system

Abstract

We provide the system. [Solution] Means of obtaining past sales data, A means of analyzing acquired data using a generation algorithm, A means of identifying new projects and proposing improvement measures based on the analysis results, A means of scheduling appointments and handling emails through an automated agent, A system that includes a means of responding to customer inquiries using a real-time chatbot.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Unexamined Patent Application Publication No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In the sales department, especially in companies with many junior sales members, the implementation of efficient sales activities and the variation in the quality of customer service are issues. This may reduce the overall efficiency of sales and hinder the improvement of the company's performance. Also, since manual analysis of sales data requires a great deal of time and labor, automated support is demanded. 【Means for Solving the Problems】 【0005】 This invention solves the above problems by providing a system that analyzes past sales data using a generation algorithm after acquiring that data. This system has the function of discovering new leads and proposing improvement measures based on the analysis results, and supports sales activities by setting appointments and responding to emails through an automated agent. In addition, it improves the quality of customer service by responding immediately to customer inquiries using a real-time chatbot. 【0006】 "Sales data" refers to data that includes information about a company's sales activities, such as customer information, negotiation history, and sales performance. 【0007】 A "generative algorithm" is a part of a program that generates new information or suggestions based on certain rules or data. 【0008】 "Analysis" is the process of examining data in detail and finding patterns and correlations that exist between them. 【0009】 "New projects" refer to new sales opportunities with customers or markets with which we have not previously had any relationship. 【0010】 "Improvement measures" refer to specific action plans or proposals aimed at improving the efficiency and quality of work. 【0011】 An "automation agent" is software that performs specific tasks automatically with minimal human intervention. 【0012】 "Appointment setting" refers to the act of coordinating and deciding on a date and time for a business meeting or consultation with a customer during sales activities. 【0013】 "Email correspondence" refers to the task of receiving emails from customers and business partners and providing appropriate replies. 【0014】 A "real-time chatbot" is a program that interacts with users in real time through a chat interface and is mainly used for customer service. 【0015】 A "natural language processing model" is an algorithm for machines to understand and process human language, and is used to analyze the meaning and structure of language. 【Brief Explanation of Drawings】 【0016】 [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [[ID=4"]] [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】 【0017】 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. 【0018】 First, the terms used in the following description will be explained. 【0019】 In the following embodiments, the numbered 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0020】 In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0021】 In the following embodiments, the numbered 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 disks (e.g., hard disks), or magnetic tapes, etc. 【0022】 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). 【0023】 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." 【0024】 [First Embodiment] 【0025】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0026】 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. 【0027】 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). 【0028】 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. 【0029】 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. 【0030】 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. 【0031】 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. 【0032】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0033】 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. 【0034】 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. 【0035】 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. 【0036】 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". 【0037】 This invention is a system for automating sales support and customer service, and can be implemented as follows. This system analyzes past sales data and automatically proposes solutions for identifying new leads and improving sales activities. Furthermore, it improves sales efficiency by supporting appointment setting and real-time responses to customer inquiries in sales activities. 【0038】 The server retrieves necessary data from databases of CRM systems and sales analytics tools that manage sales data. This data includes customer information, transaction history, and past sales performance. The server analyzes the retrieved data using generation algorithms to identify patterns of sales success and new sales opportunities. 【0039】 Based on the analysis results, the server generates improvement suggestions for specific customer segments and notifies the sales team. These suggestions may include implementing email campaigns or optimizing visit schedules. In particular, it identifies customer segments that tend to have a high conversion rate and recommends appropriate approaches to sales representatives for those segments. 【0040】 The terminal receives new case information provided by the server, incorporates it into the schedule using an automated agent, and sets up appointments with customers as needed. The terminal's email system also enables quick email replies to customers using predefined templates. 【0041】 Users utilize a real-time chatbot installed on their devices to provide immediate responses to customer inquiries. The chatbot automatically responds to general questions and escalates complex issues to the user. This enables prompt responses that satisfy customers. 【0042】 In this way, the present invention highly automates sales and customer service processes, achieving operational efficiency and improved customer satisfaction. Specifically, sales teams can utilize automatically generated proposals in weekly meetings to plan and adjust strategies. This entire process is useful in improving the quality of sales and, in particular, in promoting the early development of junior sales members. 【0043】 The following describes the processing flow. 【0044】 Step 1: 【0045】 The server connects to the CRM system and sales analytics tools to retrieve sales data for the past 30 days. This data includes customer information, transaction history, and sales performance. This data is converted into a format suitable for analysis and stored in a database on the server. 【0046】 Step 2: 【0047】 The server activates a generation algorithm and begins analysis using the stored sales data. The server considers factors such as customer attributes and purchase history, and uses a machine learning model to identify successful sales patterns and discover new business opportunities. 【0048】 Step 3: 【0049】 Based on the analysis results, the server generates improvement suggestions to optimize sales activities. These suggestions include targeted approaches to specific customer segments and sales strategies to increase closing rates. The generated suggestions are sent to the sales team as a report. 【0050】 Step 4: 【0051】 The terminal receives new case information from the server and uses an automated agent to set up schedules and appointments. The terminal sends scheduling emails to customers and receives responses as needed. 【0052】 Step 5: 【0053】 Users receive customer inquiries using a real-time chatbot installed on their devices. The chatbot automatically responds to general questions, and complex issues are escalated to the user. The user then manually provides detailed answers based on this information. 【0054】 Step 6: 【0055】 The server records the results of users' sales activities and customer interactions, and uses this data for subsequent analysis. This allows the entire system to be continuously improved, enhancing sales efficiency and effectiveness. 【0056】 (Example 1) 【0057】 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." 【0058】 In sales activities, efficiently acquiring and analyzing information necessary for identifying new leads and improving sales processes is crucial. However, many companies are unable to fully utilize the vast amount of data they possess, and lack the appropriate tools and processes for efficient sales activities. As a result, problems arise such as a decline in the quality of customer service and a decrease in sales efficiency. 【0059】 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. 【0060】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the acquired information using a machine learning algorithm, and means for identifying new business opportunities and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved customer satisfaction. 【0061】 "Sales-related information" refers to all data related to sales activities, such as customer information, transaction history, and sales performance. 【0062】 A "machine learning algorithm" refers to a method that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0063】 "New business opportunities" refer to potential future transactions and projects that are discovered based on existing sales activities. 【0064】 "Improvement measures" refer to specific action plans aimed at improving the efficiency and results of sales activities. 【0065】 An "automated management agent" refers to a program that assists users by automating the setting and execution of plans. 【0066】 "Communication support" refers to activities that involve communicating with customers through email, messages, and other means. 【0067】 A "real-time conversational agent" refers to a system that automatically interacts with users in real time, using tools such as chatbots. 【0068】 "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language. 【0069】 This invention is a system for automating and streamlining sales activities. The following hardware and software are used to implement the invention. 【0070】 The server first retrieves sales-related information from customer relationship management databases and sales analytics tools. This includes customer information, transaction history, and past sales performance. Specifically, databases such as SQL Server and MySQL® are used, and the server extracts information using SQL queries. The server then inputs this information into a generating AI model and analyzes the data through machine learning algorithms. This analysis process can discover successful sales patterns and identify new business opportunities. 【0071】 The terminal uses analysis results received from the server and an automated management agent to set appointments based on the sales representative's schedule. For example, it can automatically add new cases using the Google® Calendar API and optimize visit schedules. Furthermore, the terminal's email system uses templates provided by the server to ensure rapid communication with customers. 【0072】 Users utilize a real-time conversational agent built into their devices to respond to customer inquiries in real time. Using natural language processing technology, the agent automatically answers common questions, while allowing users to provide detailed responses to more complex inquiries. This enables fast and highly accurate customer service. 【0073】 As a concrete example, users can formulate strategies based on proposals generated by the server during weekly sales meetings. This process is particularly useful for developing the skills of junior sales members. Furthermore, an example of a prompt to input into the AI ​​model is, "Based on past sales data, please identify customer segments with high conversion rates and generate proposals to optimize visit schedules." In this way, it is possible to improve the quality and efficiency of the entire sales process. 【0074】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0075】 Step 1: 【0076】 The server retrieves sales-related information from customer relationship management databases and sales analytics tools. Inputs include database query requests, which output customer information, transaction history, sales performance, and other data from systems such as SQL Server and MySQL. This data is collected for initial analysis and subsequent processing. 【0077】 Step 2: 【0078】 The server inputs the acquired sales-related information into a generating AI model, which then analyzes it using machine learning algorithms. The input is the dataset acquired in Step 1, and the output is the identification of successful sales patterns and new business opportunities. Data processing includes feature extraction and normalization, and a mechanism is built in which the AI ​​model uses this data to discover patterns. 【0079】 Step 3: 【0080】 The server proposes improvement measures based on the analysis results. The input is the analysis results from step 2, and the output is a proposal for implementing a specific campaign or an optimized visit schedule. Specifically, the server automatically generates the proposal and prepares to notify the sales team. 【0081】 Step 4: 【0082】 The terminal uses an automated management agent to add new case information received from the server to the schedule. The input is a suggestion for improvement measures, and the output is new appointment information added to the sales representative's calendar. The system uses the Google Calendar API or similar tools to ensure that the changes are properly reflected in each representative's schedule. 【0083】 Step 5: 【0084】 The terminal's email system uses server templates to send emails to customers. The input is an email template based on the proposal in Step 3, and the output is the email content sent to the customer. The email system will perform individual customizations as needed to provide the most relevant information to the customer. 【0085】 Step 6: 【0086】 Users respond to customer inquiries using a real-time conversational agent. The input is the customer's inquiry, and the output is either an automated response from the agent or a direct response from the user. Specifically, the chatbot provides standard responses to general questions, while the user takes over for more complex inquiries. 【0087】 (Application Example 1) 【0088】 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." 【0089】 This invention aims to solve the problems of decreased efficiency in sales activities and reduced customer satisfaction due to delays in customer service. In particular, in electronic payment services, there is a demand for rapid analysis of transaction data and proposals that meet customer needs. To meet these demands, it is necessary to support the sales team and automate customer service. 【0090】 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. 【0091】 In this invention, the server includes means for acquiring past sales data, means for analyzing the acquired data using a generation algorithm, and means for identifying new projects and proposing improvement measures based on the analysis results. This makes it possible to improve sales efficiency and provide prompt and accurate customer service in electronic payment services. 【0092】 "Past sales data" refers to customer information and transaction history recorded in the past during sales activities, and is data used for sales analysis and evaluation. 【0093】 A "generative algorithm" is a computational method for deriving useful patterns or information from input data, and machine learning models are an example of this. 【0094】 An "automation agent" is a program or system that automatically performs specific tasks, such as scheduling appointments or responding to emails. 【0095】 A "real-time chatbot" is a conversational program that can respond to user inquiries immediately, and it uses natural language processing to automatically provide answers. 【0096】 An "electronic payment service" is a service that provides a system for paying for goods and services online using digital technology. 【0097】 "Transaction data" refers to data containing information about commercial transactions, including purchase history and payment information. 【0098】 A "machine learning model" is a collection of algorithms that learn patterns from data and use that knowledge to make predictions and judgments about new data. 【0099】 "Customer requirements" refer to the specific needs and expectations that a buyer or service user desires for a product or service. 【0100】 "Automatic response means" refers to a technology or system that automatically generates and provides a response to the user in response to specific conditions. 【0101】 The system in this invention is realized through the respective roles of the server, terminal, and user. 【0102】 The server first retrieves historical sales data from CRM systems and sales analysis tools. Specifically, it collects data using Python and performs data cleansing and preprocessing using the Pandas library. Next, it uses a machine learning model with scikit-learn to analyze the data and identify patterns of successful sales. Based on these analysis results, it automatically generates strategies for identifying new leads and improving sales activities. 【0103】 The terminal receives proposals and new project information provided by the server. Based on this information, the automated agent quickly sets up appointments and responds to emails using pre-prepared templates. 【0104】 Furthermore, users can instantly respond to customer inquiries by utilizing a real-time chatbot. This chatbot is equipped with natural language processing models such as Rasa and Dialogflow, and can automatically respond to common questions while escalating complex issues to a human resource representative. 【0105】 For example, a sales representative for an electronic payment service could refer to the data generated by this system during a weekly meeting and propose a strategy for effectively approaching a newly targeted customer segment. 【0106】 A concrete example of a prompt message for the generating AI model is, "Based on the latest customer transaction data, analyze patterns with high conversion rates and propose new sales opportunities." By using this prompt, the system provides quick and accurate sales support, improving the efficiency and effectiveness of sales activities. 【0107】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0108】 Step 1: 【0109】 The server retrieves historical sales data from CRM systems and sales analysis tools. This data includes customer information and transaction history, which is used as input. The retrieved data is cleansed using the Pandas library to remove noise and prepare it for analysis. 【0110】 Step 2: 【0111】 The server uses a machine learning model powered by scikit-learn to analyze the cleansed data as input. This model discovers patterns of successful sales and generates new sales opportunities and improvement suggestions based on specific conditions. These results are then output and provided to the sales team. 【0112】 Step 3: 【0113】 The terminal receives proposals and new project information from the server as input and passes it to an automated agent. This agent sets up appointments using a scheduling management system and uses email templates to communicate quickly with customers. The output of this entire process is an updated customer contact plan. 【0114】 Step 4: 【0115】 The user initiates an immediate response to inquiries entered by the customer into a real-time chatbot launched on their device. This chatbot uses natural language processing models such as Rasa and Dialogflow to analyze the question and automatically generate an appropriate reply. For complex questions, it can escalate to a human resource representative. The output of this step is a fast and accurate response designed to improve customer satisfaction. 【0116】 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. 【0117】 This invention incorporates an emotion engine into a system that automates sales support and customer service, thereby recognizing the user's emotional state in real time and improving the quality of sales activities and customer service. In addition to conventional functions such as analyzing past sales data, identifying new leads, and proposing improvements to sales activities, this system enables more appropriate communication by utilizing emotional information during interactions with users. 【0118】 The server retrieves data from CRM systems and sales analytics tools and analyzes this data using generation algorithms. Based on the analysis results, it proposes solutions for identifying new leads and improving sales activities. These proposals include customer segment-specific approaches and specific strategies for increasing conversion rates. 【0119】 The terminal receives sales strategies provided by the server and uses automated agents to schedule appointments and handle emails. It also features a real-time chatbot that analyzes the user's emotional state through an emotion engine, facilitating natural conversations with customers. 【0120】 When users respond to customer inquiries via their devices, they can adjust their approach based on feedback provided by the emotion engine. For example, if a customer's response is negative, the emotion engine detects this and prompts the user to respond more flexibly. Conversely, if the customer's interest is high, recommendations are made for developing sales techniques. 【0121】 As a concrete example, the emotion engine analyzes the user's stress level during customer interactions and, if necessary, makes suggestions to reduce their workload. This feedback enables users to operate more efficiently and with less stress, ultimately contributing to improved customer satisfaction. 【0122】 In this way, the present invention integrates emotion recognition technology into a sales support system, enabling simultaneous improvement of operational efficiency and the quality of customer service. As a result, the effectiveness of sales activities is maximized, and the overall competitiveness of the company is strengthened. 【0123】 The following describes the processing flow. 【0124】 Step 1: 【0125】 The server retrieves sales data such as customer information, deal history, and sales performance from databases of CRM systems and sales analytics tools. The retrieved data is then formatted for easier analysis and stored in the server's internal data storage. 【0126】 Step 2: 【0127】 The server starts data analysis using a generative algorithm based on the stored sales data. It applies machine learning models to identify successful patterns and determine which approaches are effective for which customer segments. 【0128】 Step 3: 【0129】 The server proposes sales strategies based on the analysis results. These proposals include, for example, additional offers for existing customers, approaches for potential customers, and messaging strategies. These proposals are generated in report format and distributed to the sales department. 【0130】 Step 4: 【0131】 The terminal uses an automated agent to schedule appointments and handle customer emails based on the proposed sales strategy. Using email templates, it's possible to respond to a large number of customers individually in a short amount of time. 【0132】 Step 5: 【0133】 The device integrates a real-time chatbot, and an emotion engine operates during interactions with the user. It analyzes the customer's emotions during the conversation and generates appropriate responses based on that emotional information. 【0134】 Step 6: 【0135】 Users receive sentiment analysis feedback from the chatbot and adjust their interactions accordingly. For example, if a customer expresses dissatisfaction, they are instructed to flexibly change their approach. Furthermore, when the sentiment engine detects a high level of interest, actions are prompted to provide more in-depth sales proposals. 【0136】 Step 7: 【0137】 The server records activity data, including user interaction results, and uses this data for future sales analysis. This allows the entire system to be continuously improved, leading to increased sales efficiency and customer satisfaction for users. 【0138】 (Example 2) 【0139】 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." 【0140】 In traditional sales activities, sales representatives were unable to fully utilize customer information and struggled to respond appropriately to customer interactions. As a result, improving closing rates and customer satisfaction was difficult. Furthermore, there was a need to understand customer emotions in real time and provide responses accordingly. 【0141】 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. 【0142】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the information using a generation AI model, and means for discovering new cases and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved quality of customer service. 【0143】 "Past sales-related information" is a general term for all data related to sales activities, including customer history, transaction history, and communication history. 【0144】 A "generative AI model" is an artificial intelligence model used to analyze data and perform predictions and classifications, and it includes techniques such as machine learning and deep learning. 【0145】 An "automated process system" is a collection of programs or functions that automatically perform tasks such as scheduling appointments and processing emails. 【0146】 A "real-time dialogue system" is software or a program designed to engage in instantaneous conversations with users or customers, and often utilizes natural language processing technology. 【0147】 "Analyzing emotional states" refers to the process of identifying and understanding emotions from the voice, text, facial expressions, etc., of users and customers. 【0148】 This invention is a system that improves the efficiency of sales activities and the quality of customer service. In this system, the server, terminals, and users each play their respective roles and work together. The specific software includes a CRM system and sales analysis tools, a sentiment analysis API, and a real-time chat system equipped with natural language processing technology. 【0149】 server 【0150】 The server retrieves historical sales-related information from various data sources. Examples of software used include business information systems and customer relationship management (CRM) software. The retrieved information is then analyzed using Python's pandas library and machine learning algorithms (e.g., TENSORFLOW®, scikit-learn). Through this analysis, the server detects new leads and generates optimized sales strategies based on the analysis results. 【0151】 terminal 【0152】 The terminal automates processes such as scheduling and email correspondence based on sales strategies received from the server. This utilizes automation tools and scheduling programs. Furthermore, it features a chat function that leverages natural language processing technology to enable real-time interaction with customers. This function analyzes the user's emotional state via an emotion analysis API and determines the appropriate response. 【0153】 User 【0154】 When users communicate with customers using their devices, they receive feedback based on analysis results, which helps them improve the quality of their interactions. For example, by knowing the customer's emotional changes in real time, users can facilitate communication that reduces stress. Also, if positive emotions are detected, they can suggest ways of highlighting the product's advantages. 【0155】 Specific examples and prompt statements 【0156】 For example, if this system detects signs that a customer is interested in a product, the terminal can display a prompt message to the user such as: "It appears the customer is showing increased interest. Please explain the product's features and benefits in more detail and emphasize its value." This prompt message enables the effective development of sales activities. 【0157】 This invention makes it possible to achieve an efficient and responsive sales process, dramatically improving customer satisfaction and a company's competitiveness. 【0158】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0159】 Step 1: 【0160】 The server retrieves historical sales-related information from data sources. This information includes customer history, transaction history, and past communication history. Customer profiles are retrieved from the CRM system as input data, and the information is organized based on this. The data is centralized and converted into an analyzable format. 【0161】 Step 2: 【0162】 The server analyzes acquired sales-related information using a generation AI model. Specifically, it preprocesses the data using the Python pandas library and analyzes the data using machine learning algorithms (e.g., TensorFlow). It receives organized customer information as input and outputs the potential for new deals and successful sales patterns. Based on the analysis results, sales strategy proposals are generated. 【0163】 Step 3: 【0164】 The server transmits the sales strategy obtained through analysis to the terminal. This transmission uses data transfer via network communication. Using the analysis results as input, the server provides optimized sales strategy data to the terminal as output. 【0165】 Step 4: 【0166】 The terminal receives sales strategies sent from the server and uses an automated process system to handle scheduling and email correspondence. Specific actions include scheduling meetings using a calendar application and assisting with email creation using pre-defined templates. The input is the sales strategy from the server, and the output is the execution of specific actions. 【0167】 Step 5: 【0168】 The terminal uses a real-time dialogue system to handle customer interactions. This system uses an emotion analysis API to analyze the emotional state of users and customers in real time. It receives customer inquiries and conversation data as input and outputs responses that correspond to the emotional state. 【0169】 Step 6: 【0170】 The user adjusts communication with the customer based on feedback provided from the device. Specifically, they refer to the results of sentiment analysis and proceed with the dialogue according to suggested prompts. For example, if the customer's interest is high, they will provide a more detailed product explanation. The system uses real-time analyzed customer sentiment data as input and provides adjusted communication as output. 【0171】 (Application Example 2) 【0172】 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". 【0173】 In modern e-commerce, providing personalized service tailored to the user's emotional state is essential to more effectively drive customer purchasing behavior. However, traditional systems have struggled to recognize user emotions in real time and provide product recommendations and promotions accordingly. As a result, improvements in customer satisfaction and purchasing intent have been limited. 【0174】 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. 【0175】 In this invention, the server includes means for acquiring past business data, means for analyzing the acquired data using a generation algorithm, and means for recognizing the user's emotions in real time and providing product recommendations and purchase promotions according to that state. This enables personalized purchase suggestions based on the customer's emotions. 【0176】 "Past business data" refers to all information about corporate activities accumulated in the past, and analyzing this data can contribute to the discovery of new business opportunities and improvement measures. 【0177】 A "generative algorithm" is a computational method for deriving new insights based on data, and it commonly uses machine learning models. 【0178】 An "automation agent" refers to a program or software system that mechanically executes specific business processes, with the aim of minimizing human intervention. 【0179】 A "real-time response system" refers to a system that provides immediate responses to user input and inquiries, and often utilizes natural language processing technology. 【0180】 "A means of recognizing user emotions in real time and providing product recommendations and purchase promotions tailored to that state" refers to technology that instantly evaluates the emotional state of a user and generates personalized purchase suggestions based on that evaluation. 【0181】 The system implementing this invention consists of a server that analyzes past business data, a terminal that interfaces with customers, and a user that improves business operations based on customer feedback. 【0182】 The server plays a central role in data processing, retrieving historical business data from the database and analyzing it using a generative algorithm. This generative algorithm leverages machine learning models to identify successful business patterns. Suitable software for data analysis includes AWS® data analysis tools and Google Cloud Machine Learning. For sentiment analysis, sentiment analysis APIs such as AWS Rekognition and Google Cloud Vision are used. 【0183】 The terminal functions as the user-customer interface and can be a smartphone or computer. The terminal is equipped with a real-time response system that uses natural language processing models to immediately respond to customer inquiries. Furthermore, the terminal's camera and microphone recognize the user's emotions in real time and transmit this information to the server. This enables emotion-based product recommendations and purchase promotions. 【0184】 Users make decisions to improve business processes based on information and feedback provided through their devices. For example, if positive emotions are detected while a user is browsing a product page on their device, the server will suggest related products in that category and promote sales. 【0185】 For example, when a user is searching for a new home appliance and clearly shows interest, related accessories will be suggested to them. In this way, a dynamic purchasing experience based on the user's emotions is provided. Example prompt: "Use the user's emotion management system to determine their level of interest and suggest products they are likely to purchase." 【0186】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0187】 Step 1: 【0188】 The server retrieves historical business data from the database. This data includes past sales history and customer behavior logs. The input is raw data from the database, and the output is a formatted dataset prepared for analysis. This data forms the basis for subsequent generation algorithm processing. 【0189】 Step 2: 【0190】 The server analyzes the acquired data using a generation algorithm. This algorithm utilizes machine learning models to perform calculations to identify successful patterns and trends. The input is a prepared dataset, and the output is insights into successful patterns and relevant variables. This process enables the development of new business strategies. 【0191】 Step 3: 【0192】 The terminal acts as a real-time interface with the customer, using a camera and microphone to acquire user emotional information. Input consists of camera video and audio data, while output is the user's emotional state as determined by an emotional analysis API. This emotional information is sent to a server and used for context-appropriate actions. 【0193】 Step 4: 【0194】 The server executes an algorithm that recommends relevant products based on the user's emotional state, which is recognized in real time. The input is the user's emotional state and insights obtained through machine learning, and the output is a personalized list of products and promotional suggestions. This ensures that appropriate products are presented according to the user's interests. 【0195】 Step 5: 【0196】 Users review the information presented on their device and make purchasing decisions. Input is recommended product information, and output is a purchase decision or a request for additional information. This feedback is also recorded on the server and used for future data analysis. 【0197】 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. 【0198】 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. 【0199】 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. 【0200】 [Second Embodiment] 【0201】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0202】 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. 【0203】 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). 【0204】 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. 【0205】 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. 【0206】 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). 【0207】 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. 【0208】 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. 【0209】 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. 【0210】 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. 【0211】 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. 【0212】 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". 【0213】 This invention is a system for automating sales support and customer service, and can be implemented as follows. This system analyzes past sales data and automatically proposes solutions for identifying new leads and improving sales activities. Furthermore, it improves sales efficiency by supporting appointment setting and real-time responses to customer inquiries in sales activities. 【0214】 The server retrieves necessary data from databases of CRM systems and sales analytics tools that manage sales data. This data includes customer information, transaction history, and past sales performance. The server analyzes the retrieved data using generation algorithms to identify patterns of sales success and new sales opportunities. 【0215】 Based on the analysis results, the server generates improvement suggestions for specific customer segments and notifies the sales team. These suggestions may include implementing email campaigns or optimizing visit schedules. In particular, it identifies customer segments that tend to have a high conversion rate and recommends appropriate approaches to sales representatives for those segments. 【0216】 The terminal receives new case information provided by the server, incorporates it into the schedule using an automated agent, and sets up appointments with customers as needed. The terminal's email system also enables quick email replies to customers using predefined templates. 【0217】 Users utilize a real-time chatbot installed on their devices to provide immediate responses to customer inquiries. The chatbot automatically responds to general questions and escalates complex issues to the user. This enables prompt responses that satisfy customers. 【0218】 In this way, the present invention highly automates sales and customer service processes, achieving operational efficiency and improved customer satisfaction. Specifically, sales teams can utilize automatically generated proposals in weekly meetings to plan and adjust strategies. This entire process is useful in improving the quality of sales and, in particular, in promoting the early development of junior sales members. 【0219】 The following describes the processing flow. 【0220】 Step 1: 【0221】 The server connects to the CRM system and sales analytics tools to retrieve sales data for the past 30 days. This data includes customer information, transaction history, and sales performance. This data is converted into a format suitable for analysis and stored in a database on the server. 【0222】 Step 2: 【0223】 The server activates a generation algorithm and begins analysis using the stored sales data. The server considers factors such as customer attributes and purchase history, and uses a machine learning model to identify successful sales patterns and discover new business opportunities. 【0224】 Step 3: 【0225】 Based on the analysis results, the server generates improvement suggestions to optimize sales activities. These suggestions include targeted approaches to specific customer segments and sales strategies to increase closing rates. The generated suggestions are sent to the sales team as a report. 【0226】 Step 4: 【0227】 The terminal receives new case information from the server and uses an automated agent to set up schedules and appointments. The terminal sends scheduling emails to customers and receives responses as needed. 【0228】 Step 5: 【0229】 Users receive customer inquiries using a real-time chatbot installed on their devices. The chatbot automatically responds to general questions, and complex issues are escalated to the user. The user then manually provides detailed answers based on this information. 【0230】 Step 6: 【0231】 The server records the results of users' sales activities and customer interactions, and uses this data for subsequent analysis. This allows the entire system to be continuously improved, enhancing sales efficiency and effectiveness. 【0232】 (Example 1) 【0233】 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." 【0234】 In sales activities, efficiently acquiring and analyzing information necessary for identifying new leads and improving sales processes is crucial. However, many companies are unable to fully utilize the vast amount of data they possess, and lack the appropriate tools and processes for efficient sales activities. As a result, problems arise such as a decline in the quality of customer service and a decrease in sales efficiency. 【0235】 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. 【0236】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the acquired information using a machine learning algorithm, and means for identifying new business opportunities and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved customer satisfaction. 【0237】 "Sales-related information" refers to all data related to sales activities, such as customer information, transaction history, and sales performance. 【0238】 A "machine learning algorithm" refers to a method that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0239】 "New business opportunities" refer to potential future transactions and projects that are discovered based on existing sales activities. 【0240】 "Improvement measures" refer to specific action plans aimed at improving the efficiency and results of sales activities. 【0241】 An "automated management agent" refers to a program that assists users by automating the setting and execution of plans. 【0242】 "Communication support" refers to activities that involve communicating with customers through email, messages, and other means. 【0243】 A "real-time conversational agent" refers to a system that automatically interacts with users in real time, using tools such as chatbots. 【0244】 "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language. 【0245】 This invention is a system for automating and streamlining sales activities. The following hardware and software are used to implement the invention. 【0246】 The server first retrieves sales-related information from customer relationship management databases and sales analytics tools. This includes customer information, transaction history, and past sales performance. Specifically, databases such as SQL Server and MySQL are used, and the server extracts information using SQL queries. The server then inputs this information into a generating AI model and analyzes the data through machine learning algorithms. This analysis process can discover successful sales patterns and identify new business opportunities. 【0247】 The terminal uses analysis results received from the server and an automated management agent to schedule appointments based on the sales representative's schedule. For example, it can automatically add new cases using the Google Calendar API and optimize visit schedules. Furthermore, the terminal's email system uses templates provided by the server to ensure rapid communication with customers. 【0248】 Users utilize a real-time conversational agent built into their devices to respond to customer inquiries in real time. Using natural language processing technology, the agent automatically answers common questions, while allowing users to provide detailed responses to more complex inquiries. This enables fast and highly accurate customer service. 【0249】 As a concrete example, users can formulate strategies based on proposals generated by the server during weekly sales meetings. This process is particularly useful for developing the skills of junior sales members. Furthermore, an example of a prompt to input into the AI ​​model is, "Based on past sales data, please identify customer segments with high conversion rates and generate proposals to optimize visit schedules." In this way, it is possible to improve the quality and efficiency of the entire sales process. 【0250】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0251】 Step 1: 【0252】 The server retrieves sales-related information from customer relationship management databases and sales analytics tools. Inputs include database query requests, which output customer information, transaction history, sales performance, and other data from systems such as SQL Server and MySQL. This data is collected for initial analysis and subsequent processing. 【0253】 Step 2: 【0254】 The server inputs the acquired sales-related information into a generating AI model, which then analyzes it using machine learning algorithms. The input is the dataset acquired in Step 1, and the output is the identification of successful sales patterns and new business opportunities. Data processing includes feature extraction and normalization, and a mechanism is built in which the AI ​​model uses this data to discover patterns. 【0255】 Step 3: 【0256】 The server proposes improvement measures based on the analysis results. The input is the analysis results from step 2, and the output is a proposal for implementing a specific campaign or an optimized visit schedule. Specifically, the server automatically generates the proposal and prepares to notify the sales team. 【0257】 Step 4: 【0258】 The terminal uses an automated management agent to add new case information received from the server to the schedule. The input is a suggestion for improvement measures, and the output is new appointment information added to the sales representative's calendar. The system uses the Google Calendar API or similar tools to ensure that the changes are properly reflected in each representative's schedule. 【0259】 Step 5: 【0260】 The terminal's email system uses server templates to send emails to customers. The input is an email template based on the proposal in Step 3, and the output is the email content sent to the customer. The email system will perform individual customizations as needed to provide the most relevant information to the customer. 【0261】 Step 6: 【0262】 Users respond to customer inquiries using a real-time conversational agent. The input is the customer's inquiry, and the output is either an automated response from the agent or a direct response from the user. Specifically, the chatbot provides standard responses to general questions, while the user takes over for more complex inquiries. 【0263】 (Application Example 1) 【0264】 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 glasses 214 will be referred to as the "terminal." 【0265】 This invention aims to solve the problems of decreased efficiency in sales activities and reduced customer satisfaction due to delays in customer service. In particular, in electronic payment services, there is a demand for rapid analysis of transaction data and proposals that meet customer needs. To meet these demands, it is necessary to support the sales team and automate customer service. 【0266】 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. 【0267】 In this invention, the server includes means for acquiring past sales data, means for analyzing the acquired data using a generation algorithm, and means for identifying new projects and proposing improvement measures based on the analysis results. This makes it possible to improve sales efficiency and provide prompt and accurate customer service in electronic payment services. 【0268】 "Past sales data" refers to customer information and transaction history recorded in the past during sales activities, and is data used for sales analysis and evaluation. 【0269】 A "generative algorithm" is a computational method for deriving useful patterns or information from input data, and machine learning models are an example of this. 【0270】 An "automation agent" is a program or system that automatically performs specific tasks, such as scheduling appointments or responding to emails. 【0271】 A "real-time chatbot" is a conversational program that can respond to user inquiries immediately, and it uses natural language processing to automatically provide answers. 【0272】 An "electronic payment service" is a service that provides a system for paying for goods and services online using digital technology. 【0273】 "Transaction data" refers to data containing information about commercial transactions, including purchase history and payment information. 【0274】 A "machine learning model" is a collection of algorithms that learn patterns from data and use that knowledge to make predictions and judgments about new data. 【0275】 "Customer requirements" refer to the specific needs and expectations that a buyer or service user desires for a product or service. 【0276】 "Automatic response means" refers to a technology or system that automatically generates and provides a response to the user in response to specific conditions. 【0277】 The system in this invention is realized through the respective roles of the server, terminal, and user. 【0278】 The server first retrieves historical sales data from CRM systems and sales analysis tools. Specifically, it collects data using Python and performs data cleansing and preprocessing using the Pandas library. Next, it uses a machine learning model with scikit-learn to analyze the data and identify patterns of successful sales. Based on these analysis results, it automatically generates strategies for identifying new leads and improving sales activities. 【0279】 The terminal receives proposals and new project information provided by the server. Based on this information, the automated agent quickly sets up appointments and responds to emails using pre-prepared templates. 【0280】 Furthermore, users can instantly respond to customer inquiries by utilizing a real-time chatbot. This chatbot is equipped with natural language processing models such as Rasa and Dialogflow, and can automatically respond to common questions while escalating complex issues to a human resource representative. 【0281】 As a specific example, it is possible for a salesperson of an electronic payment service to refer to the data generated by this system in a weekly meeting and propose as a strategy an effective approach to a newly targeted customer segment. 【0282】 As a specific example of a prompt sentence for a generative AI model, there is "Based on the latest customer transaction data, analyze patterns with a high conversion rate and propose new business opportunities." By using this prompt, the system provides quick and accurate sales support, improving the efficiency and effectiveness of sales activities. 【0283】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0284】 Step 1: 【0285】 The server acquires past sales data from a CRM system or a sales analysis tool. This data includes customer information and transaction histories, which are used as input. The acquired data is cleansed using the Pandas library and noise is removed to prepare it in a state suitable for analysis. 【0286】 Step 2: 【0287】 The server performs analysis using a machine learning model using scikit-learn with the cleansed data as input. This model discovers patterns of sales success and generates new business cases and improvement proposals based on specific conditions. This result is output and provided to the sales team. 【0288】 Step 3: 【0289】 The terminal passes the proposals and new case information received from the server as input to an automated agent. This agent sets appointments in a schedule management system and conducts prompt communication with customers using a mail template. The output of this series of processes is an updated customer contact plan. 【0290】 Step 4: 【0291】 The user initiates an immediate response to inquiries entered by the customer into a real-time chatbot launched on their device. This chatbot uses natural language processing models such as Rasa and Dialogflow to analyze the question and automatically generate an appropriate reply. For complex questions, it can escalate to a human resource representative. The output of this step is a fast and accurate response designed to improve customer satisfaction. 【0292】 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. 【0293】 This invention incorporates an emotion engine into a system that automates sales support and customer service, thereby recognizing the user's emotional state in real time and improving the quality of sales activities and customer service. In addition to conventional functions such as analyzing past sales data, identifying new leads, and proposing improvements to sales activities, this system enables more appropriate communication by utilizing emotional information during interactions with users. 【0294】 The server retrieves data from CRM systems and sales analytics tools and analyzes this data using generation algorithms. Based on the analysis results, it proposes solutions for identifying new leads and improving sales activities. These proposals include customer segment-specific approaches and specific strategies for increasing conversion rates. 【0295】 The terminal receives sales strategies provided by the server and uses automated agents to schedule appointments and handle emails. It also features a real-time chatbot that analyzes the user's emotional state through an emotion engine, facilitating natural conversations with customers. 【0296】 When users respond to customer inquiries via their devices, they can adjust their approach based on feedback provided by the emotion engine. For example, if a customer's response is negative, the emotion engine detects this and prompts the user to respond more flexibly. Conversely, if the customer's interest is high, recommendations are made for developing sales techniques. 【0297】 As a concrete example, the emotion engine analyzes the user's stress level during customer interactions and, if necessary, makes suggestions to reduce their workload. This feedback enables users to operate more efficiently and with less stress, ultimately contributing to improved customer satisfaction. 【0298】 In this way, the present invention integrates emotion recognition technology into a sales support system, enabling simultaneous improvement of operational efficiency and the quality of customer service. As a result, the effectiveness of sales activities is maximized, and the overall competitiveness of the company is strengthened. 【0299】 The following describes the processing flow. 【0300】 Step 1: 【0301】 The server retrieves sales data such as customer information, deal history, and sales performance from databases of CRM systems and sales analytics tools. The retrieved data is then formatted for easier analysis and stored in the server's internal data storage. 【0302】 Step 2: 【0303】 The server starts data analysis using a generative algorithm based on the stored sales data. It applies machine learning models to identify successful patterns and determine which approaches are effective for which customer segments. 【0304】 Step 3: 【0305】 The server proposes a business strategy based on the analysis results. The proposals include, for example, additional proposals for existing customers, approach methods for potential customers, messaging strategies, etc. These proposals are generated in report form and distributed to the sales department. 【0306】 Step 4: 【0307】 Based on the proposed business strategy, the terminal uses an automated agent to set appointments and conduct email correspondence with customers. Using an email template, it is possible to provide individual responses to many customers in a short time. 【0308】 Step 5: 【0309】 A real-time chatbot is integrated into the terminal, and an emotion engine operates during the interaction with the user. Analyze the customer's emotions during the interaction with the user and generate appropriate responses based on the emotion information. 【0310】 Step 6: 【0311】 The user receives the emotion analysis feedback provided by the chatbot and adjusts the interaction accordingly. For example, when the customer shows dissatisfaction, the user is instructed to change the response flexibly. Also, when the emotion engine detects high interest, actions for making a deeper business proposal are encouraged. 【0312】 Step 7: 【0313】 The server records the activity data including the user's response results and utilizes this data for the next business analysis. As a result, the entire system is continuously improved, and the user's business efficiency and customer satisfaction are enhanced. 【0314】 (Example 2) 【0315】 Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0316】 In traditional sales activities, sales representatives were unable to fully utilize customer information and struggled to respond appropriately to customer interactions. As a result, improving closing rates and customer satisfaction was difficult. Furthermore, there was a need to understand customer emotions in real time and provide responses accordingly. 【0317】 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. 【0318】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the information using a generation AI model, and means for discovering new cases and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved quality of customer service. 【0319】 "Past sales-related information" is a general term for all data related to sales activities, including customer history, transaction history, and communication history. 【0320】 A "generative AI model" is an artificial intelligence model used to analyze data and perform predictions and classifications, and it includes techniques such as machine learning and deep learning. 【0321】 An "automated process system" is a collection of programs or functions that automatically perform tasks such as scheduling appointments and processing emails. 【0322】 A "real-time dialogue system" is software or a program designed to engage in instantaneous conversations with users or customers, and often utilizes natural language processing technology. 【0323】 "Analyzing emotional states" refers to the process of identifying and understanding emotions from the voice, text, facial expressions, etc., of users and customers. 【0324】 This invention is a system that improves the efficiency of sales activities and the quality of customer service. In this system, the server, terminals, and users each play their respective roles and work together. The specific software includes a CRM system and sales analysis tools, a sentiment analysis API, and a real-time chat system equipped with natural language processing technology. 【0325】 server 【0326】 The server retrieves historical sales-related information from various data sources. Examples of software used include business information systems and customer relationship management (CRM) software. The retrieved information is then analyzed using Python's pandas library and machine learning algorithms (such as TensorFlow and scikit-learn). Through this analysis, the server detects new business opportunities and generates optimized sales strategies based on the analysis results. 【0327】 terminal 【0328】 The terminal automates processes such as scheduling and email correspondence based on sales strategies received from the server. This utilizes automation tools and scheduling programs. Furthermore, it features a chat function that leverages natural language processing technology to enable real-time interaction with customers. This function analyzes the user's emotional state via an emotion analysis API and determines the appropriate response. 【0329】 User 【0330】 When users communicate with customers using their devices, they receive feedback based on analysis results, which helps them improve the quality of their interactions. For example, by knowing the customer's emotional changes in real time, users can facilitate communication that reduces stress. Also, if positive emotions are detected, they can suggest ways of highlighting the product's advantages. 【0331】 Specific examples and prompt statements 【0332】 For example, if this system detects signs that a customer is interested in a product, the terminal can display a prompt message to the user such as: "It appears the customer is showing increased interest. Please explain the product's features and benefits in more detail and emphasize its value." This prompt message enables the effective development of sales activities. 【0333】 This invention makes it possible to achieve an efficient and responsive sales process, dramatically improving customer satisfaction and a company's competitiveness. 【0334】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0335】 Step 1: 【0336】 The server retrieves historical sales-related information from data sources. This information includes customer history, transaction history, and past communication history. Customer profiles are retrieved from the CRM system as input data, and the information is organized based on this. The data is centralized and converted into an analyzable format. 【0337】 Step 2: 【0338】 The server analyzes acquired sales-related information using a generation AI model. Specifically, it preprocesses the data using the Python pandas library and analyzes the data using machine learning algorithms (e.g., TensorFlow). It receives organized customer information as input and outputs the potential for new deals and successful sales patterns. Based on the analysis results, sales strategy proposals are generated. 【0339】 Step 3: 【0340】 The server transmits the sales strategy obtained through analysis to the terminal. This transmission uses data transfer via network communication. Using the analysis results as input, the server provides optimized sales strategy data to the terminal as output. 【0341】 Step 4: 【0342】 The terminal receives sales strategies sent from the server and uses an automated process system to handle scheduling and email correspondence. Specific actions include scheduling meetings using a calendar application and assisting with email creation using pre-defined templates. The input is the sales strategy from the server, and the output is the execution of specific actions. 【0343】 Step 5: 【0344】 The terminal uses a real-time dialogue system to handle customer interactions. This system uses an emotion analysis API to analyze the emotional state of users and customers in real time. It receives customer inquiries and conversation data as input and outputs responses that correspond to the emotional state. 【0345】 Step 6: 【0346】 The user adjusts communication with the customer based on feedback provided from the device. Specifically, they refer to the results of sentiment analysis and proceed with the dialogue according to suggested prompts. For example, if the customer's interest is high, they will provide a more detailed product explanation. The system uses real-time analyzed customer sentiment data as input and provides adjusted communication as output. 【0347】 (Application Example 2) 【0348】 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." 【0349】 In modern e-commerce, providing personalized service tailored to the user's emotional state is essential to more effectively drive customer purchasing behavior. However, traditional systems have struggled to recognize user emotions in real time and provide product recommendations and promotions accordingly. As a result, improvements in customer satisfaction and purchasing intent have been limited. 【0350】 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. 【0351】 In this invention, the server includes means for acquiring past business data, means for analyzing the acquired data using a generation algorithm, and means for recognizing the user's emotions in real time and providing product recommendations and purchase promotions according to that state. This enables personalized purchase suggestions based on the customer's emotions. 【0352】 "Past business data" refers to all information about corporate activities accumulated in the past, and analyzing this data can contribute to the discovery of new business opportunities and improvement measures. 【0353】 A "generative algorithm" is a computational method for deriving new insights based on data, and it commonly uses machine learning models. 【0354】 An "automation agent" refers to a program or software system that mechanically executes specific business processes, with the aim of minimizing human intervention. 【0355】 A "real-time response system" refers to a system that provides immediate responses to user input and inquiries, and often utilizes natural language processing technology. 【0356】 "A means of recognizing user emotions in real time and providing product recommendations and purchase promotions tailored to that state" refers to technology that instantly evaluates the emotional state of a user and generates personalized purchase suggestions based on that evaluation. 【0357】 The system implementing this invention consists of a server that analyzes past business data, a terminal that interfaces with customers, and a user that improves business operations based on customer feedback. 【0358】 The server plays a central role in data processing, retrieving historical business data from the database and analyzing it using a generative algorithm. This generative algorithm leverages machine learning models to identify successful business patterns. Suitable software for data analysis includes AWS data analysis tools and Google Cloud Machine Learning. For sentiment analysis, sentiment analysis APIs such as AWS Rekognition and Google Cloud Vision are used. 【0359】 The terminal functions as the user-customer interface and can be a smartphone or computer. The terminal is equipped with a real-time response system that uses natural language processing models to immediately respond to customer inquiries. Furthermore, the terminal's camera and microphone recognize the user's emotions in real time and transmit this information to the server. This enables emotion-based product recommendations and purchase promotions. 【0360】 Users make decisions to improve business processes based on information and feedback provided through their devices. For example, if positive emotions are detected while a user is browsing a product page on their device, the server will suggest related products in that category and promote sales. 【0361】 For example, when a user is searching for a new home appliance and clearly shows interest, related accessories will be suggested to them. In this way, a dynamic purchasing experience based on the user's emotions is provided. Example prompt: "Use the user's emotion management system to determine their level of interest and suggest products they are likely to purchase." 【0362】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0363】 Step 1: 【0364】 The server retrieves historical business data from the database. This data includes past sales history and customer behavior logs. The input is raw data from the database, and the output is a formatted dataset prepared for analysis. This data forms the basis for subsequent generation algorithm processing. 【0365】 Step 2: 【0366】 The server analyzes the acquired data using a generation algorithm. This algorithm utilizes machine learning models to perform calculations to identify successful patterns and trends. The input is a prepared dataset, and the output is insights into successful patterns and relevant variables. This process enables the development of new business strategies. 【0367】 Step 3: 【0368】 The terminal acts as a real-time interface with the customer, using a camera and microphone to acquire user emotional information. Input consists of camera video and audio data, while output is the user's emotional state as determined by an emotional analysis API. This emotional information is sent to a server and used for context-appropriate actions. 【0369】 Step 4: 【0370】 The server executes an algorithm that recommends relevant products based on the user's emotional state, which is recognized in real time. The input is the user's emotional state and insights obtained through machine learning, and the output is a personalized list of products and promotional suggestions. This ensures that appropriate products are presented according to the user's interests. 【0371】 Step 5: 【0372】 Users review the information presented on their device and make purchasing decisions. Input is recommended product information, and output is a purchase decision or a request for additional information. This feedback is also recorded on the server and used for future data analysis. 【0373】 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. 【0374】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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. 【0375】 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. 【0376】 [Third Embodiment] 【0377】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0378】 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. 【0379】 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). 【0380】 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. 【0381】 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. 【0382】 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). 【0383】 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. 【0384】 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. 【0385】 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. 【0386】 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. 【0387】 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. 【0388】 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". 【0389】 This invention is a system for automating sales support and customer service, and can be implemented as follows. This system analyzes past sales data and automatically proposes solutions for identifying new leads and improving sales activities. Furthermore, it improves sales efficiency by supporting appointment setting and real-time responses to customer inquiries in sales activities. 【0390】 The server retrieves necessary data from databases of CRM systems and sales analytics tools that manage sales data. This data includes customer information, transaction history, and past sales performance. The server analyzes the retrieved data using generation algorithms to identify patterns of sales success and new sales opportunities. 【0391】 Based on the analysis results, the server generates improvement suggestions for specific customer segments and notifies the sales team. These suggestions may include implementing email campaigns or optimizing visit schedules. In particular, it identifies customer segments that tend to have a high conversion rate and recommends appropriate approaches to sales representatives for those segments. 【0392】 The terminal receives new case information provided by the server, incorporates it into the schedule using an automated agent, and sets up appointments with customers as needed. The terminal's email system also enables quick email replies to customers using predefined templates. 【0393】 Users utilize a real-time chatbot installed on their devices to provide immediate responses to customer inquiries. The chatbot automatically responds to general questions and escalates complex issues to the user. This enables prompt responses that satisfy customers. 【0394】 In this way, the present invention highly automates sales and customer service processes, achieving operational efficiency and improved customer satisfaction. Specifically, sales teams can utilize automatically generated proposals in weekly meetings to plan and adjust strategies. This entire process is useful in improving the quality of sales and, in particular, in promoting the early development of junior sales members. 【0395】 The following describes the processing flow. 【0396】 Step 1: 【0397】 The server connects to the CRM system and sales analytics tools to retrieve sales data for the past 30 days. This data includes customer information, transaction history, and sales performance. This data is converted into a format suitable for analysis and stored in a database on the server. 【0398】 Step 2: 【0399】 The server activates a generation algorithm and begins analysis using the stored sales data. The server considers factors such as customer attributes and purchase history, and uses a machine learning model to identify successful sales patterns and discover new business opportunities. 【0400】 Step 3: 【0401】 Based on the analysis results, the server generates improvement suggestions to optimize sales activities. These suggestions include targeted approaches to specific customer segments and sales strategies to increase closing rates. The generated suggestions are sent to the sales team as a report. 【0402】 Step 4: 【0403】 The terminal receives new case information from the server and uses an automated agent to set up schedules and appointments. The terminal sends scheduling emails to customers and receives responses as needed. 【0404】 Step 5: 【0405】 Users receive customer inquiries using a real-time chatbot installed on their devices. The chatbot automatically responds to general questions, and complex issues are escalated to the user. The user then manually provides detailed answers based on this information. 【0406】 Step 6: 【0407】 The server records the results of users' sales activities and customer interactions, and uses this data for subsequent analysis. This allows the entire system to be continuously improved, enhancing sales efficiency and effectiveness. 【0408】 (Example 1) 【0409】 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." 【0410】 In sales activities, efficiently acquiring and analyzing information necessary for identifying new leads and improving sales processes is crucial. However, many companies are unable to fully utilize the vast amount of data they possess, and lack the appropriate tools and processes for efficient sales activities. As a result, problems arise such as a decline in the quality of customer service and a decrease in sales efficiency. 【0411】 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. 【0412】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the acquired information using a machine learning algorithm, and means for identifying new business opportunities and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved customer satisfaction. 【0413】 "Sales-related information" refers to all data related to sales activities, such as customer information, transaction history, and sales performance. 【0414】 A "machine learning algorithm" refers to a method that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0415】 "New business opportunities" refer to potential future transactions and projects that are discovered based on existing sales activities. 【0416】 "Improvement measures" refer to specific action plans aimed at improving the efficiency and results of sales activities. 【0417】 An "automated management agent" refers to a program that assists users by automating the setting and execution of plans. 【0418】 "Communication support" refers to activities that involve communicating with customers through email, messages, and other means. 【0419】 A "real-time conversational agent" refers to a system that automatically interacts with users in real time, using tools such as chatbots. 【0420】 "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language. 【0421】 This invention is a system for automating and streamlining sales activities. The following hardware and software are used to implement the invention. 【0422】 The server first retrieves sales-related information from customer relationship management databases and sales analytics tools. This includes customer information, transaction history, and past sales performance. Specifically, databases such as SQL Server and MySQL are used, and the server extracts information using SQL queries. The server then inputs this information into a generating AI model and analyzes the data through machine learning algorithms. This analysis process can discover successful sales patterns and identify new business opportunities. 【0423】 The terminal uses analysis results received from the server and an automated management agent to schedule appointments based on the sales representative's schedule. For example, it can automatically add new cases using the Google Calendar API and optimize visit schedules. Furthermore, the terminal's email system uses templates provided by the server to ensure rapid communication with customers. 【0424】 Users utilize a real-time conversational agent built into their devices to respond to customer inquiries in real time. Using natural language processing technology, the agent automatically answers common questions, while allowing users to provide detailed responses to more complex inquiries. This enables fast and highly accurate customer service. 【0425】 As a concrete example, users can formulate strategies based on proposals generated by the server during weekly sales meetings. This process is particularly useful for developing the skills of junior sales members. Furthermore, an example of a prompt to input into the AI ​​model is, "Based on past sales data, please identify customer segments with high conversion rates and generate proposals to optimize visit schedules." In this way, it is possible to improve the quality and efficiency of the entire sales process. 【0426】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0427】 Step 1: 【0428】 The server retrieves sales-related information from customer relationship management databases and sales analytics tools. Inputs include database query requests, which output customer information, transaction history, sales performance, and other data from systems such as SQL Server and MySQL. This data is collected for initial analysis and subsequent processing. 【0429】 Step 2: 【0430】 The server inputs the acquired sales-related information into a generating AI model, which then analyzes it using machine learning algorithms. The input is the dataset acquired in Step 1, and the output is the identification of successful sales patterns and new business opportunities. Data processing includes feature extraction and normalization, and a mechanism is built in which the AI ​​model uses this data to discover patterns. 【0431】 Step 3: 【0432】 The server proposes improvement measures based on the analysis results. The input is the analysis results from step 2, and the output is a proposal for implementing a specific campaign or an optimized visit schedule. Specifically, the server automatically generates the proposal and prepares to notify the sales team. 【0433】 Step 4: 【0434】 The terminal uses an automated management agent to add new case information received from the server to the schedule. The input is a suggestion for improvement measures, and the output is new appointment information added to the sales representative's calendar. The system uses the Google Calendar API or similar tools to ensure that the changes are properly reflected in each representative's schedule. 【0435】 Step 5: 【0436】 The terminal's email system uses server templates to send emails to customers. The input is an email template based on the proposal in Step 3, and the output is the email content sent to the customer. The email system will perform individual customizations as needed to provide the most relevant information to the customer. 【0437】 Step 6: 【0438】 Users respond to customer inquiries using a real-time conversational agent. The input is the customer's inquiry, and the output is either an automated response from the agent or a direct response from the user. Specifically, the chatbot provides standard responses to general questions, while the user takes over for more complex inquiries. 【0439】 (Application Example 1) 【0440】 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." 【0441】 This invention aims to solve the problems of decreased efficiency in sales activities and reduced customer satisfaction due to delays in customer service. In particular, in electronic payment services, there is a demand for rapid analysis of transaction data and proposals that meet customer needs. To meet these demands, it is necessary to support the sales team and automate customer service. 【0442】 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. 【0443】 In this invention, the server includes means for acquiring past sales data, means for analyzing the acquired data using a generation algorithm, and means for identifying new projects and proposing improvement measures based on the analysis results. This makes it possible to improve sales efficiency and provide prompt and accurate customer service in electronic payment services. 【0444】 "Past sales data" refers to customer information and transaction history recorded in the past during sales activities, and is data used for sales analysis and evaluation. 【0445】 A "generative algorithm" is a computational method for deriving useful patterns or information from input data, and machine learning models are an example of this. 【0446】 An "automation agent" is a program or system that automatically performs specific tasks, such as scheduling appointments or responding to emails. 【0447】 A "real-time chatbot" is a conversational program that can respond to user inquiries immediately, and it uses natural language processing to automatically provide answers. 【0448】 An "electronic payment service" is a service that provides a system for paying for goods and services online using digital technology. 【0449】 "Transaction data" refers to data containing information about commercial transactions, including purchase history and payment information. 【0450】 A "machine learning model" is a collection of algorithms that learn patterns from data and use that knowledge to make predictions and judgments about new data. 【0451】 "Customer requirements" refer to the specific needs and expectations that a buyer or service user desires for a product or service. 【0452】 "Automatic response means" refers to a technology or system that automatically generates and provides a response to the user in response to specific conditions. 【0453】 The system in this invention is realized through the respective roles of the server, terminal, and user. 【0454】 The server first retrieves historical sales data from CRM systems and sales analysis tools. Specifically, it collects data using Python and performs data cleansing and preprocessing using the Pandas library. Next, it uses a machine learning model with scikit-learn to analyze the data and identify patterns of successful sales. Based on these analysis results, it automatically generates strategies for identifying new leads and improving sales activities. 【0455】 The terminal receives proposals and new project information provided by the server. Based on this information, the automated agent quickly sets up appointments and responds to emails using pre-prepared templates. 【0456】 Furthermore, users can instantly respond to customer inquiries by utilizing a real-time chatbot. This chatbot is equipped with natural language processing models such as Rasa and Dialogflow, and can automatically respond to common questions while escalating complex issues to a human resource representative. 【0457】 For example, a sales representative for an electronic payment service could refer to the data generated by this system during a weekly meeting and propose a strategy for effectively approaching a newly targeted customer segment. 【0458】 A concrete example of a prompt message for the generating AI model is, "Based on the latest customer transaction data, analyze patterns with high conversion rates and propose new sales opportunities." By using this prompt, the system provides quick and accurate sales support, improving the efficiency and effectiveness of sales activities. 【0459】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0460】 Step 1: 【0461】 The server retrieves historical sales data from CRM systems and sales analysis tools. This data includes customer information and transaction history, which is used as input. The retrieved data is cleansed using the Pandas library to remove noise and prepare it for analysis. 【0462】 Step 2: 【0463】 The server uses a machine learning model powered by scikit-learn to analyze the cleansed data as input. This model discovers patterns of successful sales and generates new sales opportunities and improvement suggestions based on specific conditions. These results are then output and provided to the sales team. 【0464】 Step 3: 【0465】 The terminal receives proposals and new project information from the server as input and passes it to an automated agent. This agent sets up appointments using a scheduling management system and uses email templates to communicate quickly with customers. The output of this entire process is an updated customer contact plan. 【0466】 Step 4: 【0467】 The user initiates an immediate response to inquiries entered by the customer into a real-time chatbot launched on their device. This chatbot uses natural language processing models such as Rasa and Dialogflow to analyze the question and automatically generate an appropriate reply. For complex questions, it can escalate to a human resource representative. The output of this step is a fast and accurate response designed to improve customer satisfaction. 【0468】 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. 【0469】 This invention incorporates an emotion engine into a system that automates sales support and customer service, thereby recognizing the user's emotional state in real time and improving the quality of sales activities and customer service. In addition to conventional functions such as analyzing past sales data, identifying new leads, and proposing improvements to sales activities, this system enables more appropriate communication by utilizing emotional information during interactions with users. 【0470】 The server retrieves data from CRM systems and sales analytics tools and analyzes this data using generation algorithms. Based on the analysis results, it proposes solutions for identifying new leads and improving sales activities. These proposals include customer segment-specific approaches and specific strategies for increasing conversion rates. 【0471】 The terminal receives sales strategies provided by the server and uses automated agents to schedule appointments and handle emails. It also features a real-time chatbot that analyzes the user's emotional state through an emotion engine, facilitating natural conversations with customers. 【0472】 When users respond to customer inquiries via their devices, they can adjust their approach based on feedback provided by the emotion engine. For example, if a customer's response is negative, the emotion engine detects this and prompts the user to respond more flexibly. Conversely, if the customer's interest is high, recommendations are made for developing sales techniques. 【0473】 As a concrete example, the emotion engine analyzes the user's stress level during customer interactions and, if necessary, makes suggestions to reduce their workload. This feedback enables users to operate more efficiently and with less stress, ultimately contributing to improved customer satisfaction. 【0474】 In this way, the present invention integrates emotion recognition technology into a sales support system, enabling simultaneous improvement of operational efficiency and the quality of customer service. As a result, the effectiveness of sales activities is maximized, and the overall competitiveness of the company is strengthened. 【0475】 The following describes the processing flow. 【0476】 Step 1: 【0477】 The server retrieves sales data such as customer information, deal history, and sales performance from databases of CRM systems and sales analytics tools. The retrieved data is then formatted for easier analysis and stored in the server's internal data storage. 【0478】 Step 2: 【0479】 The server starts data analysis using a generative algorithm based on the stored sales data. It applies machine learning models to identify successful patterns and determine which approaches are effective for which customer segments. 【0480】 Step 3: 【0481】 The server proposes sales strategies based on the analysis results. These proposals include, for example, additional offers for existing customers, approaches for potential customers, and messaging strategies. These proposals are generated in report format and distributed to the sales department. 【0482】 Step 4: 【0483】 The terminal uses an automated agent to schedule appointments and handle customer emails based on the proposed sales strategy. Using email templates, it's possible to respond to a large number of customers individually in a short amount of time. 【0484】 Step 5: 【0485】 The device integrates a real-time chatbot, and an emotion engine operates during interactions with the user. It analyzes the customer's emotions during the conversation and generates appropriate responses based on that emotional information. 【0486】 Step 6: 【0487】 Users receive sentiment analysis feedback from the chatbot and adjust their interactions accordingly. For example, if a customer expresses dissatisfaction, they are instructed to flexibly change their approach. Furthermore, when the sentiment engine detects a high level of interest, actions are prompted to provide more in-depth sales proposals. 【0488】 Step 7: 【0489】 The server records activity data, including user interaction results, and uses this data for future sales analysis. This allows the entire system to be continuously improved, leading to increased sales efficiency and customer satisfaction for users. 【0490】 (Example 2) 【0491】 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." 【0492】 In traditional sales activities, sales representatives were unable to fully utilize customer information and struggled to respond appropriately to customer interactions. As a result, improving closing rates and customer satisfaction was difficult. Furthermore, there was a need to understand customer emotions in real time and provide responses accordingly. 【0493】 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. 【0494】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the information using a generation AI model, and means for discovering new cases and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved quality of customer service. 【0495】 "Past sales-related information" is a general term for all data related to sales activities, including customer history, transaction history, and communication history. 【0496】 A "generative AI model" is an artificial intelligence model used to analyze data and perform predictions and classifications, and it includes techniques such as machine learning and deep learning. 【0497】 An "automated process system" is a collection of programs or functions that automatically perform tasks such as scheduling appointments and processing emails. 【0498】 A "real-time dialogue system" is software or a program designed to engage in instantaneous conversations with users or customers, and often utilizes natural language processing technology. 【0499】 "Analyzing emotional states" refers to the process of identifying and understanding emotions from the voice, text, facial expressions, etc., of users and customers. 【0500】 This invention is a system that improves the efficiency of sales activities and the quality of customer service. In this system, the server, terminals, and users each play their respective roles and work together. The specific software includes a CRM system and sales analysis tools, a sentiment analysis API, and a real-time chat system equipped with natural language processing technology. 【0501】 server 【0502】 The server retrieves historical sales-related information from various data sources. Examples of software used include business information systems and customer relationship management (CRM) software. The retrieved information is then analyzed using Python's pandas library and machine learning algorithms (such as TensorFlow and scikit-learn). Through this analysis, the server detects new business opportunities and generates optimized sales strategies based on the analysis results. 【0503】 terminal 【0504】 The terminal automates processes such as scheduling and email correspondence based on sales strategies received from the server. This utilizes automation tools and scheduling programs. Furthermore, it features a chat function that leverages natural language processing technology to enable real-time interaction with customers. This function analyzes the user's emotional state via an emotion analysis API and determines the appropriate response. 【0505】 User 【0506】 When users communicate with customers using their devices, they receive feedback based on analysis results, which helps them improve the quality of their interactions. For example, by knowing the customer's emotional changes in real time, users can facilitate communication that reduces stress. Also, if positive emotions are detected, they can suggest ways of highlighting the product's advantages. 【0507】 Specific examples and prompt statements 【0508】 For example, if this system detects signs that a customer is interested in a product, the terminal can display a prompt message to the user such as: "It appears the customer is showing increased interest. Please explain the product's features and benefits in more detail and emphasize its value." This prompt message enables the effective development of sales activities. 【0509】 This invention makes it possible to achieve an efficient and responsive sales process, dramatically improving customer satisfaction and a company's competitiveness. 【0510】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0511】 Step 1: 【0512】 The server retrieves historical sales-related information from data sources. This information includes customer history, transaction history, and past communication history. Customer profiles are retrieved from the CRM system as input data, and the information is organized based on this. The data is centralized and converted into an analyzable format. 【0513】 Step 2: 【0514】 The server analyzes acquired sales-related information using a generation AI model. Specifically, it preprocesses the data using the Python pandas library and analyzes the data using machine learning algorithms (e.g., TensorFlow). It receives organized customer information as input and outputs the potential for new deals and successful sales patterns. Based on the analysis results, sales strategy proposals are generated. 【0515】 Step 3: 【0516】 The server transmits the sales strategy obtained through analysis to the terminal. This transmission uses data transfer via network communication. Using the analysis results as input, the server provides optimized sales strategy data to the terminal as output. 【0517】 Step 4: 【0518】 The terminal receives sales strategies sent from the server and uses an automated process system to handle scheduling and email correspondence. Specific actions include scheduling meetings using a calendar application and assisting with email creation using pre-defined templates. The input is the sales strategy from the server, and the output is the execution of specific actions. 【0519】 Step 5: 【0520】 The terminal uses a real-time dialogue system to handle customer interactions. This system uses an emotion analysis API to analyze the emotional state of users and customers in real time. It receives customer inquiries and conversation data as input and outputs responses that correspond to the emotional state. 【0521】 Step 6: 【0522】 The user adjusts communication with the customer based on feedback provided from the device. Specifically, they refer to the results of sentiment analysis and proceed with the dialogue according to suggested prompts. For example, if the customer's interest is high, they will provide a more detailed product explanation. The system uses real-time analyzed customer sentiment data as input and provides adjusted communication as output. 【0523】 (Application Example 2) 【0524】 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." 【0525】 In modern e-commerce, providing personalized service tailored to the user's emotional state is essential to more effectively drive customer purchasing behavior. However, traditional systems have struggled to recognize user emotions in real time and provide product recommendations and promotions accordingly. As a result, improvements in customer satisfaction and purchasing intent have been limited. 【0526】 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. 【0527】 In this invention, the server includes means for acquiring past business data, means for analyzing the acquired data using a generation algorithm, and means for recognizing the user's emotions in real time and providing product recommendations and purchase promotions according to that state. This enables personalized purchase suggestions based on the customer's emotions. 【0528】 "Past business data" refers to all information about corporate activities accumulated in the past, and analyzing this data can contribute to the discovery of new business opportunities and improvement measures. 【0529】 A "generative algorithm" is a computational method for deriving new insights based on data, and it commonly uses machine learning models. 【0530】 An "automation agent" refers to a program or software system that mechanically executes specific business processes, with the aim of minimizing human intervention. 【0531】 A "real-time response system" refers to a system that provides immediate responses to user input and inquiries, and often utilizes natural language processing technology. 【0532】 "A means of recognizing user emotions in real time and providing product recommendations and purchase promotions tailored to that state" refers to technology that instantly evaluates the emotional state of a user and generates personalized purchase suggestions based on that evaluation. 【0533】 The system implementing this invention consists of a server that analyzes past business data, a terminal that interfaces with customers, and a user that improves business operations based on customer feedback. 【0534】 The server plays a central role in data processing, retrieving historical business data from the database and analyzing it using a generative algorithm. This generative algorithm leverages machine learning models to identify successful business patterns. Suitable software for data analysis includes AWS data analysis tools and Google Cloud Machine Learning. For sentiment analysis, sentiment analysis APIs such as AWS Rekognition and Google Cloud Vision are used. 【0535】 The terminal functions as the user-customer interface and can be a smartphone or computer. The terminal is equipped with a real-time response system that uses natural language processing models to immediately respond to customer inquiries. Furthermore, the terminal's camera and microphone recognize the user's emotions in real time and transmit this information to the server. This enables emotion-based product recommendations and purchase promotions. 【0536】 Users make decisions to improve business processes based on information and feedback provided through their devices. For example, if positive emotions are detected while a user is browsing a product page on their device, the server will suggest related products in that category and promote sales. 【0537】 For example, when a user is searching for a new home appliance and clearly shows interest, related accessories will be suggested to them. In this way, a dynamic purchasing experience based on the user's emotions is provided. Example prompt: "Use the user's emotion management system to determine their level of interest and suggest products they are likely to purchase." 【0538】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0539】 Step 1: 【0540】 The server retrieves historical business data from the database. This data includes past sales history and customer behavior logs. The input is raw data from the database, and the output is a formatted dataset prepared for analysis. This data forms the basis for subsequent generation algorithm processing. 【0541】 Step 2: 【0542】 The server analyzes the acquired data using a generation algorithm. This algorithm utilizes machine learning models to perform calculations to identify successful patterns and trends. The input is a prepared dataset, and the output is insights into successful patterns and relevant variables. This process enables the development of new business strategies. 【0543】 Step 3: 【0544】 The terminal acts as a real-time interface with the customer, using a camera and microphone to acquire user emotional information. Input consists of camera video and audio data, while output is the user's emotional state as determined by an emotional analysis API. This emotional information is sent to a server and used for context-appropriate actions. 【0545】 Step 4: 【0546】 The server executes an algorithm that recommends relevant products based on the user's emotional state, which is recognized in real time. The input is the user's emotional state and insights obtained through machine learning, and the output is a personalized list of products and promotional suggestions. This ensures that appropriate products are presented according to the user's interests. 【0547】 Step 5: 【0548】 Users review the information presented on their device and make purchasing decisions. Input is recommended product information, and output is a purchase decision or a request for additional information. This feedback is also recorded on the server and used for future data analysis. 【0549】 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. 【0550】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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. 【0551】 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. 【0552】 [Fourth Embodiment] 【0553】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0554】 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. 【0555】 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). 【0556】 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. 【0557】 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. 【0558】 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). 【0559】 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. 【0560】 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. 【0561】 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. 【0562】 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. 【0563】 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. 【0564】 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. 【0565】 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". 【0566】 This invention is a system for automating sales support and customer service, and can be implemented as follows. This system analyzes past sales data and automatically proposes solutions for identifying new leads and improving sales activities. Furthermore, it improves sales efficiency by supporting appointment setting and real-time responses to customer inquiries in sales activities. 【0567】 The server retrieves necessary data from databases of CRM systems and sales analytics tools that manage sales data. This data includes customer information, transaction history, and past sales performance. The server analyzes the retrieved data using generation algorithms to identify patterns of sales success and new sales opportunities. 【0568】 Based on the analysis results, the server generates improvement suggestions for specific customer segments and notifies the sales team. These suggestions may include implementing email campaigns or optimizing visit schedules. In particular, it identifies customer segments that tend to have a high conversion rate and recommends appropriate approaches to sales representatives for those segments. 【0569】 The terminal receives new case information provided by the server, incorporates it into the schedule using an automated agent, and sets up appointments with customers as needed. The terminal's email system also enables quick email replies to customers using predefined templates. 【0570】 Users utilize a real-time chatbot installed on their devices to provide immediate responses to customer inquiries. The chatbot automatically responds to general questions and escalates complex issues to the user. This enables prompt responses that satisfy customers. 【0571】 In this way, the present invention highly automates sales and customer service processes, achieving operational efficiency and improved customer satisfaction. Specifically, sales teams can utilize automatically generated proposals in weekly meetings to plan and adjust strategies. This entire process is useful in improving the quality of sales and, in particular, in promoting the early development of junior sales members. 【0572】 The following describes the processing flow. 【0573】 Step 1: 【0574】 The server connects to the CRM system and sales analytics tools to retrieve sales data for the past 30 days. This data includes customer information, transaction history, and sales performance. This data is converted into a format suitable for analysis and stored in a database on the server. 【0575】 Step 2: 【0576】 The server activates a generation algorithm and begins analysis using the stored sales data. The server considers factors such as customer attributes and purchase history, and uses a machine learning model to identify successful sales patterns and discover new business opportunities. 【0577】 Step 3: 【0578】 Based on the analysis results, the server generates improvement suggestions to optimize sales activities. These suggestions include targeted approaches to specific customer segments and sales strategies to increase closing rates. The generated suggestions are sent to the sales team as a report. 【0579】 Step 4: 【0580】 The terminal receives new case information from the server and uses an automated agent to set up schedules and appointments. The terminal sends scheduling emails to customers and receives responses as needed. 【0581】 Step 5: 【0582】 Users receive customer inquiries using a real-time chatbot installed on their devices. The chatbot automatically responds to general questions, and complex issues are escalated to the user. The user then manually provides detailed answers based on this information. 【0583】 Step 6: 【0584】 The server records the results of users' sales activities and customer interactions, and uses this data for subsequent analysis. This allows the entire system to be continuously improved, enhancing sales efficiency and effectiveness. 【0585】 (Example 1) 【0586】 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". 【0587】 In sales activities, efficiently acquiring and analyzing information necessary for identifying new leads and improving sales processes is crucial. However, many companies are unable to fully utilize the vast amount of data they possess, and lack the appropriate tools and processes for efficient sales activities. As a result, problems arise such as a decline in the quality of customer service and a decrease in sales efficiency. 【0588】 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. 【0589】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the acquired information using a machine learning algorithm, and means for identifying new business opportunities and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved customer satisfaction. 【0590】 "Sales-related information" refers to all data related to sales activities, such as customer information, transaction history, and sales performance. 【0591】 A "machine learning algorithm" refers to a method that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0592】 "New business opportunities" refer to potential future transactions and projects that are discovered based on existing sales activities. 【0593】 "Improvement measures" refer to specific action plans aimed at improving the efficiency and results of sales activities. 【0594】 An "automated management agent" refers to a program that assists users by automating the setting and execution of plans. 【0595】 "Communication support" refers to activities that involve communicating with customers through email, messages, and other means. 【0596】 A "real-time conversational agent" refers to a system that automatically interacts with users in real time, using tools such as chatbots. 【0597】 "Natural language processing technology" refers to the technology that enables computers to understand and interpret human language. 【0598】 This invention is a system for automating and streamlining sales activities. The following hardware and software are used to implement the invention. 【0599】 The server first retrieves sales-related information from customer relationship management databases and sales analytics tools. This includes customer information, transaction history, and past sales performance. Specifically, databases such as SQL Server and MySQL are used, and the server extracts information using SQL queries. The server then inputs this information into a generating AI model and analyzes the data through machine learning algorithms. This analysis process can discover successful sales patterns and identify new business opportunities. 【0600】 The terminal uses analysis results received from the server and an automated management agent to schedule appointments based on the sales representative's schedule. For example, it can automatically add new cases using the Google Calendar API and optimize visit schedules. Furthermore, the terminal's email system uses templates provided by the server to ensure rapid communication with customers. 【0601】 Users utilize a real-time conversational agent built into their devices to respond to customer inquiries in real time. Using natural language processing technology, the agent automatically answers common questions, while allowing users to provide detailed responses to more complex inquiries. This enables fast and highly accurate customer service. 【0602】 As a concrete example, users can formulate strategies based on proposals generated by the server during weekly sales meetings. This process is particularly useful for developing the skills of junior sales members. Furthermore, an example of a prompt to input into the AI ​​model is, "Based on past sales data, please identify customer segments with high conversion rates and generate proposals to optimize visit schedules." In this way, it is possible to improve the quality and efficiency of the entire sales process. 【0603】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0604】 Step 1: 【0605】 The server retrieves sales-related information from customer relationship management databases and sales analytics tools. Inputs include database query requests, which output customer information, transaction history, sales performance, and other data from systems such as SQL Server and MySQL. This data is collected for initial analysis and subsequent processing. 【0606】 Step 2: 【0607】 The server inputs the acquired sales-related information into a generating AI model, which then analyzes it using machine learning algorithms. The input is the dataset acquired in Step 1, and the output is the identification of successful sales patterns and new business opportunities. Data processing includes feature extraction and normalization, and a mechanism is built in which the AI ​​model uses this data to discover patterns. 【0608】 Step 3: 【0609】 The server proposes improvement measures based on the analysis results. The input is the analysis results from step 2, and the output is a proposal for implementing a specific campaign or an optimized visit schedule. Specifically, the server automatically generates the proposal and prepares to notify the sales team. 【0610】 Step 4: 【0611】 The terminal uses an automated management agent to add new case information received from the server to the schedule. The input is a suggestion for improvement measures, and the output is new appointment information added to the sales representative's calendar. The system uses the Google Calendar API or similar tools to ensure that the changes are properly reflected in each representative's schedule. 【0612】 Step 5: 【0613】 The terminal's email system uses server templates to send emails to customers. The input is an email template based on the proposal in Step 3, and the output is the email content sent to the customer. The email system will perform individual customizations as needed to provide the most relevant information to the customer. 【0614】 Step 6: 【0615】 Users respond to customer inquiries using a real-time conversational agent. The input is the customer's inquiry, and the output is either an automated response from the agent or a direct response from the user. Specifically, the chatbot provides standard responses to general questions, while the user takes over for more complex inquiries. 【0616】 (Application Example 1) 【0617】 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". 【0618】 This invention aims to solve the problems of decreased efficiency in sales activities and reduced customer satisfaction due to delays in customer service. In particular, in electronic payment services, there is a demand for rapid analysis of transaction data and proposals that meet customer needs. To meet these demands, it is necessary to support the sales team and automate customer service. 【0619】 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. 【0620】 In this invention, the server includes means for acquiring past sales data, means for analyzing the acquired data using a generation algorithm, and means for identifying new projects and proposing improvement measures based on the analysis results. This makes it possible to improve sales efficiency and provide prompt and accurate customer service in electronic payment services. 【0621】 "Past sales data" refers to customer information and transaction history recorded in the past during sales activities, and is data used for sales analysis and evaluation. 【0622】 A "generative algorithm" is a computational method for deriving useful patterns or information from input data, and machine learning models are an example of this. 【0623】 An "automation agent" is a program or system that automatically performs specific tasks, such as scheduling appointments or responding to emails. 【0624】 A "real-time chatbot" is a conversational program that can respond to user inquiries immediately, and it uses natural language processing to automatically provide answers. 【0625】 An "electronic payment service" is a service that provides a system for paying for goods and services online using digital technology. 【0626】 "Transaction data" refers to data containing information about commercial transactions, including purchase history and payment information. 【0627】 A "machine learning model" is a collection of algorithms that learn patterns from data and use that knowledge to make predictions and judgments about new data. 【0628】 "Customer requirements" refer to the specific needs and expectations that a buyer or service user desires for a product or service. 【0629】 "Automatic response means" refers to a technology or system that automatically generates and provides a response to the user in response to specific conditions. 【0630】 The system in this invention is realized through the respective roles of the server, terminal, and user. 【0631】 The server first retrieves historical sales data from CRM systems and sales analysis tools. Specifically, it collects data using Python and performs data cleansing and preprocessing using the Pandas library. Next, it uses a machine learning model with scikit-learn to analyze the data and identify patterns of successful sales. Based on these analysis results, it automatically generates strategies for identifying new leads and improving sales activities. 【0632】 The terminal receives proposals and new project information provided by the server. Based on this information, the automated agent quickly sets up appointments and responds to emails using pre-prepared templates. 【0633】 Furthermore, users can instantly respond to customer inquiries by utilizing a real-time chatbot. This chatbot is equipped with natural language processing models such as Rasa and Dialogflow, and can automatically respond to common questions while escalating complex issues to a human resource representative. 【0634】 For example, a sales representative for an electronic payment service could refer to the data generated by this system during a weekly meeting and propose a strategy for effectively approaching a newly targeted customer segment. 【0635】 A concrete example of a prompt message for the generating AI model is, "Based on the latest customer transaction data, analyze patterns with high conversion rates and propose new sales opportunities." By using this prompt, the system provides quick and accurate sales support, improving the efficiency and effectiveness of sales activities. 【0636】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0637】 Step 1: 【0638】 The server retrieves historical sales data from CRM systems and sales analysis tools. This data includes customer information and transaction history, which is used as input. The retrieved data is cleansed using the Pandas library to remove noise and prepare it for analysis. 【0639】 Step 2: 【0640】 The server uses a machine learning model powered by scikit-learn to analyze the cleansed data as input. This model discovers patterns of successful sales and generates new sales opportunities and improvement suggestions based on specific conditions. These results are then output and provided to the sales team. 【0641】 Step 3: 【0642】 The terminal receives proposals and new project information from the server as input and passes it to an automated agent. This agent sets up appointments using a scheduling management system and uses email templates to communicate quickly with customers. The output of this entire process is an updated customer contact plan. 【0643】 Step 4: 【0644】 The user initiates an immediate response to inquiries entered by the customer into a real-time chatbot launched on their device. This chatbot uses natural language processing models such as Rasa and Dialogflow to analyze the question and automatically generate an appropriate reply. For complex questions, it can escalate to a human resource representative. The output of this step is a fast and accurate response designed to improve customer satisfaction. 【0645】 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. 【0646】 This invention incorporates an emotion engine into a system that automates sales support and customer service, thereby recognizing the user's emotional state in real time and improving the quality of sales activities and customer service. In addition to conventional functions such as analyzing past sales data, identifying new leads, and proposing improvements to sales activities, this system enables more appropriate communication by utilizing emotional information during interactions with users. 【0647】 The server retrieves data from CRM systems and sales analytics tools and analyzes this data using generation algorithms. Based on the analysis results, it proposes solutions for identifying new leads and improving sales activities. These proposals include customer segment-specific approaches and specific strategies for increasing conversion rates. 【0648】 The terminal receives sales strategies provided by the server and uses automated agents to schedule appointments and handle emails. It also features a real-time chatbot that analyzes the user's emotional state through an emotion engine, facilitating natural conversations with customers. 【0649】 When users respond to customer inquiries via their devices, they can adjust their approach based on feedback provided by the emotion engine. For example, if a customer's response is negative, the emotion engine detects this and prompts the user to respond more flexibly. Conversely, if the customer's interest is high, recommendations are made for developing sales techniques. 【0650】 As a concrete example, the emotion engine analyzes the user's stress level during customer interactions and, if necessary, makes suggestions to reduce their workload. This feedback enables users to operate more efficiently and with less stress, ultimately contributing to improved customer satisfaction. 【0651】 In this way, the present invention integrates emotion recognition technology into a sales support system, enabling simultaneous improvement of operational efficiency and the quality of customer service. As a result, the effectiveness of sales activities is maximized, and the overall competitiveness of the company is strengthened. 【0652】 The following describes the processing flow. 【0653】 Step 1: 【0654】 The server retrieves sales data such as customer information, deal history, and sales performance from databases of CRM systems and sales analytics tools. The retrieved data is then formatted for easier analysis and stored in the server's internal data storage. 【0655】 Step 2: 【0656】 The server starts data analysis using a generative algorithm based on the stored sales data. It applies machine learning models to identify successful patterns and determine which approaches are effective for which customer segments. 【0657】 Step 3: 【0658】 The server proposes sales strategies based on the analysis results. These proposals include, for example, additional offers for existing customers, approaches for potential customers, and messaging strategies. These proposals are generated in report format and distributed to the sales department. 【0659】 Step 4: 【0660】 The terminal uses an automated agent to schedule appointments and handle customer emails based on the proposed sales strategy. Using email templates, it's possible to respond to a large number of customers individually in a short amount of time. 【0661】 Step 5: 【0662】 The device integrates a real-time chatbot, and an emotion engine operates during interactions with the user. It analyzes the customer's emotions during the conversation and generates appropriate responses based on that emotional information. 【0663】 Step 6: 【0664】 Users receive sentiment analysis feedback from the chatbot and adjust their interactions accordingly. For example, if a customer expresses dissatisfaction, they are instructed to flexibly change their approach. Furthermore, when the sentiment engine detects a high level of interest, actions are prompted to provide more in-depth sales proposals. 【0665】 Step 7: 【0666】 The server records activity data, including user interaction results, and uses this data for future sales analysis. This allows the entire system to be continuously improved, leading to increased sales efficiency and customer satisfaction for users. 【0667】 (Example 2) 【0668】 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". 【0669】 In traditional sales activities, sales representatives were unable to fully utilize customer information and struggled to respond appropriately to customer interactions. As a result, improving closing rates and customer satisfaction was difficult. Furthermore, there was a need to understand customer emotions in real time and provide responses accordingly. 【0670】 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. 【0671】 In this invention, the server includes means for acquiring past sales-related information, means for analyzing the information using a generation AI model, and means for discovering new cases and proposing improvement measures based on the analysis results. This enables increased efficiency in sales activities and improved quality of customer service. 【0672】 "Past sales-related information" is a general term for all data related to sales activities, including customer history, transaction history, and communication history. 【0673】 A "generative AI model" is an artificial intelligence model used to analyze data and perform predictions and classifications, and it includes techniques such as machine learning and deep learning. 【0674】 An "automated process system" is a collection of programs or functions that automatically perform tasks such as scheduling appointments and processing emails. 【0675】 A "real-time dialogue system" is software or a program designed to engage in instantaneous conversations with users or customers, and often utilizes natural language processing technology. 【0676】 "Analyzing emotional states" refers to the process of identifying and understanding emotions from the voice, text, facial expressions, etc., of users and customers. 【0677】 This invention is a system that improves the efficiency of sales activities and the quality of customer service. In this system, the server, terminals, and users each play their respective roles and work together. The specific software includes a CRM system and sales analysis tools, a sentiment analysis API, and a real-time chat system equipped with natural language processing technology. 【0678】 server 【0679】 The server retrieves historical sales-related information from various data sources. Examples of software used include business information systems and customer relationship management (CRM) software. The retrieved information is then analyzed using Python's pandas library and machine learning algorithms (such as TensorFlow and scikit-learn). Through this analysis, the server detects new business opportunities and generates optimized sales strategies based on the analysis results. 【0680】 terminal 【0681】 The terminal automates processes such as scheduling and email correspondence based on sales strategies received from the server. This utilizes automation tools and scheduling programs. Furthermore, it features a chat function that leverages natural language processing technology to enable real-time interaction with customers. This function analyzes the user's emotional state via an emotion analysis API and determines the appropriate response. 【0682】 User 【0683】 When users communicate with customers using their devices, they receive feedback based on analysis results, which helps them improve the quality of their interactions. For example, by knowing the customer's emotional changes in real time, users can facilitate communication that reduces stress. Also, if positive emotions are detected, they can suggest ways of highlighting the product's advantages. 【0684】 Specific examples and prompt statements 【0685】 For example, if this system detects signs that a customer is interested in a product, the terminal can display a prompt message to the user such as: "It appears the customer is showing increased interest. Please explain the product's features and benefits in more detail and emphasize its value." This prompt message enables the effective development of sales activities. 【0686】 This invention makes it possible to achieve an efficient and responsive sales process, dramatically improving customer satisfaction and a company's competitiveness. 【0687】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0688】 Step 1: 【0689】 The server retrieves historical sales-related information from data sources. This information includes customer history, transaction history, and past communication history. Customer profiles are retrieved from the CRM system as input data, and the information is organized based on this. The data is centralized and converted into an analyzable format. 【0690】 Step 2: 【0691】 The server analyzes acquired sales-related information using a generation AI model. Specifically, it preprocesses the data using the Python pandas library and analyzes the data using machine learning algorithms (e.g., TensorFlow). It receives organized customer information as input and outputs the potential for new deals and successful sales patterns. Based on the analysis results, sales strategy proposals are generated. 【0692】 Step 3: 【0693】 The server transmits the sales strategy obtained through analysis to the terminal. This transmission uses data transfer via network communication. Using the analysis results as input, the server provides optimized sales strategy data to the terminal as output. 【0694】 Step 4: 【0695】 The terminal receives sales strategies sent from the server and uses an automated process system to handle scheduling and email correspondence. Specific actions include scheduling meetings using a calendar application and assisting with email creation using pre-defined templates. The input is the sales strategy from the server, and the output is the execution of specific actions. 【0696】 Step 5: 【0697】 The terminal uses a real-time dialogue system to handle customer interactions. This system uses an emotion analysis API to analyze the emotional state of users and customers in real time. It receives customer inquiries and conversation data as input and outputs responses that correspond to the emotional state. 【0698】 Step 6: 【0699】 The user adjusts communication with the customer based on feedback provided from the device. Specifically, they refer to the results of sentiment analysis and proceed with the dialogue according to suggested prompts. For example, if the customer's interest is high, they will provide a more detailed product explanation. The system uses real-time analyzed customer sentiment data as input and provides adjusted communication as output. 【0700】 (Application Example 2) 【0701】 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". 【0702】 In modern e-commerce, providing personalized service tailored to the user's emotional state is essential to more effectively drive customer purchasing behavior. However, traditional systems have struggled to recognize user emotions in real time and provide product recommendations and promotions accordingly. As a result, improvements in customer satisfaction and purchasing intent have been limited. 【0703】 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. 【0704】 In this invention, the server includes means for acquiring past business data, means for analyzing the acquired data using a generation algorithm, and means for recognizing the user's emotions in real time and providing product recommendations and purchase promotions according to that state. This enables personalized purchase suggestions based on the customer's emotions. 【0705】 "Past business data" refers to all information about corporate activities accumulated in the past, and analyzing this data can contribute to the discovery of new business opportunities and improvement measures. 【0706】 A "generative algorithm" is a computational method for deriving new insights based on data, and it commonly uses machine learning models. 【0707】 An "automation agent" refers to a program or software system that mechanically executes specific business processes, with the aim of minimizing human intervention. 【0708】 A "real-time response system" refers to a system that provides immediate responses to user input and inquiries, and often utilizes natural language processing technology. 【0709】 "A means of recognizing user emotions in real time and providing product recommendations and purchase promotions tailored to that state" refers to technology that instantly evaluates the emotional state of a user and generates personalized purchase suggestions based on that evaluation. 【0710】 The system implementing this invention consists of a server that analyzes past business data, a terminal that interfaces with customers, and a user that improves business operations based on customer feedback. 【0711】 The server plays a central role in data processing, retrieving historical business data from the database and analyzing it using a generative algorithm. This generative algorithm leverages machine learning models to identify successful business patterns. Suitable software for data analysis includes AWS data analysis tools and Google Cloud Machine Learning. For sentiment analysis, sentiment analysis APIs such as AWS Rekognition and Google Cloud Vision are used. 【0712】 The terminal functions as the user-customer interface and can be a smartphone or computer. The terminal is equipped with a real-time response system that uses natural language processing models to immediately respond to customer inquiries. Furthermore, the terminal's camera and microphone recognize the user's emotions in real time and transmit this information to the server. This enables emotion-based product recommendations and purchase promotions. 【0713】 Users make decisions to improve business processes based on information and feedback provided through their devices. For example, if positive emotions are detected while a user is browsing a product page on their device, the server will suggest related products in that category and promote sales. 【0714】 For example, when a user is searching for a new home appliance and clearly shows interest, related accessories will be suggested to them. In this way, a dynamic purchasing experience based on the user's emotions is provided. Example prompt: "Use the user's emotion management system to determine their level of interest and suggest products they are likely to purchase." 【0715】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0716】 Step 1: 【0717】 The server retrieves historical business data from the database. This data includes past sales history and customer behavior logs. The input is raw data from the database, and the output is a formatted dataset prepared for analysis. This data forms the basis for subsequent generation algorithm processing. 【0718】 Step 2: 【0719】 The server analyzes the acquired data using a generation algorithm. This algorithm utilizes machine learning models to perform calculations to identify successful patterns and trends. The input is a prepared dataset, and the output is insights into successful patterns and relevant variables. This process enables the development of new business strategies. 【0720】 Step 3: 【0721】 The terminal acts as a real-time interface with the customer, using a camera and microphone to acquire user emotional information. Input consists of camera video and audio data, while output is the user's emotional state as determined by an emotional analysis API. This emotional information is sent to a server and used for context-appropriate actions. 【0722】 Step 4: 【0723】 The server executes an algorithm that recommends relevant products based on the user's emotional state, which is recognized in real time. The input is the user's emotional state and insights obtained through machine learning, and the output is a personalized list of products and promotional suggestions. This ensures that appropriate products are presented according to the user's interests. 【0724】 Step 5: 【0725】 Users review the information presented on their device and make purchasing decisions. Input is recommended product information, and output is a purchase decision or a request for additional information. This feedback is also recorded on the server and used for future data analysis. 【0726】 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. 【0727】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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. 【0728】 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. 【0729】 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. 【0730】 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. 【0731】 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. 【0732】 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. 【0733】 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. 【0734】 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." 【0735】 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. 【0736】 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. 【0737】 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. 【0738】 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. 【0739】 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. 【0740】 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. 【0741】 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. 【0742】 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. 【0743】 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. 【0744】 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. 【0745】 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. 【0746】 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. 【0747】 The following is further disclosed regarding the embodiments described above. 【0748】 (Claim 1) 【0749】 Means of obtaining past sales data, 【0750】 A means of analyzing acquired data using a generation algorithm, 【0751】 A means of identifying new projects and proposing improvement measures based on the analysis results, 【0752】 A means of scheduling appointments and handling emails through an automated agent, 【0753】 A system that includes a means of responding to customer inquiries using a real-time chatbot. 【0754】 (Claim 2) 【0755】 The system according to claim 1, wherein the generation algorithm uses a machine learning model to identify successful sales patterns. 【0756】 (Claim 3) 【0757】 The system according to claim 1, wherein the real-time chatbot uses a natural language processing model to automatically respond to customer inquiries. 【0758】 "Example 1" 【0759】 (Claim 1) 【0760】 Means of obtaining past sales-related information, 【0761】 A means of analyzing acquired information using machine learning algorithms, 【0762】 A means to identify new business opportunities based on the analysis results and propose improvement measures, 【0763】 A means of performing scheduling and communication response through an automated management agent, 【0764】 A system that includes a means of providing customer support using real-time conversational agents. 【0765】 (Claim 2) 【0766】 The system according to claim 1, wherein the machine learning algorithm identifies sales achievement patterns. 【0767】 (Claim 3) 【0768】 The system according to claim 1, wherein the real-time dialogue agent uses natural language processing technology to automatically respond to customer inquiries. 【0769】 "Application Example 1" 【0770】 (Claim 1) 【0771】 Means of obtaining past sales data, 【0772】 A means of analyzing acquired data using a generation algorithm, 【0773】 A means of identifying new projects and proposing improvement measures based on the analysis results, 【0774】 A means of scheduling appointments and handling emails through an automated agent, 【0775】 A means of responding to customer inquiries using a real-time chatbot, 【0776】 Methods for analyzing transaction data from electronic payment services to discover patterns of successful sales, 【0777】 A means of providing sales representatives with proposals tailored to the individual needs of each customer, 【0778】 An automated response system equipped with the function to respond immediately to customer inquiries, 【0779】 A system that includes this. 【0780】 (Claim 2) 【0781】 The system according to claim 1, wherein the generation algorithm uses a machine learning model to identify successful sales patterns. 【0782】 (Claim 3) 【0783】 The system according to claim 1, wherein the real-time chatbot uses a natural language processing model to automatically respond to customer inquiries. 【0784】 "Example 2 of combining an emotion engine" 【0785】 (Claim 1) 【0786】 Means of obtaining past sales-related information, 【0787】 A means of analyzing acquired information using a generative AI model, 【0788】 A means of discovering new projects and proposing improvement measures based on analysis results, 【0789】 A means of performing scheduling and email correspondence through an automated process system, 【0790】 A means of responding to user inquiries using a real-time dialogue system, 【0791】 A system that includes means for analyzing the user's emotional state and adjusting the response accordingly. 【0792】 (Claim 2) 【0793】 The system according to claim 1, wherein the generating AI model uses a machine learning method to identify successful sales patterns. 【0794】 (Claim 3) 【0795】 The system according to claim 1, wherein the real-time dialogue system uses natural language processing technology to automatically respond to user inquiries. 【0796】 "Application example 2 when combining with an emotional engine" 【0797】 (Claim 1) 【0798】 Means of obtaining past business data, 【0799】 A means of analyzing acquired data using a generation algorithm, 【0800】 A means of identifying new business processes and proposing improvement measures based on the analysis results, 【0801】 A means of performing scheduling and electronic message handling through an automated agent, 【0802】 A means of responding to customer inquiries using a real-time response system, 【0803】 A system that recognizes user emotions in real time and includes means to recommend products and promote purchases according to those emotions. 【0804】 (Claim 2) 【0805】 The system according to claim 1, wherein the generation algorithm uses a machine learning model to identify successful business patterns. 【0806】 (Claim 3) 【0807】 The system according to claim 1, wherein the real-time response system uses a natural language processing model to automatically respond to customer inquiries. [Explanation of Symbols] 【0808】 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] Means of obtaining past sales data, A means of analyzing acquired data using a generation algorithm, A means of identifying new projects and proposing improvement measures based on the analysis results, A means of scheduling appointments and handling emails through an automated agent, A system that includes a means of responding to customer inquiries using a real-time chatbot. [Claim 2] The system according to claim 1, wherein the generation algorithm uses a machine learning model to identify successful sales patterns. [Claim 3] The system according to claim 1, wherein the real-time chatbot uses a natural language processing model to automatically respond to customer inquiries.

Images