can be adjusted to be more encouraging. 【0320】 In handling complaints, the terminal uses an emotion engine to analyze the emotional elements of user complaints and feedback, and the server automatically proposes emotionally sensitive solutions based on the analysis results. This allows for faster and more effective complaint resolution, thereby improving customer satisfaction. 【0321】 Furthermore, when suggesting internal contacts, the server selects the most appropriate person from the database based on the user's emotional state. For example, if the user is feeling stressed, a person skilled in comfortable communication will be suggested first. 【0322】 For example, when a user creates a proposal for a new project, the emotion engine on the device analyzes the user's input and incorporates necessary adjustments into the proposal. This process enables the user to create an accurate proposal that takes their own emotions into account. Furthermore, in the event of a complaint, the device's emotion analysis provides flexible solutions tailored to the customer's frustration, which can be used to quickly resolve the problem. 【0323】 In this way, by incorporating an emotion engine, this system improves the quality and efficiency of work and supports a more human-centered way of working. 【0324】 The following describes the processing flow. 【0325】 Step 1: 【0326】 Users input information into a terminal for creating proposals and handling complaints. This information includes details about the case and data indicating their current emotional state. 【0327】 Step 2: 【0328】 The device sends the input data to an emotion engine, which analyzes the user's emotional state in real time. The analysis results include emotional information such as whether the user is nervous, happy, or stressed. 【0329】 Step 3: 【0330】 The server uses machine learning algorithms to analyze past proposal examples and proposal data based on the analyzed sentiment data, and automatically generates proposals suitable for the current business project. During this process, the tone and style of the proposal are adjusted to match the user's emotional state. 【0331】 Step 4: 【0332】 The server searches a database of complaint handling cases and automatically suggests the optimal complaint handling solution, taking into account the user's emotions. This suggestion is based on the results of emotion analysis, providing a more flexible and empathetic approach. 【0333】 Step 5: 【0334】 The terminal automatically generates proposals and complaint handling strategies and presents them to the user. The user reviews these and enters any necessary corrections or additional information. 【0335】 Step 6: 【0336】 The server saves user-submitted revised proposals and countermeasures, accumulating them as training data for the emotion engine. This improves the system's accuracy and allows for better application to future proposals and countermeasures. 【0337】 This approach allows the system to consider user emotions and provide more humane and effective business support. 【0338】 (Example 2) 【0339】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0340】 Conventional business support systems have a problem in that, while automating business efficiency improvements, they have difficulty considering emotional factors in their suggestions and responses, resulting in a lack of human involvement. As a result, users cannot receive appropriate support that takes their emotional state into account, and countermeasures become uniform, which can lead to a lack of improvement in customer satisfaction and the quality of work. 【0341】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0342】 This invention includes a server that collects past business cases and business data, analyzes them based on a data analysis algorithm, and automatically generates proposals suitable for current business operations; a server that uses an emotion analysis system to analyze the user's emotional state and adjusts proposals based on that emotional state; and a server that stores the abilities and experience of personnel within the organization as data, searches for and proposes the most suitable candidate. This enables flexible and accurate proposals and responses that take into account the user's emotional state, thereby improving the efficiency and quality of operations. 【0343】 A "data analysis algorithm" is a computational method used to analyze past business cases and business data to identify specific patterns and relationships. 【0344】 An "emotion analysis system" is a mechanism that automatically analyzes the user's emotional state based on their input and makes appropriate suggestions and adjustments based on that analysis. 【0345】 A "data storage device" is a system that retains business-related information and the skills and experience of personnel within an organization over the long term, making it searchable and usable as needed. 【0346】 "Automatic proposal generation" is a process that automatically creates proposals suitable for current operations based on past business data. 【0347】 "Responsible person selection" is the process of using the organization's internal talent database to find the most suitable person for the user's needs and circumstances. 【0348】 In this invention, a server, terminal, and user collaborate to build a system that improves work efficiency. The server plays a central role in collecting past work cases and data and performing analysis using data analysis algorithms. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used for data analysis. In addition, an emotion analysis system is incorporated to analyze the user's emotional state from input data. Natural language processing technology is applied to the emotion analysis to automatically extract emotions from text. 【0349】 The terminal functions as an interface for receiving data input from users. When users input work-related information or feedback into the terminal, that information is sent to the server. Based on the sentiment analysis results, templates are automatically adjusted and suggestions are automatically generated as needed. 【0350】 Users can review suggestions presented by the system via their terminal and input any necessary modifications or additional information. This interaction enables more personalized business suggestions and complaint handling. 【0351】 As a concrete example, consider a scenario where a proposal for a new product is created. In this case, the server analyzes past proposal examples and analyzes the user's emotions from their input data. For example, if the user is feeling stressed, the proposal can be structured with an encouraging tone. This adjustment helps in the process where the server-generated proposal is presented to the user through their terminal, and the user completes the proposal based on it. 【0352】 An example of a prompt message would be, "Analyze the user's emotions in the new project proposal and generate feedback for the proposal." This invention aims not only to improve work efficiency but also to enable flexible responses that take user emotions into account, thereby enhancing customer satisfaction. 【0353】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0354】 Step 1: 【0355】 Users input work-related information and feedback into the terminal. The terminal collects this input data and sends it to the server. The input data includes comments and questions in text format. Specifically, the terminal receives input through the user interface, converts it into a processable format, and prepares it for transfer to the server. 【0356】 Step 2: 【0357】 The server receives data sent from the terminal. Here, an emotion analysis system is used to analyze the data and identify the user's emotional state. Specifically, natural language processing techniques are used to analyze what emotions the writer of the input text is expressing (e.g., joy, anger, anxiety). The input is the user's text data, and the output is the analyzed emotional state. 【0358】 Step 3: 【0359】 The server uses the results of sentiment analysis to process past business data and proposal examples with a data analysis algorithm, automatically generating proposals suitable for the current situation. In this process, a machine learning framework is utilized to evaluate the correlation between the input information and past data. The output is a proposal optimized for the user's situation. Specifically, the server searches a database of past examples and generates proposals while comparing them with similar cases. 【0360】 Step 4: 【0361】 The generated suggestions are adjusted in tone according to the user's emotional state. For example, if the user is showing signs of stress, the server adjusts the suggestions to include encouraging elements. The input is the analysis results and generated suggestions, and the output is the adjusted suggestions. 【0362】 Step 5: 【0363】 The terminal presents the user with a refined proposal sent from the server. The user can review it and add their own comments as needed. Specifically, the terminal displays the received data on the screen and provides an editable interface for the user. The input is the refined proposal, and the output is the final proposal including the user's feedback. 【0364】 Step 6: 【0365】 The server receives user feedback, stores it in a database, and uses it as training data for future AI models. This allows the system to make increasingly sophisticated and adaptive suggestions over time. Specifically, the server analyzes the received feedback and integrates it into the database. The input is user feedback, and the output is updated training data. 【0366】 (Application Example 2) 【0367】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0368】 In modern customer service and business proposals, accurately understanding the user's emotions and responding quickly and effectively is essential. However, conventional systems often failed to analyze emotions, resulting in purely mechanical responses. This led to decreased customer satisfaction and a lack of improvement in the quality of proposals. This invention aims to simultaneously achieve empathetic customer service and improved quality of business proposals. 【0369】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0370】 This invention includes a server that collects past proposal examples and proposal document data, analyzes them based on machine learning techniques, and automatically generates proposals suitable for current business cases; a server that analyzes the user's emotional state in real time and optimizes business responses in a human-like manner based on the analysis results; and a server that analyzes emotions in customer interactions and proposes customer service methods corresponding to specific emotional states. This enables accurate business proposals that take the user's emotions into consideration and achieves higher customer satisfaction. 【0371】 "Example proposals" refer to past business proposals and serve as the basic data for the system to generate new proposals. 【0372】 "Machine learning techniques" are technologies that use large amounts of data to improve algorithms and make predictions and decisions, and are applied to proposals and sentiment analysis. 【0373】 "Emotional state" refers to the psychological state of the user or customer, and is classified into elements such as anger, happiness, and surprise. 【0374】 "Analysis results" refer to the outcomes obtained after analysis based on data and input information, and are used to optimize business operations. 【0375】 A "business case" refers to a specific task or project related to a particular business, and is the subject of the system's proposal generation process. 【0376】 "Automatic generation" is a term that refers to the process by which a system creates proposals and countermeasures based on a specific algorithm without human intervention. 【0377】 "Customer satisfaction" is an indicator that shows the degree of customer satisfaction with the services and responses provided, and is a measure of business success. 【0378】 A "proposal document template" is a standard document template used when submitting a proposal, and its format is automatically adjusted based on the input information. 【0379】 "Optimization" refers to refining methods and processes to obtain the best possible results under certain conditions, and is a means of maximizing the efficiency and effectiveness of operations. 【0380】 The "analysis mechanism" refers to the devices or programs installed within the system to analyze the input data, and is the part responsible for processing emotions and suggested content. 【0381】 To realize the embodiments of this invention, a system consisting of a server, terminals, and users is constructed. The server collects proposal examples and proposal document data and analyzes them using machine learning techniques. Specifically, it utilizes machine learning models from a cloud service provider (e.g., Microsoft Azure) to generate proposals suitable for current business operations in real time based on historical data. 【0382】 The terminal acts as an interface with the user and is intended for use on smart devices. It utilizes a real-time analysis engine to analyze the user's emotional state based on the input information provided. Furthermore, it analyzes data collected through the device's built-in camera or microphone, and displays information that prompts business suggestions and customer service based on the analysis results. 【0383】 As a concrete example, consider a scenario where a user is handling customer service. If the user detects customer frustration through their terminal, the server uses a machine learning model based on the sentiment analysis results to generate encouraging suggestions and immediately present actionable solutions on the terminal. This enables the user to respond quickly and effectively, thereby improving customer satisfaction. 【0384】 Examples of prompt statements include the following: 【0385】 "Customer facial expressions and emotional scores: 【0386】 Anger: 0.7 【0387】 Happiness: 0.1 【0388】 Surprise: 0.1 【0389】 Sadness: 0.1 【0390】 Based on this emotional data, please suggest an appropriate customer service style. 【0391】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0392】 Step 1: 【0393】 The server collects past proposal examples and proposal document data from a database. This database contains historical information on business proposals and customer interactions. The server collects this information as input and analyzes it using machine learning algorithms to generate proposals suitable for the current business case. The output is a list of recommended proposals. 【0394】 Step 2: 【0395】 The device operates on a smart device and acquires input information from the user. This input information is collected as audio and image data through the device's camera and microphone. The device uses a real-time analysis engine to analyze this data for emotional content. From the data acquired as input, it outputs an analysis result representing the user's emotional state. This output includes emotional scores such as anger and happiness. 【0396】 Step 3: 【0397】 The server receives the results of the emotion analysis sent from the terminal. Given an emotion score as input, the server compares this with an existing database of countermeasures used in the analysis and outputs appropriate work responses and customer service methods. This generates countermeasures and styles of encouragement tailored to specific emotional states, which are then sent to the terminal. 【0398】 Step 4: 【0399】 The terminal visually or audibly presents the user with suggestions and customer service methods provided by the server. Specifically, information guiding the user to the optimal action is displayed via the display or speaker. The output in this step consists of concrete action suggestions that the user can easily implement. 【0400】 The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0401】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0402】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0403】 [Third Embodiment] 【0404】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0405】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0406】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0407】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0408】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0409】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0410】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0411】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0412】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0413】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0414】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0415】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0416】 This system is an AI-assisted platform designed to improve operational efficiency and knowledge sharing within companies, as well as to expedite complaint handling and optimize consultations. The specific implementation details are described below. 【0417】 First, the server collects past proposal examples and proposal data accumulated within the company. This data is then analyzed using machine learning algorithms to extract success factors and customer response patterns for each project. Using these analysis results, the server automatically generates proposal content and structure suitable for the current project. 【0418】 The terminal provides the user with a proposal template and prompts them to enter basic information. The user can then customize the template by combining the information they enter with automated suggestions provided by the server. This process allows the user to create proposals efficiently and effectively. 【0419】 In handling complaints, the server searches a database for past complaint handling cases. It has the functionality to analyze solutions to similar complaints and suggest the most appropriate course of action. Users can receive this information in real time through their terminals, enabling rapid complaint resolution. After a complaint is resolved, users provide feedback to the system as learning data by entering it into their terminals. 【0420】 To optimize the consultation process, the server utilizes the company's skills database to search for the most suitable candidates. When a user enters their consultation request, a list of candidates is provided based on their relevant skills and past experience. This information is displayed to the user on their device, allowing them to select a consultant and begin communication as needed. 【0421】 As a concrete example, consider a scenario where a user creates a proposal for a new product. By entering basic product information into the terminal, a draft proposal is automatically generated based on analysis results from the server. The user reviews this draft and finalizes it as the final proposal. Another concrete example of handling complaints is that for customer complaints that occur at night, a quick response can be obtained through the terminal's chatbot function. This allows the user to resolve problems quickly. 【0422】 The following describes the processing flow. 【0423】 Step 1: 【0424】 The server collects past proposal examples and proposal data from the company's database. This includes successful proposal details and the history of similar projects, preparing the data for analysis. 【0425】 Step 2: 【0426】 The server analyzes the collected data using machine learning algorithms. This analysis extracts commonalities and success factors from successful proposals, and identifies the elements and structure of those proposals. 【0427】 Step 3: 【0428】 The terminal displays a standard proposal template to the user. This template shows the basic structure of a proposal, and the user can enter the necessary information. 【0429】 Step 4: 【0430】 The user enters basic information necessary for creating a proposal (e.g., product name, target audience, expected results, etc.) into the terminal. The system then collects information relevant to the specific project. 【0431】 Step 5: 【0432】 The server automatically generates a proposal by combining the user's input information with the analysis results obtained in step 2. The generated proposal is then customized and incorporated into a proposal template. 【0433】 Step 6: 【0434】 The terminal presents the user with a customized draft proposal. The user can review this draft proposal and enter any necessary modifications or additions. 【0435】 Step 7: 【0436】 After the user completes the revisions, the terminal saves the finalized proposal, and the system records this information in the proposal database for use in future proposal generation. 【0437】 This process will streamline business processes and expedite proposal creation. 【0438】 (Example 1) 【0439】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0440】 The aim is to streamline operations and improve workflow by accelerating information processing to improve efficiency and facilitate proper knowledge sharing within companies, and by automating the rapid implementation of issues and the selection of the most suitable personnel. 【0441】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0442】 This invention includes a server that collects past information examples and document data, analyzes them based on a data processing algorithm, and automatically generates information suitable for current business operations; a server that presents document templates to users and automatically customizes the templates based on the input data; and a server that presents the automatically generated information content to users and allows users to input corrections and additional information. This improves the efficiency of operations within a company and enables the sharing of appropriate knowledge and information. 【0443】 "Information case data" refers to data on cases such as proposals and complaint handling that a company or organization has accumulated in the past. 【0444】 "Document data" refers to all data, including various forms of document information created within a company, such as proposals, reports, and complaint handling records. 【0445】 A "data processing algorithm" is a set of computational procedures for analyzing and processing digital information, and in this context, it specifically refers to data analysis methods that utilize machine learning. 【0446】 "Job description" refers to information about the business processes a company performs on a daily basis and the projects it is responsible for. 【0447】 "Information generation" means constructing new insights and proposals obtained through data processing. 【0448】 A "document template" refers to a pre-formatted document design that is prepared in advance for use as a template for proposals, reports, and other documents. 【0449】 "User" refers to an individual or member of an organization who operates or utilizes the system to perform their duties. 【0450】 "Automatically customizing templates" means dynamically changing the suggested content and document layout based on user input. 【0451】 "Information content" refers to a series of data, including data obtained through analysis and information generation, as well as proposals and solutions. 【0452】 "Problem-solving" refers to a series of processes in which a company finds and implements appropriate solutions to problems and challenges it faces. 【0453】 "Person in charge" refers to the individual responsible for implementing a specific task, project, or countermeasure. 【0454】 This invention provides an AI-assisted platform for improving operational efficiency within a company. Specifically, it includes functions for automatically generating proposals by collecting and analyzing past information, case studies, and document data; providing users with proposal templates and automatically customizing them; and presenting solutions to challenges. Furthermore, it also includes a function to identify the most suitable personnel candidates by utilizing a knowledge database of personnel within the organization. 【0455】 The server collects information, case studies, and document data from database management systems such as MySQL and PostgreSQL. Python machine learning libraries (e.g., scikit-learn and TensorFlow) are used for data processing. This allows the server to analyze success factors based on past data and generate proposals suitable for the current project. The algorithms used in the generation process may include classification and regression analysis. 【0456】 The terminal provides the user with a document template through an interface using HTML and JavaScript. The user then inputs basic information and customizes the template. Automatically generated suggestions from the server are helpful during the customization process. 【0457】 In the complaint handling function, the server rapidly searches past cases using technologies such as Elasticsearch, generates countermeasures from the analysis results, and presents them to the user via the terminal. This function enables quick and accurate problem resolution. After the problem is resolved, the user inputs feedback, which the server stores as training data. 【0458】 To optimize the consultation process, the server uses a skills database to search for the most suitable consultant. Based on the user's input, it evaluates relevant skills and past experience, and presents appropriate candidates on the user's device. The user can then select a consultant based on this information and begin the necessary consultation. 【0459】 As a concrete example, consider a scenario where a user is creating a proposal for a new product. After entering basic product information into the terminal, the server automatically generates a draft proposal based on the analysis results. The user then uses this draft to complete the final proposal. Another concrete example of handling complaints is the ability to instantly obtain solutions to complaints that arise during the night via the terminal's interface, enabling appropriate action. A prompt message such as, "I want to create a proposal for a new product's promotion strategy. Please provide an automatically generated template based on past success stories," allows the user to efficiently carry out their work. 【0460】 Thus, this system utilizes AI technology to streamline operations and supports rapid response and optimal knowledge transfer. 【0461】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0462】 Step 1: 【0463】 The server collects historical information, case studies, and document data from the company's internal database. Database connection information is used as input. After data collection, data analysis begins using a Python machine learning library. Specifically, past success factors are extracted using a classification algorithm, and case studies of complaint handling are analyzed. The output is analysis results that serve as material for generating proposals suitable for current business operations. 【0464】 Step 2: 【0465】 The terminal provides the user with a document template. The input includes basic information defined by the user. The user then inputs the necessary information through the interface based on the provided template. Based on this input, the template is automatically customized. The output is the first draft of the customized proposal. 【0466】 Step 3: 【0467】 The server automatically generates detailed proposal content using a generative AI model based on input data received from the user and an initial draft template. User data and template information are used as input. Data processing is performed by the generative AI model, and the proposal content is automatically customized. The server returns a completed draft proposal as output. 【0468】 Step 4: 【0469】 The terminal presents the user with a draft proposal sent from the server. The user reviews this draft and inputs any necessary revisions or additional information through the interface. Input actions include pointing and clicking on the areas that need revision. The output is the revised and completed proposal by the user. 【0470】 Step 5: 【0471】 The server searches for complaint handling cases and suggests solutions based on new complaint information entered by the user. The input includes detailed complaint information provided by the user. Data processing utilizes similarity searches with past data and an automated recommendation engine. The output is the recommended solution. 【0472】 Step 6: 【0473】 The server utilizes the organization's skills database to search for the most suitable representative based on the user's inquiry. Input requires information on the inquiry and expected skills. Data processing includes skill matrix matching. The output is a list of potential representatives, presented to the user via a terminal. 【0474】 This process allows organizations to efficiently prepare proposals and handle complaints, and to quickly find the most suitable consultant. 【0475】 (Application Example 1) 【0476】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0477】 Traditional business processes presented challenges due to the significant time and effort required for tasks such as proposal writing, complaint handling, and selecting the most suitable personnel. Logistics centers, in particular, demanded optimized delivery routes and rapid complaint resolution, but lacked the systems necessary to efficiently perform these tasks. Furthermore, effectively utilizing feedback within these processes and incorporating it into system improvements proved difficult. 【0478】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0479】 In this invention, the server includes means for collecting past business cases and analyzing them with an algorithm, means for presenting proposal templates to individuals and automatically adapting them, and means for individuals to modify or add to the generated proposals. This enables the suggestion of efficient delivery routes, the presentation of complaint solutions, and the selection of the most suitable personnel. 【0480】 "Business case studies" refer to a collection of specific information and data related to past work and projects within a company. 【0481】 An "algorithm" is a set of procedures or calculation methods for solving a problem, and is particularly used in machine learning to analyze patterns in data. 【0482】 A "proposal template" provides the basic structure and format for creating business proposals and plans. 【0483】 "Individuals" refers to those who use this system to create proposals or handle complaints, and generally includes employees or staff. 【0484】 A "delivery route" refers to the path or method by which goods or items are transported from their origin to their destination. 【0485】 "Complaint resolution" refers to methods and means for appropriately responding to and resolving customer complaints and problem reports. 【0486】 A "person in charge" refers to a staff member or individual who is responsible for carrying out a specific task or project. 【0487】 To implement this invention, a system is primarily required that involves a server, a terminal, and a user. 【0488】 The server collects past business case data from a database within the company and analyzes this data using machine learning algorithms (such as Python's scikit-learn). This analysis automatically generates proposals optimized for ongoing business operations. This process involves data preprocessing and feature extraction, and the development of optimized proposals using a generative AI model (e.g., GPT-3). 【0489】 The device provides the user with a generated suggestion template and features a UI that allows the user to directly input or modify information. This interface is designed for ease of use using React Native. It also displays the generated suggestion content and offers the flexibility to add comments or make modifications to it. 【0490】 Users review the generated suggestions through the terminal interface and input corrections or additional information as needed. This feedback is returned to the server, and the system uses this information to make even more accurate suggestions. In the event of a complaint, users can easily receive solutions on their terminal. The server has a database of past complaint handling cases, allowing it to quickly suggest the best solution from similar cases. 【0491】 As a concrete example, consider a case where a product is not delivered on schedule. The user can quickly receive solutions based on similar past cases via their device. An example of a prompt message in this case would be: "Please suggest the best alternative route to resolve the delay in this delivery route. Please summarize the analysis results based on similar past cases." 【0492】 Thus, this invention streamlines business processes and provides comprehensive support from proposal creation to handling customer complaints. 【0493】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0494】 Step 1: 【0495】 The server collects past business case data from the company's database. The collected data includes proposal content, complaint handling examples, and skill information of the individuals involved. This data is used to identify patterns in business operations and successful cases in complaint handling. 【0496】 Step 2: 【0497】 The server analyzes the collected data using a machine learning algorithm (using Python's scikit-learn) and automatically generates proposals that are suitable for current business projects. The input data includes past business cases, and the output is an optimized proposal template. This process involves data preprocessing, feature selection, and model application, and generates the document using a generative AI model (e.g., GPT-3). 【0498】 Step 3: 【0499】 The terminal provides the user with an automatically generated proposal template and displays an interface that allows the user to directly input and edit information. The input at this stage consists of the user's modifications and additions, and the output is the final, customized proposal. The user's actions include adjusting input values ​​and adding comments. 【0500】 Step 4: 【0501】 The server records the generated proposals and user feedback, storing them as training data for future analysis. This input feedback helps the system make more accurate proposals in subsequent analyses. The output is an updated proposal analysis model. The server performs this process automatically, improving the quality of future proposals. 【0502】 Step 5: 【0503】 When a claim arises, the server searches its database and extracts the best solution from similar past claim handling cases. Based on the input claim information, the output is a list of recommended solutions. The server generates this list and transfers it to the terminal in real time. 【0504】 Step 6: 【0505】 Users quickly handle complaints through their terminals based on the solutions presented. Inputs include the results of implementing the selected solution and any new feedback, while output confirms the completion of the complaint resolution. Users proceed through this process, making adjustments as needed. 【0506】 This type of system processing leads to increased efficiency in business operations. 【0507】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0508】 This invention aims to enable more humane and accurate responses by combining an emotion engine with an AI-based business efficiency system to analyze the user's emotional state. This system analyzes the user's emotions in real time and provides suggestions, complaint handling, and even suggests internal contacts for consultation based on the results. 【0509】 First, the server uses machine learning algorithms to analyze past proposal examples and proposal data to generate proposals tailored to the current project. Additionally, an emotion engine built into the server analyzes the user's emotional state based on their input. For example, if the user is feeling stressed, the tone of the proposal can be adjusted to be more encouraging. 【0510】 In handling complaints, the terminal uses an emotion engine to analyze the emotional elements of user complaints and feedback, and the server automatically proposes emotionally sensitive solutions based on the analysis results. This allows for faster and more effective complaint resolution, thereby improving customer satisfaction. 【0511】 Furthermore, when suggesting internal contacts, the server selects the most appropriate person from the database based on the user's emotional state. For example, if the user is feeling stressed, a person skilled in comfortable communication will be suggested first. 【0512】 For example, when a user creates a proposal for a new project, the emotion engine on the device analyzes the user's input and incorporates necessary adjustments into the proposal. This process enables the user to create an accurate proposal that takes their own emotions into account. Furthermore, in the event of a complaint, the device's emotion analysis provides flexible solutions tailored to the customer's frustration, which can be used to quickly resolve the problem. 【0513】 In this way, by incorporating an emotion engine, this system improves the quality and efficiency of work and supports a more human-centered way of working. 【0514】 The following describes the processing flow. 【0515】 Step 1: 【0516】 Users input information into a terminal for creating proposals and handling complaints. This information includes details about the case and data indicating their current emotional state. 【0517】 Step 2: 【0518】 The device sends the input data to an emotion engine, which analyzes the user's emotional state in real time. The analysis results include emotional information such as whether the user is nervous, happy, or stressed. 【0519】 Step 3: 【0520】 The server uses machine learning algorithms to analyze past proposal examples and proposal data based on the analyzed sentiment data, and automatically generates proposals suitable for the current business project. During this process, the tone and style of the proposal are adjusted to match the user's emotional state. 【0521】 Step 4: 【0522】 The server searches a database of complaint handling cases and automatically suggests the optimal complaint handling solution, taking into account the user's emotions. This suggestion is based on the results of emotion analysis, providing a more flexible and empathetic approach. 【0523】 Step 5: 【0524】 The terminal automatically generates proposals and complaint handling strategies and presents them to the user. The user reviews these and enters any necessary corrections or additional information. 【0525】 Step 6: 【0526】 The server saves user-submitted revised proposals and countermeasures, accumulating them as training data for the emotion engine. This improves the system's accuracy and allows for better application to future proposals and countermeasures. 【0527】 This approach allows the system to consider user emotions and provide more humane and effective business support. 【0528】 (Example 2) 【0529】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0530】 Conventional business support systems have a problem in that, while automating business efficiency improvements, they have difficulty considering emotional factors in their suggestions and responses, resulting in a lack of human involvement. As a result, users cannot receive appropriate support that takes their emotional state into account, and countermeasures become uniform, which can lead to a lack of improvement in customer satisfaction and the quality of work. 【0531】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0532】 This invention includes a server that collects past business cases and business data, analyzes them based on a data analysis algorithm, and automatically generates proposals suitable for current business operations; a server that uses an emotion analysis system to analyze the user's emotional state and adjusts proposals based on that emotional state; and a server that stores the abilities and experience of personnel within the organization as data, searches for and proposes the most suitable candidate. This enables flexible and accurate proposals and responses that take into account the user's emotional state, thereby improving the efficiency and quality of operations. 【0533】 A "data analysis algorithm" is a computational method used to analyze past business cases and business data to identify specific patterns and relationships. 【0534】 An "emotion analysis system" is a mechanism that automatically analyzes the user's emotional state based on their input and makes appropriate suggestions and adjustments based on that analysis. 【0535】 A "data storage device" is a system that retains business-related information and the skills and experience of personnel within an organization over the long term, making it searchable and usable as needed. 【0536】 "Automatic proposal generation" is a process that automatically creates proposals suitable for current operations based on past business data. 【0537】 "Responsible person selection" is the process of using the organization's internal talent database to find the most suitable person for the user's needs and circumstances. 【0538】 In this invention, a server, terminal, and user collaborate to build a system that improves work efficiency. The server plays a central role in collecting past work cases and data and performing analysis using data analysis algorithms. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used for data analysis. In addition, an emotion analysis system is incorporated to analyze the user's emotional state from input data. Natural language processing technology is applied to the emotion analysis to automatically extract emotions from text. 【0539】 The terminal functions as an interface for receiving data input from users. When users input work-related information or feedback into the terminal, that information is sent to the server. Based on the sentiment analysis results, templates are automatically adjusted and suggestions are automatically generated as needed. 【0540】 Users can review suggestions presented by the system via their terminal and input any necessary modifications or additional information. This interaction enables more personalized business suggestions and complaint handling. 【0541】 As a concrete example, consider a scenario where a proposal for a new product is created. In this case, the server analyzes past proposal examples and analyzes the user's emotions from their input data. For example, if the user is feeling stressed, the proposal can be structured with an encouraging tone. This adjustment helps in the process where the server-generated proposal is presented to the user through their terminal, and the user completes the proposal based on it. 【0542】 An example of a prompt message would be, "Analyze the user's emotions in the new project proposal and generate feedback for the proposal." This invention aims not only to improve work efficiency but also to enable flexible responses that take user emotions into account, thereby enhancing customer satisfaction. 【0543】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0544】 Step 1: 【0545】 Users input work-related information and feedback into the terminal. The terminal collects this input data and sends it to the server. The input data includes comments and questions in text format. Specifically, the terminal receives input through the user interface, converts it into a processable format, and prepares it for transfer to the server. 【0546】 Step 2: 【0547】 The server receives data sent from the terminal. Here, an emotion analysis system is used to analyze the data and identify the user's emotional state. Specifically, natural language processing techniques are used to analyze what emotions the writer of the input text is expressing (e.g., joy, anger, anxiety). The input is the user's text data, and the output is the analyzed emotional state. 【0548】 Step 3: 【0549】 The server uses the results of sentiment analysis to process past business data and proposal examples with a data analysis algorithm, automatically generating proposals suitable for the current situation. In this process, a machine learning framework is utilized to evaluate the correlation between the input information and past data. The output is a proposal optimized for the user's situation. Specifically, the server searches a database of past examples and generates proposals while comparing them with similar cases. 【0550】 Step 4: 【0551】 The generated suggestions are adjusted in tone according to the user's emotional state. For example, if the user is showing signs of stress, the server adjusts the suggestions to include encouraging elements. The input is the analysis results and generated suggestions, and the output is the adjusted suggestions. 【0552】 Step 5: 【0553】 The terminal presents the user with a refined proposal sent from the server. The user can review it and add their own comments as needed. Specifically, the terminal displays the received data on the screen and provides an editable interface for the user. The input is the refined proposal, and the output is the final proposal including the user's feedback. 【0554】 Step 6: 【0555】 The server receives user feedback, stores it in a database, and uses it as training data for future AI models. This allows the system to make increasingly sophisticated and adaptive suggestions over time. Specifically, the server analyzes the received feedback and integrates it into the database. The input is user feedback, and the output is updated training data. 【0556】 (Application Example 2) 【0557】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0558】 In modern customer service and business proposals, accurately understanding the user's emotions and responding quickly and effectively is essential. However, conventional systems often failed to analyze emotions, resulting in purely mechanical responses. This led to decreased customer satisfaction and a lack of improvement in the quality of proposals. This invention aims to simultaneously achieve empathetic customer service and improved quality of business proposals. 【0559】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0560】 This invention includes a server that collects past proposal examples and proposal document data, analyzes them based on machine learning techniques, and automatically generates proposals suitable for current business cases; a server that analyzes the user's emotional state in real time and optimizes business responses in a human-like manner based on the analysis results; and a server that analyzes emotions in customer interactions and proposes customer service methods corresponding to specific emotional states. This enables accurate business proposals that take the user's emotions into consideration and achieves higher customer satisfaction. 【0561】 "Example proposals" refer to past business proposals and serve as the basic data for the system to generate new proposals. 【0562】 "Machine learning techniques" are technologies that use large amounts of data to improve algorithms and make predictions and decisions, and are applied to proposals and sentiment analysis. 【0563】 "Emotional state" refers to the psychological state of the user or customer, and is classified into elements such as anger, happiness, and surprise. 【0564】 "Analysis results" refer to the outcomes obtained after analysis based on data and input information, and are used to optimize business operations. 【0565】 A "business case" refers to a specific task or project related to a particular business, and is the subject of the system's proposal generation process. 【0566】 "Automatic generation" is a term that refers to the process by which a system creates proposals and countermeasures based on a specific algorithm without human intervention. 【0567】 "Customer satisfaction" is an indicator that shows the degree of customer satisfaction with the services and responses provided, and is a measure of business success. 【0568】 A "proposal document template" is a standard document template used when submitting a proposal, and its format is automatically adjusted based on the input information. 【0569】 "Optimization" refers to refining methods and processes to obtain the best possible results under certain conditions, and is a means of maximizing the efficiency and effectiveness of operations. 【0570】 The "analysis mechanism" refers to the devices or programs installed within the system to analyze the input data, and is the part responsible for processing emotions and suggested content. 【0571】 To realize the embodiments of this invention, a system consisting of a server, terminals, and users is constructed. The server collects proposal examples and proposal document data and analyzes them using machine learning techniques. Specifically, it utilizes machine learning models from a cloud service provider (e.g., Microsoft Azure) to generate proposals suitable for current business operations in real time based on historical data. 【0572】 The terminal acts as an interface with the user and is intended for use on smart devices. It utilizes a real-time analysis engine to analyze the user's emotional state based on the input information provided. Furthermore, it analyzes data collected through the device's built-in camera or microphone, and displays information that prompts business suggestions and customer service based on the analysis results. 【0573】 As a concrete example, consider a scenario where a user is handling customer service. If the user detects customer frustration through their terminal, the server uses a machine learning model based on the sentiment analysis results to generate encouraging suggestions and immediately present actionable solutions on the terminal. This enables the user to respond quickly and effectively, thereby improving customer satisfaction. 【0574】 Examples of prompt statements include the following: 【0575】 "Customer facial expressions and emotional scores: 【0576】 Anger: 0.7 【0577】 Happiness: 0.1 【0578】 Surprise: 0.1 【0579】 Sadness: 0.1 【0580】 Based on this emotional data, please suggest an appropriate customer service style. 【0581】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0582】 Step 1: 【0583】 The server collects past proposal examples and proposal document data from a database. This database contains historical information on business proposals and customer interactions. The server collects this information as input and analyzes it using machine learning algorithms to generate proposals suitable for the current business case. The output is a list of recommended proposals. 【0584】 Step 2: 【0585】 The device operates on a smart device and acquires input information from the user. This input information is collected as audio and image data through the device's camera and microphone. The device uses a real-time analysis engine to analyze this data for emotional content. From the data acquired as input, it outputs an analysis result representing the user's emotional state. This output includes emotional scores such as anger and happiness. 【0586】 Step 3: 【0587】 The server receives the results of the emotion analysis sent from the terminal. Given an emotion score as input, the server compares this with an existing database of countermeasures used in the analysis and outputs appropriate work responses and customer service methods. This generates countermeasures and styles of encouragement tailored to specific emotional states, which are then sent to the terminal. 【0588】 Step 4: 【0589】 The terminal visually or audibly presents the user with suggestions and customer service methods provided by the server. Specifically, information guiding the user to the optimal action is displayed via the display or speaker. The output in this step consists of concrete action suggestions that the user can easily implement. 【0590】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0591】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0592】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0593】 [Fourth Embodiment] 【0594】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0595】 As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server. 【0596】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0597】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0598】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0599】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0600】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0601】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0602】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0603】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0604】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0605】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0606】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0607】 This system is an AI-assisted platform designed to improve operational efficiency and knowledge sharing within companies, as well as to expedite complaint handling and optimize consultations. The specific implementation details are described below. 【0608】 First, the server collects past proposal examples and proposal data accumulated within the company. This data is then analyzed using machine learning algorithms to extract success factors and customer response patterns for each project. Using these analysis results, the server automatically generates proposal content and structure suitable for the current project. 【0609】 The terminal provides the user with a proposal template and prompts them to enter basic information. The user can then customize the template by combining the information they enter with automated suggestions provided by the server. This process allows the user to create proposals efficiently and effectively. 【0610】 In handling complaints, the server searches a database for past complaint handling cases. It has the functionality to analyze solutions to similar complaints and suggest the most appropriate course of action. Users can receive this information in real time through their terminals, enabling rapid complaint resolution. After a complaint is resolved, users provide feedback to the system as learning data by entering it into their terminals. 【0611】 To optimize the consultation process, the server utilizes the company's skills database to search for the most suitable candidates. When a user enters their consultation request, a list of candidates is provided based on their relevant skills and past experience. This information is displayed to the user on their device, allowing them to select a consultant and begin communication as needed. 【0612】 As a concrete example, consider a scenario where a user creates a proposal for a new product. By entering basic product information into the terminal, a draft proposal is automatically generated based on analysis results from the server. The user reviews this draft and finalizes it as the final proposal. Another concrete example of handling complaints is that for customer complaints that occur at night, a quick response can be obtained through the terminal's chatbot function. This allows the user to resolve problems quickly. 【0613】 The following describes the processing flow. 【0614】 Step 1: 【0615】 The server collects past proposal examples and proposal data from the company's database. This includes successful proposal details and the history of similar projects, preparing the data for analysis. 【0616】 Step 2: 【0617】 The server analyzes the collected data using machine learning algorithms. This analysis extracts commonalities and success factors from successful proposals, and identifies the elements and structure of those proposals. 【0618】 Step 3: 【0619】 The terminal displays a standard proposal template to the user. This template shows the basic structure of a proposal, and the user can enter the necessary information. 【0620】 Step 4: 【0621】 The user enters basic information necessary for creating a proposal (e.g., product name, target audience, expected results, etc.) into the terminal. The system then collects information relevant to the specific project. 【0622】 Step 5: 【0623】 The server automatically generates a proposal by combining the user's input information with the analysis results obtained in step 2. The generated proposal is then customized and incorporated into a proposal template. 【0624】 Step 6: 【0625】 The terminal presents the user with a customized draft proposal. The user can review this draft proposal and enter any necessary modifications or additions. 【0626】 Step 7: 【0627】 After the user completes the revisions, the terminal saves the finalized proposal, and the system records this information in the proposal database for use in future proposal generation. 【0628】 This process will streamline business processes and expedite proposal creation. 【0629】 (Example 1) 【0630】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0631】 The aim is to streamline operations and improve workflow by accelerating information processing to improve efficiency and facilitate proper knowledge sharing within companies, and by automating the rapid implementation of issues and the selection of the most suitable personnel. 【0632】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0633】 This invention includes a server that collects past information examples and document data, analyzes them based on a data processing algorithm, and automatically generates information suitable for current business operations; a server that presents document templates to users and automatically customizes the templates based on the input data; and a server that presents the automatically generated information content to users and allows users to input corrections and additional information. This improves the efficiency of operations within a company and enables the sharing of appropriate knowledge and information. 【0634】 "Information case data" refers to data on cases such as proposals and complaint handling that a company or organization has accumulated in the past. 【0635】 "Document data" refers to all data, including various forms of document information created within a company, such as proposals, reports, and complaint handling records. 【0636】 A "data processing algorithm" is a set of computational procedures for analyzing and processing digital information, and in this context, it specifically refers to data analysis methods that utilize machine learning. 【0637】 "Job description" refers to information about the business processes a company performs on a daily basis and the projects it is responsible for. 【0638】 "Information generation" means constructing new insights and proposals obtained through data processing. 【0639】 A "document template" refers to a pre-formatted document design that is prepared in advance for use as a template for proposals, reports, and other documents. 【0640】 "User" refers to an individual or member of an organization who operates or utilizes the system to perform their duties. 【0641】 "Automatically customizing templates" means dynamically changing the suggested content and document layout based on user input. 【0642】 "Information content" refers to a series of data, including data obtained through analysis and information generation, as well as proposals and solutions. 【0643】 "Problem-solving" refers to a series of processes in which a company finds and implements appropriate solutions to problems and challenges it faces. 【0644】 "Person in charge" refers to the individual responsible for implementing a specific task, project, or countermeasure. 【0645】 This invention provides an AI-assisted platform for improving operational efficiency within a company. Specifically, it includes functions for automatically generating proposals by collecting and analyzing past information, case studies, and document data; providing users with proposal templates and automatically customizing them; and presenting solutions to challenges. Furthermore, it also includes a function to identify the most suitable personnel candidates by utilizing a knowledge database of personnel within the organization. 【0646】 The server collects information, case studies, and document data from database management systems such as MySQL and PostgreSQL. Python machine learning libraries (e.g., scikit-learn and TensorFlow) are used for data processing. This allows the server to analyze success factors based on past data and generate proposals suitable for the current project. The algorithms used in the generation process may include classification and regression analysis. 【0647】 The terminal provides the user with a document template through an interface using HTML and JavaScript. The user then inputs basic information and customizes the template. Automatically generated suggestions from the server are helpful during the customization process. 【0648】 In the complaint handling function, the server rapidly searches past cases using technologies such as Elasticsearch, generates countermeasures from the analysis results, and presents them to the user via the terminal. This function enables quick and accurate problem resolution. After the problem is resolved, the user inputs feedback, which the server stores as training data. 【0649】 To optimize the consultation process, the server uses a skills database to search for the most suitable consultant. Based on the user's input, it evaluates relevant skills and past experience, and presents appropriate candidates on the user's device. The user can then select a consultant based on this information and begin the necessary consultation. 【0650】 As a concrete example, consider a scenario where a user is creating a proposal for a new product. After entering basic product information into the terminal, the server automatically generates a draft proposal based on the analysis results. The user then uses this draft to complete the final proposal. Another concrete example of handling complaints is the ability to instantly obtain solutions to complaints that arise during the night via the terminal's interface, enabling appropriate action. A prompt message such as, "I want to create a proposal for a new product's promotion strategy. Please provide an automatically generated template based on past success stories," allows the user to efficiently carry out their work. 【0651】 Thus, this system utilizes AI technology to streamline operations and supports rapid response and optimal knowledge transfer. 【0652】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0653】 Step 1: 【0654】 The server collects historical information, case studies, and document data from the company's internal database. Database connection information is used as input. After data collection, data analysis begins using a Python machine learning library. Specifically, past success factors are extracted using a classification algorithm, and case studies of complaint handling are analyzed. The output is analysis results that serve as material for generating proposals suitable for current business operations. 【0655】 Step 2: 【0656】 The terminal provides the user with a document template. The input includes basic information defined by the user. The user then inputs the necessary information through the interface based on the provided template. Based on this input, the template is automatically customized. The output is the first draft of the customized proposal. 【0657】 Step 3: 【0658】 The server automatically generates detailed proposal content using a generative AI model based on input data received from the user and an initial draft template. User data and template information are used as input. Data processing is performed by the generative AI model, and the proposal content is automatically customized. The server returns a completed draft proposal as output. 【0659】 Step 4: 【0660】 The terminal presents the user with a draft proposal sent from the server. The user reviews this draft and inputs any necessary revisions or additional information through the interface. Input actions include pointing and clicking on the areas that need revision. The output is the revised and completed proposal by the user. 【0661】 Step 5: 【0662】 The server searches for complaint handling cases and suggests solutions based on new complaint information entered by the user. The input includes detailed complaint information provided by the user. Data processing utilizes similarity searches with past data and an automated recommendation engine. The output is the recommended solution. 【0663】 Step 6: 【0664】 The server utilizes the organization's skills database to search for the most suitable representative based on the user's inquiry. Input requires information on the inquiry and expected skills. Data processing includes skill matrix matching. The output is a list of potential representatives, presented to the user via a terminal. 【0665】 This process allows organizations to efficiently prepare proposals and handle complaints, and to quickly find the most suitable consultant. 【0666】 (Application Example 1) 【0667】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0668】 Traditional business processes presented challenges due to the significant time and effort required for tasks such as proposal writing, complaint handling, and selecting the most suitable personnel. Logistics centers, in particular, demanded optimized delivery routes and rapid complaint resolution, but lacked the systems necessary to efficiently perform these tasks. Furthermore, effectively utilizing feedback within these processes and incorporating it into system improvements proved difficult. 【0669】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0670】 In this invention, the server includes means for collecting past business cases and analyzing them with an algorithm, means for presenting proposal templates to individuals and automatically adapting them, and means for individuals to modify or add to the generated proposals. This enables the suggestion of efficient delivery routes, the presentation of complaint solutions, and the selection of the most suitable personnel. 【0671】 "Business case studies" refer to a collection of specific information and data related to past work and projects within a company. 【0672】 An "algorithm" is a set of procedures or calculation methods for solving a problem, and is particularly used in machine learning to analyze patterns in data. 【0673】 A "proposal template" provides the basic structure and format for creating business proposals and plans. 【0674】 "Individuals" refers to those who use this system to create proposals or handle complaints, and generally includes employees or staff. 【0675】 A "delivery route" refers to the path or method by which goods or items are transported from their origin to their destination. 【0676】 "Complaint resolution" refers to methods and means for appropriately responding to and resolving customer complaints and problem reports. 【0677】 A "person in charge" refers to a staff member or individual who is responsible for carrying out a specific task or project. 【0678】 To implement this invention, a system is primarily required that involves a server, a terminal, and a user. 【0679】 The server collects past business case data from a database within the company and analyzes this data using machine learning algorithms (such as Python's scikit-learn). This analysis automatically generates proposals optimized for ongoing business operations. This process involves data preprocessing and feature extraction, and the development of optimized proposals using a generative AI model (e.g., GPT-3). 【0680】 The device provides the user with a generated suggestion template and features a UI that allows the user to directly input or modify information. This interface is designed for ease of use using React Native. It also displays the generated suggestion content and offers the flexibility to add comments or make modifications to it. 【0681】 Users review the generated suggestions through the terminal interface and input corrections or additional information as needed. This feedback is returned to the server, and the system uses this information to make even more accurate suggestions. In the event of a complaint, users can easily receive solutions on their terminal. The server has a database of past complaint handling cases, allowing it to quickly suggest the best solution from similar cases. 【0682】 As a concrete example, consider a case where a product is not delivered on schedule. The user can quickly receive solutions based on similar past cases via their device. An example of a prompt message in this case would be: "Please suggest the best alternative route to resolve the delay in this delivery route. Please summarize the analysis results based on similar past cases." 【0683】 Thus, this invention streamlines business processes and provides comprehensive support from proposal creation to handling customer complaints. 【0684】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0685】 Step 1: 【0686】 The server collects past business case data from the company's database. The collected data includes proposal content, complaint handling examples, and skill information of the individuals involved. This data is used to identify patterns in business operations and successful cases in complaint handling. 【0687】 Step 2: 【0688】 The server analyzes the collected data using a machine learning algorithm (using Python's scikit-learn) and automatically generates proposals that are suitable for current business projects. The input data includes past business cases, and the output is an optimized proposal template. This process involves data preprocessing, feature selection, and model application, and generates the document using a generative AI model (e.g., GPT-3). 【0689】 Step 3: 【0690】 The terminal provides the user with an automatically generated proposal template and displays an interface that allows the user to directly input and edit information. The input at this stage consists of the user's modifications and additions, and the output is the final, customized proposal. The user's actions include adjusting input values ​​and adding comments. 【0691】 Step 4: 【0692】 The server records the generated proposals and user feedback, storing them as training data for future analysis. This input feedback helps the system make more accurate proposals in subsequent analyses. The output is an updated proposal analysis model. The server performs this process automatically, improving the quality of future proposals. 【0693】 Step 5: 【0694】 When a claim arises, the server searches its database and extracts the best solution from similar past claim handling cases. Based on the input claim information, the output is a list of recommended solutions. The server generates this list and transfers it to the terminal in real time. 【0695】 Step 6: 【0696】 Users quickly handle complaints through their terminals based on the solutions presented. Inputs include the results of implementing the selected solution and any new feedback, while output confirms the completion of the complaint resolution. Users proceed through this process, making adjustments as needed. 【0697】 This type of system processing leads to increased efficiency in business operations. 【0698】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0699】 This invention aims to enable more humane and accurate responses by combining an emotion engine with an AI-based business efficiency system to analyze the user's emotional state. This system analyzes the user's emotions in real time and provides suggestions, complaint handling, and even suggests internal contacts for consultation based on the results. 【0700】 First, the server uses machine learning algorithms to analyze past proposal examples and proposal data to generate proposals tailored to the current project. Additionally, an emotion engine built into the server analyzes the user's emotional state based on their input. For example, if the user is feeling stressed, the tone of the proposal can be adjusted to be more encouraging. 【0701】 In handling complaints, the terminal uses an emotion engine to analyze the emotional elements of user complaints and feedback, and the server automatically proposes emotionally sensitive solutions based on the analysis results. This allows for faster and more effective complaint resolution, thereby improving customer satisfaction. 【0702】 Furthermore, when suggesting internal contacts, the server selects the most appropriate person from the database based on the user's emotional state. For example, if the user is feeling stressed, a person skilled in comfortable communication will be suggested first. 【0703】 For example, when a user creates a proposal for a new project, the emotion engine on the device analyzes the user's input and incorporates necessary adjustments into the proposal. This process enables the user to create an accurate proposal that takes their own emotions into account. Furthermore, in the event of a complaint, the device's emotion analysis provides flexible solutions tailored to the customer's frustration, which can be used to quickly resolve the problem. 【0704】 In this way, by incorporating an emotion engine, this system improves the quality and efficiency of work and supports a more human-centered way of working. 【0705】 The following describes the processing flow. 【0706】 Step 1: 【0707】 Users input information into a terminal for creating proposals and handling complaints. This information includes details about the case and data indicating their current emotional state. 【0708】 Step 2: 【0709】 The device sends the input data to an emotion engine, which analyzes the user's emotional state in real time. The analysis results include emotional information such as whether the user is nervous, happy, or stressed. 【0710】 Step 3: 【0711】 The server uses machine learning algorithms to analyze past proposal examples and proposal data based on the analyzed sentiment data, and automatically generates proposals suitable for the current business project. During this process, the tone and style of the proposal are adjusted to match the user's emotional state. 【0712】 Step 4: 【0713】 The server searches a database of complaint handling cases and automatically suggests the optimal complaint handling solution, taking into account the user's emotions. This suggestion is based on the results of emotion analysis, providing a more flexible and empathetic approach. 【0714】 Step 5: 【0715】 The terminal automatically generates proposals and complaint handling strategies and presents them to the user. The user reviews these and enters any necessary corrections or additional information. 【0716】 Step 6: 【0717】 The server saves user-submitted revised proposals and countermeasures, accumulating them as training data for the emotion engine. This improves the system's accuracy and allows for better application to future proposals and countermeasures. 【0718】 This approach allows the system to consider user emotions and provide more humane and effective business support. 【0719】 (Example 2) 【0720】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0721】 Conventional business support systems have a problem in that, while automating business efficiency improvements, they have difficulty considering emotional factors in their suggestions and responses, resulting in a lack of human involvement. As a result, users cannot receive appropriate support that takes their emotional state into account, and countermeasures become uniform, which can lead to a lack of improvement in customer satisfaction and the quality of work. 【0722】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0723】 This invention includes a server that collects past business cases and business data, analyzes them based on a data analysis algorithm, and automatically generates proposals suitable for current business operations; a server that uses an emotion analysis system to analyze the user's emotional state and adjusts proposals based on that emotional state; and a server that stores the abilities and experience of personnel within the organization as data, searches for and proposes the most suitable candidate. This enables flexible and accurate proposals and responses that take into account the user's emotional state, thereby improving the efficiency and quality of operations. 【0724】 A "data analysis algorithm" is a computational method used to analyze past business cases and business data to identify specific patterns and relationships. 【0725】 An "emotion analysis system" is a mechanism that automatically analyzes the user's emotional state based on their input and makes appropriate suggestions and adjustments based on that analysis. 【0726】 A "data storage device" is a system that retains business-related information and the skills and experience of personnel within an organization over the long term, making it searchable and usable as needed. 【0727】 "Automatic proposal generation" is a process that automatically creates proposals suitable for current operations based on past business data. 【0728】 "Responsible person selection" is the process of using the organization's internal talent database to find the most suitable person for the user's needs and circumstances. 【0729】 In this invention, a server, terminal, and user collaborate to build a system that improves work efficiency. The server plays a central role in collecting past work cases and data and performing analysis using data analysis algorithms. Specifically, machine learning frameworks such as TensorFlow and PyTorch are used for data analysis. In addition, an emotion analysis system is incorporated to analyze the user's emotional state from input data. Natural language processing technology is applied to the emotion analysis to automatically extract emotions from text. 【0730】 The terminal functions as an interface for receiving data input from users. When users input work-related information or feedback into the terminal, that information is sent to the server. Based on the sentiment analysis results, templates are automatically adjusted and suggestions are automatically generated as needed. 【0731】 Users can review suggestions presented by the system via their terminal and input any necessary modifications or additional information. This interaction enables more personalized business suggestions and complaint handling. 【0732】 As a concrete example, consider a scenario where a proposal for a new product is created. In this case, the server analyzes past proposal examples and analyzes the user's emotions from their input data. For example, if the user is feeling stressed, the proposal can be structured with an encouraging tone. This adjustment helps in the process where the server-generated proposal is presented to the user through their terminal, and the user completes the proposal based on it. 【0733】 An example of a prompt message would be, "Analyze the user's emotions in the new project proposal and generate feedback for the proposal." This invention aims not only to improve work efficiency but also to enable flexible responses that take user emotions into account, thereby enhancing customer satisfaction. 【0734】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0735】 Step 1: 【0736】 Users input work-related information and feedback into the terminal. The terminal collects this input data and sends it to the server. The input data includes comments and questions in text format. Specifically, the terminal receives input through the user interface, converts it into a processable format, and prepares it for transfer to the server. 【0737】 Step 2: 【0738】 The server receives data sent from the terminal. Here, an emotion analysis system is used to analyze the data and identify the user's emotional state. Specifically, natural language processing techniques are used to analyze what emotions the writer of the input text is expressing (e.g., joy, anger, anxiety). The input is the user's text data, and the output is the analyzed emotional state. 【0739】 Step 3: 【0740】 The server uses the results of sentiment analysis to process past business data and proposal examples with a data analysis algorithm, automatically generating proposals suitable for the current situation. In this process, a machine learning framework is utilized to evaluate the correlation between the input information and past data. The output is a proposal optimized for the user's situation. Specifically, the server searches a database of past examples and generates proposals while comparing them with similar cases. 【0741】 Step 4: 【0742】 The generated suggestions are adjusted in tone according to the user's emotional state. For example, if the user is showing signs of stress, the server adjusts the suggestions to include encouraging elements. The input is the analysis results and generated suggestions, and the output is the adjusted suggestions. 【0743】 Step 5: 【0744】 The terminal presents the user with a refined proposal sent from the server. The user can review it and add their own comments as needed. Specifically, the terminal displays the received data on the screen and provides an editable interface for the user. The input is the refined proposal, and the output is the final proposal including the user's feedback. 【0745】 Step 6: 【0746】 The server receives user feedback, stores it in a database, and uses it as training data for future AI models. This allows the system to make increasingly sophisticated and adaptive suggestions over time. Specifically, the server analyzes the received feedback and integrates it into the database. The input is user feedback, and the output is updated training data. 【0747】 (Application Example 2) 【0748】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0749】 In modern customer service and business proposals, accurately understanding the user's emotions and responding quickly and effectively is essential. However, conventional systems often failed to analyze emotions, resulting in purely mechanical responses. This led to decreased customer satisfaction and a lack of improvement in the quality of proposals. This invention aims to simultaneously achieve empathetic customer service and improved quality of business proposals. 【0750】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0751】 This invention includes a server that collects past proposal examples and proposal document data, analyzes them based on machine learning techniques, and automatically generates proposals suitable for current business cases; a server that analyzes the user's emotional state in real time and optimizes business responses in a human-like manner based on the analysis results; and a server that analyzes emotions in customer interactions and proposes customer service methods corresponding to specific emotional states. This enables accurate business proposals that take the user's emotions into consideration and achieves higher customer satisfaction. 【0752】 "Example proposals" refer to past business proposals and serve as the basic data for the system to generate new proposals. 【0753】 "Machine learning techniques" are technologies that use large amounts of data to improve algorithms and make predictions and decisions, and are applied to proposals and sentiment analysis. 【0754】 "Emotional state" refers to the psychological state of the user or customer, and is classified into elements such as anger, happiness, and surprise. 【0755】 "Analysis results" refer to the outcomes obtained after analysis based on data and input information, and are used to optimize business operations. 【0756】 A "business case" refers to a specific task or project related to a particular business, and is the subject of the system's proposal generation process. 【0757】 "Automatic generation" is a term that refers to the process by which a system creates proposals and countermeasures based on a specific algorithm without human intervention. 【0758】 "Customer satisfaction" is an indicator that shows the degree of customer satisfaction with the services and responses provided, and is a measure of business success. 【0759】 A "proposal document template" is a standard document template used when submitting a proposal, and its format is automatically adjusted based on the input information. 【0760】 "Optimization" refers to refining methods and processes to obtain the best possible results under certain conditions, and is a means of maximizing the efficiency and effectiveness of operations. 【0761】 The "analysis mechanism" refers to the devices or programs installed within the system to analyze the input data, and is the part responsible for processing emotions and suggested content. 【0762】 To realize the embodiments of this invention, a system consisting of a server, terminals, and users is constructed. The server collects proposal examples and proposal document data and analyzes them using machine learning techniques. Specifically, it utilizes machine learning models from a cloud service provider (e.g., Microsoft Azure) to generate proposals suitable for current business operations in real time based on historical data. 【0763】 The terminal acts as an interface with the user and is intended for use on smart devices. It utilizes a real-time analysis engine to analyze the user's emotional state based on the input information provided. Furthermore, it analyzes data collected through the device's built-in camera or microphone, and displays information that prompts business suggestions and customer service based on the analysis results. 【0764】 As a concrete example, consider a scenario where a user is handling customer service. If the user detects customer frustration through their terminal, the server uses a machine learning model based on the sentiment analysis results to generate encouraging suggestions and immediately present actionable solutions on the terminal. This enables the user to respond quickly and effectively, thereby improving customer satisfaction. 【0765】 Examples of prompt statements include the following: 【0766】 "Customer facial expressions and emotional scores: 【0767】 Anger: 0.7 【0768】 Happiness: 0.1 【0769】 Surprise: 0.1 【0770】 Sadness: 0.1 【0771】 Based on this emotional data, please suggest an appropriate customer service style. 【0772】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0773】 Step 1: 【0774】 The server collects past proposal examples and proposal document data from a database. This database contains historical information on business proposals and customer interactions. The server collects this information as input and analyzes it using machine learning algorithms to generate proposals suitable for the current business case. The output is a list of recommended proposals. 【0775】 Step 2: 【0776】 The device operates on a smart device and acquires input information from the user. This input information is collected as audio and image data through the device's camera and microphone. The device uses a real-time analysis engine to analyze this data for emotional content. From the data acquired as input, it outputs an analysis result representing the user's emotional state. This output includes emotional scores such as anger and happiness. 【0777】 Step 3: 【0778】 The server receives the results of the emotion analysis sent from the terminal. Given an emotion score as input, the server compares this with an existing database of countermeasures used in the analysis and outputs appropriate work responses and customer service methods. This generates countermeasures and styles of encouragement tailored to specific emotional states, which are then sent to the terminal. 【0779】 Step 4: 【0780】 The terminal visually or audibly presents the user with suggestions and customer service methods provided by the server. Specifically, information guiding the user to the optimal action is displayed via the display or speaker. The output in this step consists of concrete action suggestions that the user can easily implement. 【0781】 The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0782】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0783】 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0784】 Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0785】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0786】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0787】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0788】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0789】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0790】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0791】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0792】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0793】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0794】 Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12. 【0795】 Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0796】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory. 【0797】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0798】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0799】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0800】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0801】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference. 【0802】 The following is further disclosed regarding the embodiments described above. 【0803】 (Claim 1) 【0804】 A method for automatically generating proposals suitable for current business projects by collecting past proposal examples and proposal data, analyzing them based on machine learning algorithms, and 【0805】 A method for presenting a proposal template to the user and automatically customizing the template based on the information entered, 【0806】 A means of presenting automatically generated suggestions to the user and allowing the user to input corrections or additional information, 【0807】 A method for automatically suggesting countermeasures for complaints by searching a database of past complaint handling cases, 【0808】 A method for creating a database of the skills and experience of internal employees, and for searching for and suggesting the most suitable candidates, 【0809】 A system that includes this. 【0810】 (Claim 2) 【0811】 The system according to claim 1, which collects user feedback after proposing a complaint resolution and stores it as training data for an AI model. 【0812】 (Claim 3) 【0813】 The system according to claim 1, which searches an internal skills database based on the content the user wants to consult about and presents the user with a list of the most suitable person in charge. 【0814】 "Example 1" 【0815】 (Claim 1) 【0816】 A means of automatically generating information suitable for current business operations by collecting past information, case studies, and document data, and analyzing them based on data processing algorithms. 【0817】 A method for presenting document templates to users and automatically customizing those templates based on the entered data, 【0818】 A means of presenting automatically generated information to the user and allowing the user to input corrections or additional information, 【0819】 A method for automatically proposing solutions to past problems by searching for past problem-solving examples from information sources, 【0820】 A method for creating a database of the knowledge and experience of personnel within an organization, and for searching for and proposing the most suitable candidates, 【0821】 A system that includes a means of utilizing practical examples by presenting automatically generated draft documents. 【0822】 (Claim 2) 【0823】 The system according to claim 1, which, after proposing solutions to problems, collects evaluation information from users and stores it as training data for a knowledge processing model. 【0824】 (Claim 3) 【0825】 The system according to claim 1, which searches an internal database of an organization based on the content that the user wishes to discuss and presents the user with a list of the most suitable personnel. 【0826】 "Application Example 1" 【0827】 (Claim 1) 【0828】 A method for collecting past business cases, analyzing them using algorithms, and automatically generating proposals suitable for current work projects, 【0829】 A method for presenting proposal templates to individuals and automatically applying the templates based on the information they enter, 【0830】 A means of presenting the generated suggestions to individuals and allowing them to input modifications or additional information, 【0831】 A method for automatically suggesting countermeasures for complaints by retrieving past complaint handling cases from records, 【0832】 A method for creating a database of the abilities and experience of team members, and for identifying and proposing the most suitable candidates, 【0833】 Based on delivery data and complaint cases, a means to recommend the optimal delivery route and complaint resolution method, 【0834】 A means to detect anomalies in real time and notify the person in charge of the appropriate solution, 【0835】 A system that includes this. 【0836】 (Claim 2) 【0837】 The system according to claim 1, which collects feedback from individuals after proposing a complaint resolution and stores it as training data for an intelligent model. 【0838】 (Claim 3) 【0839】 The system according to claim 1, which searches a database of personnel based on the content of the consultation an individual wishes to discuss and presents the individual with a list of the most suitable personnel. 【0840】 "Example 2 of combining an emotion engine" 【0841】 (Claim 1) 【0842】 A means of automatically generating proposals suitable for current operations by collecting past business cases and business data, analyzing them based on data analysis algorithms, and 【0843】 A method for presenting business templates to users and automatically adjusting the templates based on the entered data, 【0844】 A means of presenting automatically generated suggestions to the user and allowing the user to input corrections or additional data, 【0845】 A means of automatically proposing countermeasures for problems by searching past response cases from a data storage device, 【0846】 A method for storing the skills and experience of personnel within an organization as data, and for searching for and proposing the most suitable candidates, 【0847】 A means of analyzing the user's emotional state using an emotion analysis system and adjusting suggestions based on that emotional state, 【0848】 A means of selecting a staff member with the most appropriate communication skills according to the user's emotional state, 【0849】 A system that includes this. 【0850】 (Claim 2) 【0851】 The system according to claim 1, which collects user feedback after proposing a solution and stores it as training data for the generated AI model. 【0852】 (Claim 3) 【0853】 The system according to claim 1, which searches an internal skill data storage device within an organization based on the content the user wishes to consult about, and presents the user with a list of the most suitable person in charge. 【0854】 "Application example 2 of combining emotional engines" 【0855】 (Claim 1) 【0856】 A mechanism that collects past proposal examples and proposal document data, analyzes them based on machine learning methods, and automatically generates proposals suitable for current business projects, 【0857】 A mechanism that presents a proposal document template to the user and automatically adjusts the template based on the information entered, 【0858】 A mechanism that provides automatically generated suggestions to the user and allows the user to input corrections or additional information, 【0859】 A mechanism that searches a database for past complaint handling cases and automatically proposes appropriate countermeasures for complaints, 【0860】 A system that databases the skills and experience of internal staff and searches for and proposes the most suitable candidates, 【0861】 A mechanism that analyzes the user's emotional state in real time and optimizes work responses in a human-like manner based on the analysis results, 【0862】 A mechanism that analyzes emotions in customer service to propose customer service methods tailored to specific emotional states, 【0863】 A system that includes this. 【0864】 (Claim 2) 【0865】 The system according to claim 1, which collects feedback from the user after proposing a solution to a complaint and stores it as training data for an AI model. 【0866】 (Claim 3) 【0867】 The system according to claim 1, which searches an internal skills database based on the content the user wishes to discuss and presents the user with a list of the most suitable personnel. [Explanation of symbols] 【0868】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A method for automatically generating proposals suitable for current business projects by collecting past proposal examples and proposal data, analyzing them based on machine learning algorithms, and A method for presenting a proposal template to the user and automatically customizing the template based on the information entered, A means of presenting automatically generated suggestions to the user and allowing the user to input corrections or additional information, A method for automatically suggesting countermeasures for complaints by searching a database of past complaint handling cases, A method for creating a database of the skills and experience of internal employees, and for searching for and suggesting the most suitable candidates, A system that includes this. [Claim 2] The system according to claim 1, which collects user feedback after proposing a complaint resolution and stores it as training data for an AI model. [Claim 3] The system according to claim 1, which searches an internal skills database based on the content the user wants to consult about and presents the user with a list of the most suitable person in charge.

Images