system

Abstract

We provide the system. [Solution] A means of collecting multiple types of data, including communication data, sales data, and customer data, Means for preprocessing the aforementioned data and converting it into an analyzable format, A means for evaluating and predicting revenue based on the aforementioned preprocessed data, A means for generating an optimal business strategy based on the aforementioned evaluation and prediction results, A means for distributing the generated strategy to an information terminal, Means for collecting and analyzing the results of the implementation of the aforementioned strategy, A system that includes this.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a 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 Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 The inefficiency of manual operations in the collection and analysis of various data increases the complexity of revenue management and hinders the formulation of optimal strategies. Also, the difficulty of making quick decisions in real time causes an opportunity loss for coping with the intensifying market competition. To solve such problems, it is necessary to construct a system that comprehensively analyzes revenues and provides a clear action plan in real time. 【Means for Solving the Problems】 【0005】 This invention provides a system that includes means for collecting multiple types of data, including communication data, sales data, and customer data, and for preprocessing this data into an analyzable format. The system also includes means for evaluating and predicting revenue based on the preprocessed data, and for generating an optimal business strategy based on the evaluation and prediction results. The generated strategy is distributed to information terminals, enabling each store to respond quickly. Furthermore, the results of strategy implementation are collected and analyzed, forming a feedback loop that facilitates continuous improvement. 【0006】 "Communication data" refers to information related to communication contracts, including data such as the number of contracts, contract details, and usage status. 【0007】 "Sales data" refers to data that includes information about terminal sales and the provision of optional services, such as the number of units sold, sales figures, and customer demographics. 【0008】 "Customer data" refers to information about customer attributes and behavior, including data such as age, gender, purchase history, and feedback. 【0009】 "Preprocessing" refers to the process of converting raw data into an analyzable format, and includes data cleaning, missing value imputation, and outlier detection. 【0010】 "Evaluation" refers to the act of analyzing current performance and profitability based on collected data and expressing it as numerical values ​​or indicators. 【0011】 "Prediction" refers to the act of forecasting future earnings or performance based on past data and external factors. 【0012】 A "business strategy" is an action plan aimed at improving profitability and efficiency, and includes plans such as acquiring new customers, sales promotion, and inventory management. 【0013】 "Information terminal" refers to a device used to receive and display generated information and strategies, and includes tablets and computers for use in stores. [Brief explanation of the drawing] 【0014】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined. 【Embodiments for Carrying Out the Invention】 【0015】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0016】 First, the terms used in the following description will be explained. 【0017】 In the following embodiments, a 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. 【0018】 In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0019】 In the following embodiments, a 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. 【0020】 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). 【0021】 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." 【0022】 [First Embodiment] 【0023】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0024】 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. 【0025】 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). 【0026】 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. 【0027】 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. 【0028】 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. 【0029】 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. 【0030】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0031】 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. 【0032】 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. 【0033】 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. 【0034】 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". 【0035】 This system collects management data from each store, analyzes that data using an AI agent, and proposes the optimal revenue improvement strategy. To realize this process, the roles of the server, terminal, and user are clearly defined. 【0036】 The server first collects various data from each store in real time, such as the number of communication contracts, terminal sales, the number of optional services used, and customer feedback. Because this data is generated in large quantities at once, it is collected periodically via the network and stored centrally. 【0037】 Subsequently, before passing the collected data to the AI ​​agent, the server performs preprocessing by converting the data into a format that can be analyzed. Specifically, it imputes missing values ​​and corrects outliers, preparing the data for efficient analysis. 【0038】 Next, the server uses an AI agent to analyze the pre-processed data in detail. At this stage, it comprehensively evaluates the current revenue situation and predicts future revenue by considering historical data and market trends. Based on this analysis, the server generates specific business strategies for maximizing revenue. 【0039】 The terminals play a role in making business strategies delivered from the server visible to store staff. Each terminal has a function to display strategies in an easy-to-understand format, helping staff to quickly implement them. The terminals also have support functions that reduce the workload of staff by automating some processes. 【0040】 Store staff, as users, use the terminals to implement the provided business strategies. Specifically, they conduct promotional campaigns, propose new contracts, optimize inventory, and record the results on the terminals. The terminals then return these results to the server, which are used for analysis in subsequent operations. 【0041】 As a concrete example, if a store wants to promote a new product, the server analyzes market data related to the new product and sales data for similar products from the past, and proposes a promotional strategy tailored to the target customer segment. This strategy is notified to store staff via terminals, allowing them to quickly understand and implement it. This improves the efficiency of sales promotion activities and leads to increased profits. 【0042】 The following describes the processing flow. 【0043】 Step 1: 【0044】 The server collects data in real time from each store, including the number of communication contracts, terminal sales, optional service usage, and customer feedback. This data is automatically collected via a secure network and stored in a central database. 【0045】 Step 2: 【0046】 The server begins processing the collected raw data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. This process ensures the data is clean and suitable for AI analysis. 【0047】 Step 3: 【0048】 The server passes pre-processed data to the AI ​​agent and instructs it to perform the analysis. The AI ​​agent uses machine learning algorithms to analyze the data and evaluate the current revenue situation. It also predicts future revenue based on historical data and market trends. 【0049】 Step 4: 【0050】 The server receives the analysis results from the AI ​​agent and generates an optimal business strategy based on them. This strategy includes acquiring new contracts, sales promotion activities, and streamlining inventory management. 【0051】 Step 5: 【0052】 The server distributes the generated business strategies to the terminals in the stores. This distribution is customized to suit the characteristics and circumstances of each store. 【0053】 Step 6: 【0054】 The terminal visually presents business strategies received from the server to store staff. It clearly displays strategy details, implementation steps, and expected effects, helping staff act quickly and accurately. 【0055】 Step 7: 【0056】 Store staff, acting as users, execute business strategies instructed on their terminals. For example, they might launch a new sales promotion, adjust inventory, or engage in customer outreach activities. Users input the results of their strategy execution into the terminal, which is then sent to the server for further analysis. 【0057】 Step 8: 【0058】 The server analyzes the results from user execution and evaluates the effectiveness of the strategy. Based on this evaluation, the AI ​​agent's algorithm is adjusted to help generate the next strategy. This feedback loop continuously improves the accuracy and effectiveness of the entire system. 【0059】 (Example 1) 【0060】 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." 【0061】 For many companies, effectively formulating business strategies based on diverse data is a crucial challenge. In particular, there is a need to collect large amounts of data in real time, analyze it quickly and accurately to predict future profits, and then develop and implement concrete and actionable business strategies based on those results. However, traditional methods have suffered from the cumbersome preprocessing and analysis of individual data points, resulting in insufficient correlation with actual profit improvement. 【0062】 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. 【0063】 In this invention, the server includes means for acquiring multiple types of information, including communication data, sales data, and customer data, from each location; means for preprocessing the acquired information and converting it into a format suitable for analysis; and means for evaluating revenue and predicting future revenue based on the converted information. This enables efficient use of multifaceted data to generate management strategies, and sustainable revenue improvement through their implementation and evaluation. 【0064】 "Communication data" refers to data related to the usage status and contract information of communication services. 【0065】 "Sales data" refers to data regarding the sales status, quantity, and revenue of a product. 【0066】 "Customer data" refers to data related to customer attributes, purchase history, and feedback. 【0067】 "Preprocessing" refers to the data cleaning and formatting processes performed to convert raw data into a format suitable for analysis. 【0068】 An "analyzable format" is a structured data format necessary for machine learning and data analysis. 【0069】 "Evaluating and forecasting revenue" is the process of analyzing the current financial situation and estimating future sales and profits. 【0070】 A "business strategy" is a specific action plan that a company chooses to take in order to achieve its goals. 【0071】 An "information display device" is a device that visually displays digital data, and mainly includes monitors and tablets. 【0072】 A "generative AI model" is an artificial intelligence algorithm that learns from data to generate new information and predictions. 【0073】 To implement this system, servers, terminals, and users must work together and fulfill their respective roles. The purpose of this system is to efficiently collect and analyze management data from each location and provide optimized management strategies. 【0074】 The server acquires communication data, sales data, and customer data from each location in real time. This is done using a dedicated data collection module, securely transferring data over communication networks such as the internet. The data is preprocessed using data processing libraries such as Python's Pandas and NumPy. This process involves imputing missing values ​​and correcting outliers, formatting the data into a parseable format. 【0075】 Next, the server analyzes the preprocessed data using a generative AI model. Machine learning libraries such as TENSORFLOW® and PyTorch are used for the AI ​​analysis. These tools are leveraged to predict future revenues, taking into account historical data and market trends. Based on the prediction results, a business strategy is generated. 【0076】 The terminal displays the generated business strategy through a user interface. Staff can visually confirm the strategic information displayed on the terminal and immediately take concrete actions based on the strategy. For example, instructions on how to implement a promotional campaign or how to optimize inventory management are displayed graphically. 【0077】 Store staff, acting as users, implement the suggested strategies using the terminals. For example, when promoting a new product, they can plan and implement promotions tailored to target customers. The results after implementation are sent back to the server via the terminals and used for future analysis. 【0078】 For example, if a store wants to promote the sale of a new product, the server analyzes past data and market trends to develop an effective promotional strategy tailored to the target audience. By inputting a prompt such as, "Analyze and propose the optimal promotional strategy for the store's new product sales," into the AI ​​model, the model derives an appropriate strategy. This allows companies to respond quickly and maximize their profits. 【0079】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0080】 Step 1: 【0081】 The server collects communication data, sales data, and customer data from each location in real time. 【0082】 The input consists of raw data sent from each location. The server retrieves this raw data via a dedicated API. Specifically, it queries the database, checks timestamps to ensure duplicates are removed and the data is up-to-date. The output is a dataset that has been organized for preprocessing. 【0083】 Step 2: 【0084】 The server preprocesses the collected data and converts it into an analyzable format. 【0085】 The input is the cleaned dataset obtained in Step 1. The server uses Python libraries such as Pandas and NumPy to impute missing values ​​and correct outliers. Specifically, it performs data cleansing and converts data types as needed. The output is a clean dataset suitable for analysis. 【0086】 Step 3: 【0087】 The server uses pre-processed data to perform detailed data analysis with an AI agent. 【0088】 The input is the clean dataset generated in Step 2. The server applies the generated AI model and leverages libraries such as TensorFlow and PyTorch to predict future revenue. Specifically, it performs trend analysis while evaluating the model's prediction accuracy. The output is the revenue forecast and insights based on that data. 【0089】 Step 4: 【0090】 The server generates the optimal business strategy based on the data analysis results. 【0091】 The input is the revenue forecast and insights created in Step 3. The server uses a rule-based engine to develop a concrete action plan. Specifically, it determines the prioritization of strategies and customizes them for each store. The output is a document outlining the specific business strategy. 【0092】 Step 5: 【0093】 The terminal visualizes the business strategy delivered from the server for store staff. 【0094】 The input is the business strategy document generated in Step 4. The terminal displays the information clearly through a user interface. Specifically, it visualizes data using graphs and charts and presents tasks in a list format. The output is information presented in a format that staff can understand and implement. 【0095】 Step 6: 【0096】 The store staff, who are the users, use the terminal to implement the suggested strategies. 【0097】 The input is the visualization information of the business strategy provided in Step 5. The user then carries out store operation improvement activities accordingly. Specific actions include implementing promotional campaigns, making proposals to new customers, and optimizing inventory management. The output is the results of the activities carried out. 【0098】 Step 7: 【0099】 The terminal records the results of the experiment and transfers them to the server. 【0100】 The input is the activity results obtained in step 6. The terminal formats the results and sends them to the server. Specifically, it extracts important indicators from the result data and aggregates them in digital format. The output is a database record for use in subsequent analyses. 【0101】 (Application Example 1) 【0102】 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." 【0103】 In store management, it is crucial to quickly and accurately formulate optimal business strategies to maximize profits. However, with conventional systems, data collection and analysis are time-consuming, and it is difficult to effectively manage the implementation status of strategies. This has led to delays in the formulation and execution of effective strategies, resulting in decreased operational efficiency. 【0104】 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. 【0105】 In this invention, the server includes means for collecting communication information, sales information, and user information; means for pre-processing the information and converting it into an analyzable format; and means for generating business strategies based on evaluation and prediction results. This enables real-time collection and analysis of various business data, rapid generation and visual presentation of optimal business strategies, and efficient management of the progress of strategy implementation. 【0106】 "Communication information" refers to data exchanged through digital networks and includes various types of information related to communication between stores and customers. 【0107】 "Sales information" refers to data related to the sale of goods and services, including sales figures, sales amounts, and customer purchase history. 【0108】 "User information" refers to various data about a store's customers, including personal attributes, behavioral history, and feedback. 【0109】 "Preprocessing" refers to the process of organizing and shaping data so that data analysis can be performed efficiently, and includes processes such as imputing missing values ​​and normalizing data. 【0110】 "Business strategy" refers to a specific action plan formulated by a company to maximize its profits, and includes sales promotion activities, securing new contracts, and streamlining inventory management. 【0111】 "Visual presentation" refers to a method of displaying information in a graphical format so that users can understand it intuitively. 【0112】 "Strategy implementation progress" is an evaluation indicator used to monitor the status of the implementation of formulated business strategies and to confirm whether they are progressing according to plan. 【0113】 In this invention, the server is responsible for collecting communication information, sales information, and user information in real time. Because the collected data is large in volume and diverse, efficient processing is required. The server preprocesses this data and converts it into an analyzable format. This preprocessing includes tasks such as imputing missing values ​​and normalizing the data. 【0114】 Pre-processed data is analyzed using a generative AI model running on the server. The purpose of this analysis is to comprehensively evaluate the current revenue situation and predict future revenue. The server considers historical data and market trends to generate the optimal business strategy. The generated strategy is then delivered to information terminals. 【0115】 The terminal visually presents the distributed business strategy to store staff. This allows staff to easily understand the strategy and implement it quickly. The terminal also provides an interface for managing the progress of strategy implementation and checking its achievement status. 【0116】 Store staff, as users, implement sales promotion activities, propose new contracts, and improve inventory management based on strategies displayed on their terminals. The results are recorded on the terminals and sent back to the server. The server uses these results for analysis in subsequent operations. 【0117】 As a concrete example, when a store introduces a new product, an AI model generates a sales promotion strategy. For instance, it might analyze weekend sales patterns and suggest running a campaign on Friday featuring a specific product. This suggestion is obtained by inputting a prompt message into the AI ​​model such as, "Based on the following sales data and feedback, please suggest the optimal sales strategy for the new product: Sales data: ..., Feedback: ...". 【0118】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0119】 Step 1: 【0120】 The server collects communication information, sales information, and user information from stores in real time. This data is obtained via the network, and the input of the collected data includes many types and formats. The output is stored as raw information for use in the next processing step. Specifically, it performs operations such as retrieving data using APIs and storing it in a database. 【0121】 Step 2: 【0122】 The server preprocesses the collected data and converts it into an analyzable format. The input is the various data collected in step 1, and the output is data with missing values ​​imputed and normalized as necessary. Specifically, it uses data cleaning techniques to correct outliers and filter the data, shaping it into a form that can be easily handled by machine learning models. 【0123】 Step 3: 【0124】 The server receives pre-processed data and analyzes it in detail using a generative AI model. The input is the data pre-processed in step 2, and the output includes revenue forecasts and the optimal business strategies for achieving them. Specifically, it uses machine learning frameworks such as Keras and TensorFlow to process the data through the model and generate prediction results. 【0125】 Step 4: 【0126】 The server distributes the generated business strategy to the information terminal. The input is the business strategy data generated in step 3, and the output is the strategy information received by the terminal. Specifically, it uses a notification API to send the strategy data to the terminal. 【0127】 Step 5: 【0128】 The terminal visually displays business strategies delivered from the server to store staff. The input is strategy data sent from the server, and the output is a clear presentation of the strategy through a visual user interface. Specifically, it uses a UI framework to display the strategy in graph and chart format. 【0129】 Step 6: 【0130】 The store staff, acting as users, perform specific tasks based on the strategy displayed on the terminal and record the results on the terminal. The input is the strategy content displayed on the terminal, and the output is data related to the results of the strategy's implementation. Specifically, they execute sales promotion measures according to the strategy and input the results into the application. 【0131】 Step 7: 【0132】 The terminal returns the results of the strategy's implementation to the server, providing data for use in subsequent analyses. The input is the implementation result data recorded by the user, and the output is the information sent to the server. Specifically, it uses a data transmission protocol to upload the result data to the server. 【0133】 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. 【0134】 This invention is a system that collects communication data, sales data, and customer data, and uses them to formulate business strategies to improve profitability. Furthermore, this system incorporates an emotion engine that recognizes user emotions and has the function of adjusting strategies while taking the user's emotional state into consideration. 【0135】 The server collects customer data in real time from customer-employee interactions at each store. This data includes customer tone of voice, changes in facial expressions, and the content of text chats. The data collected by the server is pre-processed and converted into a format that can be analyzed. 【0136】 The emotion engine uses voice analysis, facial expression analysis, and text analysis to identify customer emotions. For example, it can determine whether a customer is excited or calm from their voice tone, and facial expression recognition technology can read their smile or surprised expression. 【0137】 The server combines the acquired emotion recognition data with other collected data, evaluates revenue performance via an AI agent, and predicts future revenue. This means that newly recognized customer emotions directly influence the formulation of business strategies. Through this process, the server generates highly personalized strategies based on customer feedback. 【0138】 The terminal displays strategies delivered from the server to store staff. These visualized strategies include suggestions that take user emotions into consideration, assisting staff in providing responses and services that match customer emotions. The terminal collects the results after the strategy has been implemented and returns them to the server. 【0139】 Store staff, acting as users, take action based on the provided strategies and improve the accuracy of emotional data through interactions with customers. For example, involving staff specially trained to respond calmly to agitated customers can improve customer satisfaction. After implementing the strategy, users provide feedback on the implementation details and results via a terminal, which can then be used to improve the system for future use. 【0140】 This system achieves a higher level of revenue improvement than conventional data analysis by integrating customer data and sentiment data. 【0141】 The following describes the processing flow. 【0142】 Step 1: 【0143】 The server collects communication data, sales data, and customer data generated at each store in real time. The collection process is carried out through an automated network system, and the data is securely stored in a central database. 【0144】 Step 2: 【0145】 The server transfers data such as voice, facial expressions, and text obtained from customer interactions to the emotion engine. This emotion engine analyzes the user's emotional state and identifies emotions such as excitement, anxiety, and satisfaction. 【0146】 Step 3: 【0147】 The server combines the sentiment analysis results obtained from the sentiment engine with other collected data (communication, sales, and customer data) and passes it to the AI ​​agent. This AI agent uses a machine learning model to evaluate revenue and make future predictions. 【0148】 Step 4: 【0149】 The server generates an optimal business strategy that reflects emotional data based on the analysis results from the AI ​​agent. This strategy includes sales promotion activities and service improvements that respond to customer emotions. 【0150】 Step 5: 【0151】 The server delivers the generated business strategy to terminals in the stores. The terminals visualize the strategy in a format that is easy for staff to understand, and present the implementation steps and goals. 【0152】 Step 6: 【0153】 The terminal displays specific actions for customer service to store staff, who are the users of the device, and supports the provision of service that is appropriate to the customer's emotions. This allows staff to respond flexibly to customers' feelings. 【0154】 Step 7: 【0155】 Store staff, who are users of the system, put the strategies provided through the terminal into action. For example, they might engage in conversations that alleviate customer anxiety or offer special services to improve customer satisfaction. 【0156】 Step 8: 【0157】 The terminal then sends user feedback information back to the server. The server analyzes the received results and evaluates the effectiveness of the business strategy. This improves the accuracy of the strategy and customer service skills for future interactions. 【0158】 (Example 2) 【0159】 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 as the "terminal". 【0160】 Traditional business strategy systems often failed to adequately consider customer emotional states, resulting in inefficient revenue evaluation and forecasting. This made it difficult to effectively improve customer satisfaction without maximizing business profitability. Furthermore, the lack of rapid and accurate feedback on the effectiveness of implemented strategies hindered continuous improvement. 【0161】 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. 【0162】 In this invention, the server includes means for collecting communication data, sales data, and customer data; means for analyzing pre-processed data and sentiment data; and means for generating and delivering personalized business strategies. This enables the development of business strategies that take customer sentiment into consideration and optimize revenue, as well as rapid feedback on their effectiveness. 【0163】 "Communication data" refers to all information sent and received over a network, including emails, messages, and call logs. 【0164】 "Sales data" refers to information related to the transactions of goods and services, and includes sales figures, sales volume, customer attributes, etc. 【0165】 "Customer data" refers to information about a specific customer, including their profile, purchase history, and inquiry history. 【0166】 "Preprocessing" refers to the preparation process for converting collected data into an analyzable format, which involves organizing, filtering, and structuring the data. 【0167】 "Emotional data" refers to information about a customer's emotional state, extracted from sources such as voice, facial expressions, and text. 【0168】 A "business strategy" refers to a plan or set of measures designed to achieve specific goals, aiming to improve revenue and customer satisfaction. 【0169】 An "information terminal" refers to a device used to receive and display data and instructions from a server, and includes tablets and personal computers. 【0170】 A "machine learning algorithm" refers to a computer program that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0171】 A "generative model" refers to an algorithm that generates output based on input information, and is used for natural language generation and image generation. 【0172】 A "prompt statement" refers to an instruction statement that is input to a generative model to elicit some kind of response. 【0173】 The system of this invention aims to improve business profitability by collecting, preprocessing, analyzing, generating strategies for, and distributing data. The specific implementation method is described below. 【0174】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. This allows for the continuous accumulation of raw data about interactions with each customer. 【0175】 The collected data is preprocessed by the server. Specifically, this includes filtering to reduce noise, structuring facial expression data using face recognition, and formatting text data using natural language processing. This preprocessing converts the data into a format that can be analyzed. 【0176】 An emotion engine embedded in the server analyzes pre-processed data to identify the customer's emotional state. In this process, the emotion engine uses voice analysis, facial expression analysis, and text analysis to extract emotions from each type of data. 【0177】 In strategy generation, the server uses AI agents based on collected and analyzed data to formulate individual business strategies. This involves applying machine learning algorithms to evaluate and predict profitability, and then generating strategies based on the results. An example of a prompt for the generated AI model is, "Based on recent customer interaction data, please tell me what customized products should be suggested on the next visit." 【0178】 The terminal visually delivers strategies generated from the server to store staff. Specifically, it displays strategies using tablet devices or displays and provides visual feedback to enable staff to understand them intuitively. 【0179】 Store staff, who are users of the system, interact with customers based on the provided strategy. Because the strategy includes suggestions that take into account the customer's emotional state, staff can provide optimal service and responses. This improves customer satisfaction and increases sales. 【0180】 After the strategy is implemented, the terminal collects the results and returns them to the server. This allows the server to evaluate the strategy's effectiveness and receive feedback for future strategy development. This process allows the system to continuously improve and create more accurate strategies. 【0181】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0182】 Step 1: 【0183】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. Inputs for this data include movement and sound within the store, and output is customer interaction data. This data includes recordings of voice calls, text chat logs, and video data obtained through facial recognition. 【0184】 Step 2: 【0185】 The server preprocesses the collected interaction data. This process involves filtering out noisy audio data, performing facial recognition on video data, and structuring text data. The input is raw data, and the output is data in an analyzable format. This process improves the accuracy of the data and transforms it to be suitable for the next analysis step. 【0186】 Step 3: 【0187】 The emotion engine identifies customer emotions from pre-processed data. It analyzes voice tone using voice analysis, detects smiles and surprised expressions using facial expression analysis, and extracts emotional keywords through text analysis. The input data is the output of step 2 and is output as emotion data. This process provides concrete data on the customer's psychological state. 【0188】 Step 4: 【0189】 The server integrates sentiment data and other collected data, and uses an AI agent to evaluate and predict profitability. Inputs include sentiment data, communication data, and sales data, and the output generates predicted future revenue scenarios. Here, machine learning algorithms are applied to analyze data correlations and make sales predictions. 【0190】 Step 5: 【0191】 The server generates personalized business strategies based on evaluation and prediction results. This generation process uses data obtained in the previous step as input and outputs specific sales plans and service proposals for customers. A generation AI model is used here, taking prompts as input to generate specific suggestions. For example, a prompt might be, "Please tell me what customized products you should suggest on my next visit." 【0192】 Step 6: 【0193】 The terminal receives business strategies generated from the server and displays them visually to store staff. The input is strategic data, and the output is visualized information displayed on a tablet or screen. Store staff can then view this information and take specific actions based on the strategy. 【0194】 Step 7: 【0195】 Store staff, acting as users, interact with customers based on the presented strategy and obtain results from its implementation. The input is the displayed business strategy, and the output is customer feedback and sales data. The results of actual customer interactions are used in the next feedback and improvement steps. 【0196】 Step 8: 【0197】 The terminal sends data obtained after the strategy is implemented to the server. The input is the result of customer interaction, and the output is in a data format for analysis. The server analyzes this data, evaluates the effectiveness of the strategy, and makes further improvements. 【0198】 (Application Example 2) 【0199】 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". 【0200】 In modern retail and service industries, meticulous service based on customer emotions and behavior is essential. However, many businesses lack the mechanisms to accurately capture customer emotions and provide services accordingly. As a result, services that do not meet customer expectations occur, leading to decreased customer satisfaction and reduced profits. This invention aims to solve these problems and maximize profits by enabling real-time customer service support based on customer emotions. 【0201】 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. 【0202】 In this invention, the server includes means for collecting multiple types of information, including communication information, distribution information, and customer information; means for pre-processing the information and converting it into an analyzable format; and means for recognizing customer emotions and adjusting customer service methods. This enables the provision of personalized services based on customer emotions. 【0203】 "Communication information" refers to information including data and call content exchanged over a network. 【0204】 "Distribution information" refers to information regarding the sale, inventory status, and logistics processes of goods and services. 【0205】 "Customer information" refers to information about customers' personal data, purchase history, behavioral patterns, and preferences. 【0206】 "Preprocessing" refers to the operations necessary to convert raw data into an analyzable format, such as data cleaning and format conversion. 【0207】 An "analyzable format" refers to a format in which collected data is prepared in a way that is suitable for machine learning algorithms and statistical analysis. 【0208】 "Profit" refers to the economic results or income that a company earns through its activities. 【0209】 "Business strategy" refers to the policies and plans that a company formulates to achieve its business objectives. 【0210】 "Terminal device" refers to a device used to transmit or receive information, including computers and smartphones. 【0211】 "Customer emotions" refer to the psychological state or feelings a customer experiences at a particular moment. 【0212】 "Adjustment" refers to the act of changing settings or operations to suit specific conditions or purposes. 【0213】 This invention is a system for providing personalized services based on customer emotions. Specifically, it collects communication information, distribution information, and customer information, and generates business strategies based on these. The specific configuration and method for carrying out this invention are described below. 【0214】 The server uses cameras and microphones installed in the store to collect customers' facial expressions and voices in real time. Hardware includes high-resolution cameras (e.g., Logitech Brio) and high-precision microphones (e.g., Shure MV5C). The server receives the collected data and analyzes it using machine learning techniques. In this process, it utilizes Google Cloud's machine learning APIs (e.g., Cloud Speech-to-Text API and Vision AI) to identify customer emotions. 【0215】 Once the analysis is complete, the data is sent via Firebase to the store staff's terminal devices. These terminal devices are the staff's smartphones or tablets. Based on the received sentiment data, the terminals display business strategies, including customer service methods, on the screen. This enables staff to respond appropriately to customers' emotions. 【0216】 For example, if the system analyzes that a customer walking through the store has a calm expression, it will suggest to the staff, "Recommend the new product and explain the details if they are interested." Conversely, if a customer looks unhappy, it will provide instructions such as, "Respond in a calm tone and ask if they have any problems." 【0217】 This system is expected to improve the quality of service provided to each customer, and consequently, the profitability of the stores. 【0218】 Example of a prompt: 【0219】 Please describe a system that uses generative AI to analyze customers' facial expressions and tone of voice in a store in real time, and then proposes customer service strategies based on those emotions. 【0220】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0221】 Step 1: 【0222】 The server acquires customer facial expression and audio data in real time from cameras and microphones installed in the store. The cameras capture facial features as video, and the microphones record voice tone as audio. This data is then input into the server. 【0223】 Step 2: 【0224】 The server preprocesses the acquired video data using image processing software. This enhances facial features and removes noise. The preprocessed data is then used as input for analyzing the customer's facial expressions. 【0225】 Step 3: 【0226】 The server utilizes Google Cloud's Vision AI to analyze customer facial expressions from pre-processed video data. This allows it to output specific emotional states, such as whether the customer is angry or happy. 【0227】 Step 4: 【0228】 Meanwhile, the server converts the acquired audio data into text data using Google Cloud's Speech-to-Text API. This conversion analyzes the tone of voice and outputs it as additional information for recognizing emotions. 【0229】 Step 5: 【0230】 The server integrates emotion data from Vision AI and speech tone data from Speech-to-Text to evaluate overall customer sentiment. Based on this evaluation, a generative AI model is used to determine the appropriate customer service approach and generate a customer service strategy. 【0231】 Step 6: 【0232】 The generated customer service strategy is sent to the device via Firebase. The device receives this information and visually presents the strategy to the store staff. Based on the instructions displayed on the screen, the staff begins to provide appropriate service to the customer. 【0233】 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. 【0234】 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. 【0235】 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. 【0236】 [Second Embodiment] 【0237】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0238】 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. 【0239】 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). 【0240】 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. 【0241】 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. 【0242】 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). 【0243】 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. 【0244】 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. 【0245】 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. 【0246】 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. 【0247】 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. 【0248】 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". 【0249】 This system collects management data from each store, analyzes that data using an AI agent, and proposes the optimal revenue improvement strategy. To realize this process, the roles of the server, terminal, and user are clearly defined. 【0250】 The server first collects various data from each store in real time, such as the number of communication contracts, terminal sales, the number of optional services used, and customer feedback. Because this data is generated in large quantities at once, it is collected periodically via the network and stored centrally. 【0251】 Subsequently, before passing the collected data to the AI ​​agent, the server performs preprocessing by converting the data into a format that can be analyzed. Specifically, it imputes missing values ​​and corrects outliers, preparing the data for efficient analysis. 【0252】 Next, the server uses an AI agent to analyze the pre-processed data in detail. At this stage, it comprehensively evaluates the current revenue situation and predicts future revenue by considering historical data and market trends. Based on this analysis, the server generates specific business strategies for maximizing revenue. 【0253】 The terminals play a role in making business strategies delivered from the server visible to store staff. Each terminal has a function to display strategies in an easy-to-understand format, helping staff to quickly implement them. The terminals also have support functions that reduce the workload of staff by automating some processes. 【0254】 Store staff, as users, use the terminals to implement the provided business strategies. Specifically, they conduct promotional campaigns, propose new contracts, optimize inventory, and record the results on the terminals. The terminals then return these results to the server, which are used for analysis in subsequent operations. 【0255】 As a concrete example, if a store wants to promote a new product, the server analyzes market data related to the new product and sales data for similar products from the past, and proposes a promotional strategy tailored to the target customer segment. This strategy is notified to store staff via terminals, allowing them to quickly understand and implement it. This improves the efficiency of sales promotion activities and leads to increased profits. 【0256】 The following describes the processing flow. 【0257】 Step 1: 【0258】 The server collects data in real time from each store, including the number of communication contracts, terminal sales, optional service usage, and customer feedback. This data is automatically collected via a secure network and stored in a central database. 【0259】 Step 2: 【0260】 The server begins processing the collected raw data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. This process ensures the data is clean and suitable for AI analysis. 【0261】 Step 3: 【0262】 The server passes pre-processed data to the AI ​​agent and instructs it to perform the analysis. The AI ​​agent uses machine learning algorithms to analyze the data and evaluate the current revenue situation. It also predicts future revenue based on historical data and market trends. 【0263】 Step 4: 【0264】 The server receives the analysis results from the AI ​​agent and generates an optimal business strategy based on them. This strategy includes acquiring new contracts, sales promotion activities, and streamlining inventory management. 【0265】 Step 5: 【0266】 The server distributes the generated business strategies to the terminals in the stores. This distribution is customized to suit the characteristics and circumstances of each store. 【0267】 Step 6: 【0268】 The terminal visually presents business strategies received from the server to store staff. It clearly displays strategy details, implementation steps, and expected effects, helping staff act quickly and accurately. 【0269】 Step 7: 【0270】 Store staff, acting as users, execute business strategies instructed on their terminals. For example, they might launch a new sales promotion, adjust inventory, or engage in customer outreach activities. Users input the results of their strategy execution into the terminal, which is then sent to the server for further analysis. 【0271】 Step 8: 【0272】 The server analyzes the results from user execution and evaluates the effectiveness of the strategy. Based on this evaluation, the AI ​​agent's algorithm is adjusted to help generate the next strategy. This feedback loop continuously improves the accuracy and effectiveness of the entire system. 【0273】 (Example 1) 【0274】 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." 【0275】 For many companies, effectively formulating business strategies based on diverse data is a crucial challenge. In particular, there is a need to collect large amounts of data in real time, analyze it quickly and accurately to predict future profits, and then develop and implement concrete and actionable business strategies based on those results. However, traditional methods have suffered from the cumbersome preprocessing and analysis of individual data points, resulting in insufficient correlation with actual profit improvement. 【0276】 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. 【0277】 In this invention, the server includes means for acquiring a plurality of types of information including communication data, sales data, and customer data from each base, means for preprocessing the acquired information and converting it into a format suitable for analysis, and means for evaluating revenue and predicting future revenue based on the information converted into the format. As a result, it becomes possible to efficiently utilize multi-faceted data to generate business strategies and continuously improve revenue through the execution and evaluation thereof. 【0278】 "Communication data" refers to data related to the usage status and contract information of communication services. 【0279】 "Sales data" refers to data related to the sales status, quantity, and sales of products. 【0280】 "Customer data" refers to data related to customer attribute information, purchase history, and feedback. 【0281】 "Preprocessing" is a process of data cleaning and shaping performed to convert raw data into a format suitable for analysis. 【0282】 "Analyzable format" is a structured data format required for performing machine learning and data analysis. 【0283】 "Evaluating and predicting revenue" is a process of analyzing the current financial situation and inferring future sales and profits. 【0284】 "Business strategy" is a specific action plan selected by a company to achieve its goals. 【0285】 "Information display device" is a device that visually displays digital data, mainly including monitors and tablets. 【0286】 "Generated AI model" is an artificial intelligence algorithm that learns from data to generate new information and predictions. 【0287】 To implement this system, servers, terminals, and users must work together and fulfill their respective roles. The purpose of this system is to efficiently collect and analyze management data from each location and provide optimized management strategies. 【0288】 The server acquires communication data, sales data, and customer data from each location in real time. This is done using a dedicated data collection module, securely transferring data over communication networks such as the internet. The data is preprocessed using data processing libraries such as Python's Pandas and NumPy. This process involves imputing missing values ​​and correcting outliers, formatting the data into a parseable format. 【0289】 Next, the server analyzes the preprocessed data using a generative AI model. Machine learning libraries such as TensorFlow and PyTorch are used for the AI ​​analysis. These tools are leveraged to predict future revenues, taking into account historical data and market trends. Based on the prediction results, a business strategy is generated. 【0290】 The terminal displays the generated business strategy through a user interface. Staff can visually confirm the strategic information displayed on the terminal and immediately take concrete actions based on the strategy. For example, instructions on how to implement a promotional campaign or how to optimize inventory management are displayed graphically. 【0291】 Store staff, acting as users, implement the suggested strategies using the terminals. For example, when promoting a new product, they can plan and implement promotions tailored to target customers. The results after implementation are sent back to the server via the terminals and used for future analysis. 【0292】 For example, if a store wants to promote the sale of a new product, the server analyzes past data and market trends to develop an effective promotional strategy tailored to the target audience. By inputting a prompt such as, "Analyze and propose the optimal promotional strategy for the store's new product sales," into the AI ​​model, the model derives an appropriate strategy. This allows companies to respond quickly and maximize their profits. 【0293】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0294】 Step 1: 【0295】 The server collects communication data, sales data, and customer data from each location in real time. 【0296】 The input consists of raw data sent from each location. The server retrieves this raw data via a dedicated API. Specifically, it queries the database, checks timestamps to ensure duplicates are removed and the data is up-to-date. The output is a dataset that has been organized for preprocessing. 【0297】 Step 2: 【0298】 The server preprocesses the collected data and converts it into an analyzable format. 【0299】 The input is the cleaned dataset obtained in Step 1. The server uses Python libraries such as Pandas and NumPy to impute missing values ​​and correct outliers. Specifically, it performs data cleansing and converts data types as needed. The output is a clean dataset suitable for analysis. 【0300】 Step 3: 【0301】 The server uses pre-processed data to perform detailed data analysis with an AI agent. 【0302】 The input is the clean dataset generated in Step 2. The server applies a generative AI model and utilizes libraries such as TensorFlow and PyTorch to predict future revenues. As specific operations, trend analysis is performed while evaluating the prediction accuracy of the model. The output is the revenue prediction and insights based on that data. 【0303】 Step 4: 【0304】 The server generates an optimal business strategy based on the data analysis results. 【0305】 The input is the revenue prediction and insights created in Step 3. The server uses a rule - based engine to formulate a specific action plan. As specific operations, it determines the priority of the strategy and performs customization according to each store. The output is a document of the specific business strategy. 【0306】 Step 5: 【0307】 The terminal visualizes the business strategy distributed from the server to the store staff. 【0308】 The input is the document of the business strategy generated in Step 4. The terminal displays the information clearly through the user interface. As specific operations, it visualizes the data using graphs and charts and presents the tasks in a list format. The output is information presented in a form that the staff can understand and practice. 【0309】 Step 6: 【0310】 The store staff, who are the users, utilize the terminal to implement the proposed strategy. 【0311】 The input is the visualization information of the business strategy provided in Step 5. The user then carries out store operation improvement activities accordingly. Specific actions include implementing promotional campaigns, making proposals to new customers, and optimizing inventory management. The output is the results of the activities carried out. 【0312】 Step 7: 【0313】 The terminal records the results of the experiment and transfers them to the server. 【0314】 The input is the activity results obtained in step 6. The terminal formats the results and sends them to the server. Specifically, it extracts important indicators from the result data and aggregates them in digital format. The output is a database record for use in subsequent analyses. 【0315】 (Application Example 1) 【0316】 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." 【0317】 In store management, it is crucial to quickly and accurately formulate optimal business strategies to maximize profits. However, with conventional systems, data collection and analysis are time-consuming, and it is difficult to effectively manage the implementation status of strategies. This has led to delays in the formulation and execution of effective strategies, resulting in decreased operational efficiency. 【0318】 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. 【0319】 In this invention, the server includes means for collecting communication information, sales information, and user information; means for pre-processing the information and converting it into an analyzable format; and means for generating business strategies based on evaluation and prediction results. This enables real-time collection and analysis of various business data, rapid generation and visual presentation of optimal business strategies, and efficient management of the progress of strategy implementation. 【0320】 "Communication information" refers to data exchanged through digital networks and includes various types of information related to communication between stores and customers. 【0321】 "Sales information" refers to data related to the sale of goods and services, including sales figures, sales amounts, and customer purchase history. 【0322】 "User information" refers to various data about a store's customers, including personal attributes, behavioral history, and feedback. 【0323】 "Preprocessing" refers to the process of organizing and shaping data so that data analysis can be performed efficiently, and includes processes such as imputing missing values ​​and normalizing data. 【0324】 "Business strategy" refers to a specific action plan formulated by a company to maximize its profits, and includes sales promotion activities, securing new contracts, and streamlining inventory management. 【0325】 "Visual presentation" refers to a method of displaying information in a graphical format so that users can understand it intuitively. 【0326】 "Strategy implementation progress" is an evaluation indicator used to monitor the status of the implementation of formulated business strategies and to confirm whether they are progressing according to plan. 【0327】 In this invention, the server is responsible for collecting communication information, sales information, and user information in real time. Because the collected data is large in volume and diverse, efficient processing is required. The server preprocesses this data and converts it into an analyzable format. This preprocessing includes tasks such as imputing missing values ​​and normalizing the data. 【0328】 Pre-processed data is analyzed using a generative AI model running on the server. The purpose of this analysis is to comprehensively evaluate the current revenue situation and predict future revenue. The server considers historical data and market trends to generate the optimal business strategy. The generated strategy is then delivered to information terminals. 【0329】 The terminal visually presents the distributed business strategy to store staff. This allows staff to easily understand the strategy and implement it quickly. The terminal also provides an interface for managing the progress of strategy implementation and checking its achievement status. 【0330】 Store staff, as users, implement sales promotion activities, propose new contracts, and improve inventory management based on strategies displayed on their terminals. The results are recorded on the terminals and sent back to the server. The server uses these results for analysis in subsequent operations. 【0331】 As a concrete example, when a store introduces a new product, an AI model generates a sales promotion strategy. For instance, it might analyze weekend sales patterns and suggest running a campaign on Friday featuring a specific product. This suggestion is obtained by inputting a prompt message into the AI ​​model such as, "Based on the following sales data and feedback, please suggest the optimal sales strategy for the new product: Sales data: ..., Feedback: ...". 【0332】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0333】 Step 1: 【0334】 The server collects communication information, sales information, and user information from stores in real time. This data is obtained via the network, and the input of the collected data includes many types and formats. The output is stored as raw information for use in the next processing step. Specifically, it performs operations such as retrieving data using APIs and storing it in a database. 【0335】 Step 2: 【0336】 The server preprocesses the collected data and converts it into an analyzable format. The input is the various data collected in step 1, and the output is data with missing values ​​imputed and normalized as necessary. Specifically, it uses data cleaning techniques to correct outliers and filter the data, shaping it into a form that can be easily handled by machine learning models. 【0337】 Step 3: 【0338】 The server receives pre-processed data and analyzes it in detail using a generative AI model. The input is the data pre-processed in step 2, and the output includes revenue forecasts and the optimal business strategies for achieving them. Specifically, it uses machine learning frameworks such as Keras and TensorFlow to process the data through the model and generate prediction results. 【0339】 Step 4: 【0340】 The server distributes the generated business strategy to the information terminal. The input is the business strategy data generated in step 3, and the output is the strategy information received by the terminal. Specifically, it uses a notification API to send the strategy data to the terminal. 【0341】 Step 5: 【0342】 The terminal visually displays business strategies delivered from the server to store staff. The input is strategy data sent from the server, and the output is a clear presentation of the strategy through a visual user interface. Specifically, it uses a UI framework to display the strategy in graph and chart format. 【0343】 Step 6: 【0344】 The store staff, acting as users, perform specific tasks based on the strategy displayed on the terminal and record the results on the terminal. The input is the strategy content displayed on the terminal, and the output is data related to the results of the strategy's implementation. Specifically, they execute sales promotion measures according to the strategy and input the results into the application. 【0345】 Step 7: 【0346】 The terminal returns the results of the strategy's implementation to the server, providing data for use in subsequent analyses. The input is the implementation result data recorded by the user, and the output is the information sent to the server. Specifically, it uses a data transmission protocol to upload the result data to the server. 【0347】 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. 【0348】 This invention is a system that collects communication data, sales data, and customer data, and uses them to formulate business strategies to improve profitability. Furthermore, this system incorporates an emotion engine that recognizes user emotions and has the function of adjusting strategies while taking the user's emotional state into consideration. 【0349】 The server collects customer data in real time from customer-employee interactions at each store. This data includes customer tone of voice, changes in facial expressions, and the content of text chats. The data collected by the server is pre-processed and converted into a format that can be analyzed. 【0350】 The emotion engine uses voice analysis, facial expression analysis, and text analysis to identify customer emotions. For example, it can determine whether a customer is excited or calm from their voice tone, and facial expression recognition technology can read their smile or surprised expression. 【0351】 The server combines the acquired emotion recognition data with other collected data, evaluates revenue performance via an AI agent, and predicts future revenue. This means that newly recognized customer emotions directly influence the formulation of business strategies. Through this process, the server generates highly personalized strategies based on customer feedback. 【0352】 The terminal displays strategies delivered from the server to store staff. These visualized strategies include suggestions that take user emotions into consideration, assisting staff in providing responses and services that match customer emotions. The terminal collects the results after the strategy has been implemented and returns them to the server. 【0353】 Store staff, acting as users, take action based on the provided strategies and improve the accuracy of emotional data through interactions with customers. For example, involving staff specially trained to respond calmly to agitated customers can improve customer satisfaction. After implementing the strategy, users provide feedback on the implementation details and results via a terminal, which can then be used to improve the system for future use. 【0354】 This system achieves a higher level of revenue improvement than conventional data analysis by integrating customer data and sentiment data. 【0355】 The following describes the processing flow. 【0356】 Step 1: 【0357】 The server collects communication data, sales data, and customer data generated at each store in real time. The collection process is carried out through an automated network system, and the data is securely stored in a central database. 【0358】 Step 2: 【0359】 The server transfers data such as voice, facial expressions, and text obtained from customer interactions to the emotion engine. This emotion engine analyzes the user's emotional state and identifies emotions such as excitement, anxiety, and satisfaction. 【0360】 Step 3: 【0361】 The server combines the sentiment analysis results obtained from the sentiment engine with other collected data (communication, sales, and customer data) and passes it to the AI ​​agent. This AI agent uses a machine learning model to evaluate revenue and make future predictions. 【0362】 Step 4: 【0363】 The server generates an optimal business strategy that reflects emotional data based on the analysis results from the AI ​​agent. This strategy includes sales promotion activities and service improvements that respond to customer emotions. 【0364】 Step 5: 【0365】 The server delivers the generated business strategy to terminals in the stores. The terminals visualize the strategy in a format that is easy for staff to understand, and present the implementation steps and goals. 【0366】 Step 6: 【0367】 The terminal displays specific actions for customer service to store staff, who are the users of the device, and supports the provision of service that is appropriate to the customer's emotions. This allows staff to respond flexibly to customers' feelings. 【0368】 Step 7: 【0369】 Store staff, who are users of the system, put the strategies provided through the terminal into action. For example, they might engage in conversations that alleviate customer anxiety or offer special services to improve customer satisfaction. 【0370】 Step 8: 【0371】 The terminal then sends user feedback information back to the server. The server analyzes the received results and evaluates the effectiveness of the business strategy. This improves the accuracy of the strategy and customer service skills for future interactions. 【0372】 (Example 2) 【0373】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0374】 Traditional business strategy systems often failed to adequately consider customer emotional states, resulting in inefficient revenue evaluation and forecasting. This made it difficult to effectively improve customer satisfaction without maximizing business profitability. Furthermore, the lack of rapid and accurate feedback on the effectiveness of implemented strategies hindered continuous improvement. 【0375】 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. 【0376】 In this invention, the server includes means for collecting communication data, sales data, and customer data; means for analyzing pre-processed data and sentiment data; and means for generating and delivering personalized business strategies. This enables the development of business strategies that take customer sentiment into consideration and optimize revenue, as well as rapid feedback on their effectiveness. 【0377】 "Communication data" refers to all information sent and received over a network, including emails, messages, and call logs. 【0378】 "Sales data" refers to information related to the transactions of goods and services, and includes sales figures, sales volume, customer attributes, etc. 【0379】 "Customer data" refers to information about a specific customer, including their profile, purchase history, and inquiry history. 【0380】 "Preprocessing" refers to the preparation process for converting collected data into an analyzable format, which involves organizing, filtering, and structuring the data. 【0381】 "Emotional data" refers to information about a customer's emotional state, extracted from sources such as voice, facial expressions, and text. 【0382】 A "business strategy" refers to a plan or set of measures designed to achieve specific goals, aiming to improve revenue and customer satisfaction. 【0383】 An "information terminal" refers to a device used to receive and display data and instructions from a server, and includes tablets and personal computers. 【0384】 A "machine learning algorithm" refers to a computer program that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0385】 A "generative model" refers to an algorithm that generates output based on input information, and is used for natural language generation and image generation. 【0386】 A "prompt statement" refers to an instruction statement that is input to a generative model to elicit some kind of response. 【0387】 The system of this invention aims to improve business profitability by collecting, preprocessing, analyzing, generating strategies for, and distributing data. The specific implementation method is described below. 【0388】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. This allows for the continuous accumulation of raw data about interactions with each customer. 【0389】 The collected data is preprocessed by the server. Specifically, this includes filtering to reduce noise, structuring facial expression data using face recognition, and formatting text data using natural language processing. This preprocessing converts the data into a format that can be analyzed. 【0390】 An emotion engine embedded in the server analyzes pre-processed data to identify the customer's emotional state. In this process, the emotion engine uses voice analysis, facial expression analysis, and text analysis to extract emotions from each type of data. 【0391】 In strategy generation, the server uses AI agents based on collected and analyzed data to formulate individual business strategies. This involves applying machine learning algorithms to evaluate and predict profitability, and then generating strategies based on the results. An example of a prompt for the generated AI model is, "Based on recent customer interaction data, please tell me what customized products should be suggested on the next visit." 【0392】 The terminal visually delivers strategies generated from the server to store staff. Specifically, it displays strategies using tablet devices or displays and provides visual feedback to enable staff to understand them intuitively. 【0393】 Store staff, who are users of the system, interact with customers based on the provided strategy. Because the strategy includes suggestions that take into account the customer's emotional state, staff can provide optimal service and responses. This improves customer satisfaction and increases sales. 【0394】 After the strategy is implemented, the terminal collects the results and returns them to the server. This allows the server to evaluate the strategy's effectiveness and receive feedback for future strategy development. This process allows the system to continuously improve and create more accurate strategies. 【0395】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0396】 Step 1: 【0397】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. Inputs for this data include movement and sound within the store, and output is customer interaction data. This data includes recordings of voice calls, text chat logs, and video data obtained through facial recognition. 【0398】 Step 2: 【0399】 The server preprocesses the collected interaction data. This process involves filtering out noisy audio data, performing facial recognition on video data, and structuring text data. The input is raw data, and the output is data in an analyzable format. This process improves the accuracy of the data and transforms it to be suitable for the next analysis step. 【0400】 Step 3: 【0401】 The emotion engine identifies customer emotions from pre-processed data. It analyzes voice tone using voice analysis, detects smiles and surprised expressions using facial expression analysis, and extracts emotional keywords through text analysis. The input data is the output of step 2 and is output as emotion data. This process provides concrete data on the customer's psychological state. 【0402】 Step 4: 【0403】 The server integrates sentiment data and other collected data, and uses an AI agent to evaluate and predict profitability. Inputs include sentiment data, communication data, and sales data, and the output generates predicted future revenue scenarios. Here, machine learning algorithms are applied to analyze data correlations and make sales predictions. 【0404】 Step 5: 【0405】 The server generates personalized business strategies based on evaluation and prediction results. This generation process uses data obtained in the previous step as input and outputs specific sales plans and service proposals for customers. A generation AI model is used here, taking prompts as input to generate specific suggestions. For example, a prompt might be, "Please tell me what customized products you should suggest on my next visit." 【0406】 Step 6: 【0407】 The terminal receives business strategies generated from the server and displays them visually to store staff. The input is strategic data, and the output is visualized information displayed on a tablet or screen. Store staff can then view this information and take specific actions based on the strategy. 【0408】 Step 7: 【0409】 Store staff, acting as users, interact with customers based on the presented strategy and obtain results from its implementation. The input is the displayed business strategy, and the output is customer feedback and sales data. The results of actual customer interactions are used in the next feedback and improvement steps. 【0410】 Step 8: 【0411】 The terminal sends data obtained after the strategy is implemented to the server. The input is the result of customer interaction, and the output is in a data format for analysis. The server analyzes this data, evaluates the effectiveness of the strategy, and makes further improvements. 【0412】 (Application Example 2) 【0413】 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." 【0414】 In modern retail and service industries, meticulous service based on customer emotions and behavior is essential. However, many businesses lack the mechanisms to accurately capture customer emotions and provide services accordingly. As a result, services that do not meet customer expectations occur, leading to decreased customer satisfaction and reduced profits. This invention aims to solve these problems and maximize profits by enabling real-time customer service support based on customer emotions. 【0415】 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. 【0416】 In this invention, the server includes means for collecting multiple types of information, including communication information, distribution information, and customer information; means for pre-processing the information and converting it into an analyzable format; and means for recognizing customer emotions and adjusting customer service methods. This enables the provision of personalized services based on customer emotions. 【0417】 "Communication information" refers to information including data and call content exchanged over a network. 【0418】 "Distribution information" refers to information regarding the sale, inventory status, and logistics processes of goods and services. 【0419】 "Customer information" refers to information about customers' personal data, purchase history, behavioral patterns, and preferences. 【0420】 "Preprocessing" refers to the operations necessary to convert raw data into an analyzable format, such as data cleaning and format conversion. 【0421】 An "analyzable format" refers to a format in which collected data is prepared in a way that is suitable for machine learning algorithms and statistical analysis. 【0422】 "Profit" refers to the economic results or income that a company earns through its activities. 【0423】 "Business strategy" refers to the policies and plans that a company formulates to achieve its business objectives. 【0424】 "Terminal device" refers to a device used to transmit or receive information, including computers and smartphones. 【0425】 "Customer emotions" refer to the psychological state or feelings a customer experiences at a particular moment. 【0426】 "Adjustment" refers to the act of changing settings or operations to suit specific conditions or purposes. 【0427】 This invention is a system for providing personalized services based on customer emotions. Specifically, it collects communication information, distribution information, and customer information, and generates business strategies based on these. The specific configuration and method for carrying out this invention are described below. 【0428】 The server uses cameras and microphones installed in the store to collect customers' facial expressions and voices in real time. Hardware includes high-resolution cameras (e.g., Logitech Brio) and high-precision microphones (e.g., Shure MV5C). The server receives the collected data and analyzes it using machine learning techniques. In this process, it utilizes Google Cloud's machine learning APIs (e.g., Cloud Speech-to-Text API and Vision AI) to identify customer emotions. 【0429】 Once the analysis is complete, the data is sent via Firebase to the store staff's terminal devices. These terminal devices are the staff's smartphones or tablets. Based on the received sentiment data, the terminals display business strategies, including customer service methods, on the screen. This enables staff to respond appropriately to customers' emotions. 【0430】 For example, if the system analyzes that a customer walking through the store has a calm expression, it will suggest to the staff, "Recommend the new product and explain the details if they are interested." Conversely, if a customer looks unhappy, it will provide instructions such as, "Respond in a calm tone and ask if they have any problems." 【0431】 This system is expected to improve the quality of service provided to each customer, and consequently, the profitability of the stores. 【0432】 Example of a prompt: 【0433】 Please describe a system that uses generative AI to analyze customers' facial expressions and tone of voice in a store in real time, and then proposes customer service strategies based on those emotions. 【0434】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0435】 Step 1: 【0436】 The server acquires customer facial expression and audio data in real time from cameras and microphones installed in the store. The cameras capture facial features as video, and the microphones record voice tone as audio. This data is then input into the server. 【0437】 Step 2: 【0438】 The server preprocesses the acquired video data using image processing software. This enhances facial features and removes noise. The preprocessed data is then used as input for analyzing the customer's facial expressions. 【0439】 Step 3: 【0440】 The server utilizes Google Cloud's Vision AI to analyze customer facial expressions from pre-processed video data. This allows it to output specific emotional states, such as whether the customer is angry or happy. 【0441】 Step 4: 【0442】 Meanwhile, the server converts the acquired audio data into text data using Google Cloud's Speech-to-Text API. This conversion analyzes the tone of voice and outputs it as additional information for recognizing emotions. 【0443】 Step 5: 【0444】 The server integrates emotion data from Vision AI and speech tone data from Speech-to-Text to evaluate overall customer sentiment. Based on this evaluation, a generative AI model is used to determine the appropriate customer service approach and generate a customer service strategy. 【0445】 Step 6: 【0446】 The generated customer service strategy is sent to the device via Firebase. The device receives this information and visually presents the strategy to the store staff. Based on the instructions displayed on the screen, the staff begins to provide appropriate service to the customer. 【0447】 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. 【0448】 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. 【0449】 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. 【0450】 [Third Embodiment] 【0451】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0452】 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. 【0453】 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). 【0454】 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. 【0455】 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. 【0456】 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). 【0457】 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. 【0458】 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. 【0459】 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. 【0460】 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. 【0461】 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. 【0462】 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". 【0463】 This system collects management data from each store, analyzes that data using an AI agent, and proposes the optimal revenue improvement strategy. To realize this process, the roles of the server, terminal, and user are clearly defined. 【0464】 The server first collects various data from each store in real time, such as the number of communication contracts, terminal sales, the number of optional services used, and customer feedback. Because this data is generated in large quantities at once, it is collected periodically via the network and stored centrally. 【0465】 Subsequently, before passing the collected data to the AI ​​agent, the server performs preprocessing by converting the data into a format that can be analyzed. Specifically, it imputes missing values ​​and corrects outliers, preparing the data for efficient analysis. 【0466】 Next, the server uses an AI agent to analyze the pre-processed data in detail. At this stage, it comprehensively evaluates the current revenue situation and predicts future revenue by considering historical data and market trends. Based on this analysis, the server generates specific business strategies for maximizing revenue. 【0467】 The terminals play a role in making business strategies delivered from the server visible to store staff. Each terminal has a function to display strategies in an easy-to-understand format, helping staff to quickly implement them. The terminals also have support functions that reduce the workload of staff by automating some processes. 【0468】 Store staff, as users, use the terminals to implement the provided business strategies. Specifically, they conduct promotional campaigns, propose new contracts, optimize inventory, and record the results on the terminals. The terminals then return these results to the server, which are used for analysis in subsequent operations. 【0469】 As a concrete example, if a store wants to promote a new product, the server analyzes market data related to the new product and sales data for similar products from the past, and proposes a promotional strategy tailored to the target customer segment. This strategy is notified to store staff via terminals, allowing them to quickly understand and implement it. This improves the efficiency of sales promotion activities and leads to increased profits. 【0470】 The following describes the processing flow. 【0471】 Step 1: 【0472】 The server collects data in real time from each store, including the number of communication contracts, terminal sales, optional service usage, and customer feedback. This data is automatically collected via a secure network and stored in a central database. 【0473】 Step 2: 【0474】 The server begins processing the collected raw data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. This process ensures the data is clean and suitable for AI analysis. 【0475】 Step 3: 【0476】 The server passes pre-processed data to the AI ​​agent and instructs it to perform the analysis. The AI ​​agent uses machine learning algorithms to analyze the data and evaluate the current revenue situation. It also predicts future revenue based on historical data and market trends. 【0477】 Step 4: 【0478】 The server receives the analysis results from the AI ​​agent and generates an optimal business strategy based on them. This strategy includes acquiring new contracts, sales promotion activities, and streamlining inventory management. 【0479】 Step 5: 【0480】 The server distributes the generated business strategies to the terminals in the stores. This distribution is customized to suit the characteristics and circumstances of each store. 【0481】 Step 6: 【0482】 The terminal visually presents business strategies received from the server to store staff. It clearly displays strategy details, implementation steps, and expected effects, helping staff act quickly and accurately. 【0483】 Step 7: 【0484】 Store staff, acting as users, execute business strategies instructed on their terminals. For example, they might launch a new sales promotion, adjust inventory, or engage in customer outreach activities. Users input the results of their strategy execution into the terminal, which is then sent to the server for further analysis. 【0485】 Step 8: 【0486】 The server analyzes the results from user execution and evaluates the effectiveness of the strategy. Based on this evaluation, the AI ​​agent's algorithm is adjusted to help generate the next strategy. This feedback loop continuously improves the accuracy and effectiveness of the entire system. 【0487】 (Example 1) 【0488】 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." 【0489】 For many companies, effectively formulating business strategies based on diverse data is a crucial challenge. In particular, there is a need to collect large amounts of data in real time, analyze it quickly and accurately to predict future profits, and then develop and implement concrete and actionable business strategies based on those results. However, traditional methods have suffered from the cumbersome preprocessing and analysis of individual data points, resulting in insufficient correlation with actual profit improvement. 【0490】 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. 【0491】 In this invention, the server includes means for acquiring multiple types of information, including communication data, sales data, and customer data, from each location; means for preprocessing the acquired information and converting it into a format suitable for analysis; and means for evaluating revenue and predicting future revenue based on the converted information. This enables efficient use of multifaceted data to generate management strategies, and sustainable revenue improvement through their implementation and evaluation. 【0492】 "Communication data" refers to data related to the usage status and contract information of communication services. 【0493】 "Sales data" refers to data regarding the sales status, quantity, and revenue of a product. 【0494】 "Customer data" refers to data related to customer attributes, purchase history, and feedback. 【0495】 "Preprocessing" refers to the data cleaning and formatting processes performed to convert raw data into a format suitable for analysis. 【0496】 An "analyzable format" is a structured data format necessary for machine learning and data analysis. 【0497】 "Evaluating and forecasting revenue" is the process of analyzing the current financial situation and estimating future sales and profits. 【0498】 A "business strategy" is a specific action plan that a company chooses to take in order to achieve its goals. 【0499】 An "information display device" is a device that visually displays digital data, and mainly includes monitors and tablets. 【0500】 A "generative AI model" is an artificial intelligence algorithm that learns from data to generate new information and predictions. 【0501】 To implement this system, servers, terminals, and users must work together and fulfill their respective roles. The purpose of this system is to efficiently collect and analyze management data from each location and provide optimized management strategies. 【0502】 The server acquires communication data, sales data, and customer data from each location in real time. This is done using a dedicated data collection module, securely transferring data over communication networks such as the internet. The data is preprocessed using data processing libraries such as Python's Pandas and NumPy. This process involves imputing missing values ​​and correcting outliers, formatting the data into a parseable format. 【0503】 Next, the server analyzes the preprocessed data using a generative AI model. Machine learning libraries such as TensorFlow and PyTorch are used for the AI ​​analysis. These tools are leveraged to predict future revenues, taking into account historical data and market trends. Based on the prediction results, a business strategy is generated. 【0504】 The terminal displays the generated business strategy through a user interface. Staff can visually confirm the strategic information displayed on the terminal and immediately take concrete actions based on the strategy. For example, instructions on how to implement a promotional campaign or how to optimize inventory management are displayed graphically. 【0505】 Store staff, acting as users, implement the suggested strategies using the terminals. For example, when promoting a new product, they can plan and implement promotions tailored to target customers. The results after implementation are sent back to the server via the terminals and used for future analysis. 【0506】 For example, if a store wants to promote the sale of a new product, the server analyzes past data and market trends to develop an effective promotional strategy tailored to the target audience. By inputting a prompt such as, "Analyze and propose the optimal promotional strategy for the store's new product sales," into the AI ​​model, the model derives an appropriate strategy. This allows companies to respond quickly and maximize their profits. 【0507】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0508】 Step 1: 【0509】 The server collects communication data, sales data, and customer data from each location in real time. 【0510】 The input consists of raw data sent from each location. The server retrieves this raw data via a dedicated API. Specifically, it queries the database, checks timestamps to ensure duplicates are removed and the data is up-to-date. The output is a dataset that has been organized for preprocessing. 【0511】 Step 2: 【0512】 The server preprocesses the collected data and converts it into an analyzable format. 【0513】 The input is the cleaned dataset obtained in Step 1. The server uses Python libraries such as Pandas and NumPy to impute missing values ​​and correct outliers. Specifically, it performs data cleansing and converts data types as needed. The output is a clean dataset suitable for analysis. 【0514】 Step 3: 【0515】 The server uses pre-processed data to perform detailed data analysis with an AI agent. 【0516】 The input is the clean dataset generated in Step 2. The server applies the generated AI model and leverages libraries such as TensorFlow and PyTorch to predict future revenue. Specifically, it performs trend analysis while evaluating the model's prediction accuracy. The output is the revenue forecast and insights based on that data. 【0517】 Step 4: 【0518】 The server generates the optimal business strategy based on the data analysis results. 【0519】 The input is the revenue forecast and insights created in Step 3. The server uses a rule-based engine to develop a concrete action plan. Specifically, it determines the prioritization of strategies and customizes them for each store. The output is a document outlining the specific business strategy. 【0520】 Step 5: 【0521】 The terminal visualizes the business strategy delivered from the server for store staff. 【0522】 The input is the business strategy document generated in Step 4. The terminal displays the information clearly through a user interface. Specifically, it visualizes data using graphs and charts and presents tasks in a list format. The output is information presented in a format that staff can understand and implement. 【0523】 Step 6: 【0524】 The store staff, who are the users, use the terminal to implement the suggested strategies. 【0525】 The input is the visualization information of the business strategy provided in Step 5. The user then carries out store operation improvement activities accordingly. Specific actions include implementing promotional campaigns, making proposals to new customers, and optimizing inventory management. The output is the results of the activities carried out. 【0526】 Step 7: 【0527】 The terminal records the results of the experiment and transfers them to the server. 【0528】 The input is the activity results obtained in step 6. The terminal formats the results and sends them to the server. Specifically, it extracts important indicators from the result data and aggregates them in digital format. The output is a database record for use in subsequent analyses. 【0529】 (Application Example 1) 【0530】 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." 【0531】 In store management, it is crucial to quickly and accurately formulate optimal business strategies to maximize profits. However, with conventional systems, data collection and analysis are time-consuming, and it is difficult to effectively manage the implementation status of strategies. This has led to delays in the formulation and execution of effective strategies, resulting in decreased operational efficiency. 【0532】 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. 【0533】 In this invention, the server includes means for collecting communication information, sales information, and user information; means for pre-processing the information and converting it into an analyzable format; and means for generating business strategies based on evaluation and prediction results. This enables real-time collection and analysis of various business data, rapid generation and visual presentation of optimal business strategies, and efficient management of the progress of strategy implementation. 【0534】 "Communication information" refers to data exchanged through digital networks and includes various types of information related to communication between stores and customers. 【0535】 "Sales information" refers to data related to the sale of goods and services, including sales figures, sales amounts, and customer purchase history. 【0536】 "User information" refers to various data about a store's customers, including personal attributes, behavioral history, and feedback. 【0537】 "Preprocessing" refers to the process of organizing and shaping data so that data analysis can be performed efficiently, and includes processes such as imputing missing values ​​and normalizing data. 【0538】 "Business strategy" refers to a specific action plan formulated by a company to maximize its profits, and includes sales promotion activities, securing new contracts, and streamlining inventory management. 【0539】 "Visual presentation" refers to a method of displaying information in a graphical format so that users can understand it intuitively. 【0540】 "Strategy implementation progress" is an evaluation indicator used to monitor the status of the implementation of formulated business strategies and to confirm whether they are progressing according to plan. 【0541】 In this invention, the server is responsible for collecting communication information, sales information, and user information in real time. Because the collected data is large in volume and diverse, efficient processing is required. The server preprocesses this data and converts it into an analyzable format. This preprocessing includes tasks such as imputing missing values ​​and normalizing the data. 【0542】 Pre-processed data is analyzed using a generative AI model running on the server. The purpose of this analysis is to comprehensively evaluate the current revenue situation and predict future revenue. The server considers historical data and market trends to generate the optimal business strategy. The generated strategy is then delivered to information terminals. 【0543】 The terminal visually presents the distributed business strategy to store staff. This allows staff to easily understand the strategy and implement it quickly. The terminal also provides an interface for managing the progress of strategy implementation and checking its achievement status. 【0544】 Store staff, as users, implement sales promotion activities, propose new contracts, and improve inventory management based on strategies displayed on their terminals. The results are recorded on the terminals and sent back to the server. The server uses these results for analysis in subsequent operations. 【0545】 As a concrete example, when a store introduces a new product, an AI model generates a sales promotion strategy. For instance, it might analyze weekend sales patterns and suggest running a campaign on Friday featuring a specific product. This suggestion is obtained by inputting a prompt message into the AI ​​model such as, "Based on the following sales data and feedback, please suggest the optimal sales strategy for the new product: Sales data: ..., Feedback: ...". 【0546】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0547】 Step 1: 【0548】 The server collects communication information, sales information, and user information from stores in real time. This data is obtained via the network, and the input of the collected data includes many types and formats. The output is stored as raw information for use in the next processing step. Specifically, it performs operations such as retrieving data using APIs and storing it in a database. 【0549】 Step 2: 【0550】 The server preprocesses the collected data and converts it into an analyzable format. The input is the various data collected in step 1, and the output is data with missing values ​​imputed and normalized as necessary. Specifically, it uses data cleaning techniques to correct outliers and filter the data, shaping it into a form that can be easily handled by machine learning models. 【0551】 Step 3: 【0552】 The server receives pre-processed data and analyzes it in detail using a generative AI model. The input is the data pre-processed in step 2, and the output includes revenue forecasts and the optimal business strategies for achieving them. Specifically, it uses machine learning frameworks such as Keras and TensorFlow to process the data through the model and generate prediction results. 【0553】 Step 4: 【0554】 The server distributes the generated business strategy to the information terminal. The input is the business strategy data generated in step 3, and the output is the strategy information received by the terminal. Specifically, it uses a notification API to send the strategy data to the terminal. 【0555】 Step 5: 【0556】 The terminal visually displays business strategies delivered from the server to store staff. The input is strategy data sent from the server, and the output is a clear presentation of the strategy through a visual user interface. Specifically, it uses a UI framework to display the strategy in graph and chart format. 【0557】 Step 6: 【0558】 The store staff, acting as users, perform specific tasks based on the strategy displayed on the terminal and record the results on the terminal. The input is the strategy content displayed on the terminal, and the output is data related to the results of the strategy's implementation. Specifically, they execute sales promotion measures according to the strategy and input the results into the application. 【0559】 Step 7: 【0560】 The terminal returns the results of the strategy's implementation to the server, providing data for use in subsequent analyses. The input is the implementation result data recorded by the user, and the output is the information sent to the server. Specifically, it uses a data transmission protocol to upload the result data to the server. 【0561】 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. 【0562】 This invention is a system that collects communication data, sales data, and customer data, and uses them to formulate business strategies to improve profitability. Furthermore, this system incorporates an emotion engine that recognizes user emotions and has the function of adjusting strategies while taking the user's emotional state into consideration. 【0563】 The server collects customer data in real time from customer-employee interactions at each store. This data includes customer tone of voice, changes in facial expressions, and the content of text chats. The data collected by the server is pre-processed and converted into a format that can be analyzed. 【0564】 The emotion engine uses voice analysis, facial expression analysis, and text analysis to identify customer emotions. For example, it can determine whether a customer is excited or calm from their voice tone, and facial expression recognition technology can read their smile or surprised expression. 【0565】 The server combines the acquired emotion recognition data with other collected data, evaluates revenue performance via an AI agent, and predicts future revenue. This means that newly recognized customer emotions directly influence the formulation of business strategies. Through this process, the server generates highly personalized strategies based on customer feedback. 【0566】 The terminal displays strategies delivered from the server to store staff. These visualized strategies include suggestions that take user emotions into consideration, assisting staff in providing responses and services that match customer emotions. The terminal collects the results after the strategy has been implemented and returns them to the server. 【0567】 Store staff, acting as users, take action based on the provided strategies and improve the accuracy of emotional data through interactions with customers. For example, involving staff specially trained to respond calmly to agitated customers can improve customer satisfaction. After implementing the strategy, users provide feedback on the implementation details and results via a terminal, which can then be used to improve the system for future use. 【0568】 This system achieves a higher level of revenue improvement than conventional data analysis by integrating customer data and sentiment data. 【0569】 The following describes the processing flow. 【0570】 Step 1: 【0571】 The server collects communication data, sales data, and customer data generated at each store in real time. The collection process is carried out through an automated network system, and the data is securely stored in a central database. 【0572】 Step 2: 【0573】 The server transfers data such as voice, facial expressions, and text obtained from customer interactions to the emotion engine. This emotion engine analyzes the user's emotional state and identifies emotions such as excitement, anxiety, and satisfaction. 【0574】 Step 3: 【0575】 The server combines the sentiment analysis results obtained from the sentiment engine with other collected data (communication, sales, and customer data) and passes it to the AI ​​agent. This AI agent uses a machine learning model to evaluate revenue and make future predictions. 【0576】 Step 4: 【0577】 The server generates an optimal business strategy that reflects emotional data based on the analysis results from the AI ​​agent. This strategy includes sales promotion activities and service improvements that respond to customer emotions. 【0578】 Step 5: 【0579】 The server delivers the generated business strategy to terminals in the stores. The terminals visualize the strategy in a format that is easy for staff to understand, and present the implementation steps and goals. 【0580】 Step 6: 【0581】 The terminal displays specific actions for customer service to store staff, who are the users of the device, and supports the provision of service that is appropriate to the customer's emotions. This allows staff to respond flexibly to customers' feelings. 【0582】 Step 7: 【0583】 Store staff, who are users of the system, put the strategies provided through the terminal into action. For example, they might engage in conversations that alleviate customer anxiety or offer special services to improve customer satisfaction. 【0584】 Step 8: 【0585】 The terminal then sends user feedback information back to the server. The server analyzes the received results and evaluates the effectiveness of the business strategy. This improves the accuracy of the strategy and customer service skills for future interactions. 【0586】 (Example 2) 【0587】 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." 【0588】 Traditional business strategy systems often failed to adequately consider customer emotional states, resulting in inefficient revenue evaluation and forecasting. This made it difficult to effectively improve customer satisfaction without maximizing business profitability. Furthermore, the lack of rapid and accurate feedback on the effectiveness of implemented strategies hindered continuous improvement. 【0589】 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. 【0590】 In this invention, the server includes means for collecting communication data, sales data, and customer data; means for analyzing pre-processed data and sentiment data; and means for generating and delivering personalized business strategies. This enables the development of business strategies that take customer sentiment into consideration and optimize revenue, as well as rapid feedback on their effectiveness. 【0591】 "Communication data" refers to all information sent and received over a network, including emails, messages, and call logs. 【0592】 "Sales data" refers to information related to the transactions of goods and services, and includes sales figures, sales volume, customer attributes, etc. 【0593】 "Customer data" refers to information about a specific customer, including their profile, purchase history, and inquiry history. 【0594】 "Preprocessing" refers to the preparation process for converting collected data into an analyzable format, which involves organizing, filtering, and structuring the data. 【0595】 "Emotional data" refers to information about a customer's emotional state, extracted from sources such as voice, facial expressions, and text. 【0596】 A "business strategy" refers to a plan or set of measures designed to achieve specific goals, aiming to improve revenue and customer satisfaction. 【0597】 An "information terminal" refers to a device used to receive and display data and instructions from a server, and includes tablets and personal computers. 【0598】 A "machine learning algorithm" refers to a computer program that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0599】 A "generative model" refers to an algorithm that generates output based on input information, and is used for natural language generation and image generation. 【0600】 A "prompt statement" refers to an instruction statement that is input to a generative model to elicit some kind of response. 【0601】 The system of this invention aims to improve business profitability by collecting, preprocessing, analyzing, generating strategies for, and distributing data. The specific implementation method is described below. 【0602】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. This allows for the continuous accumulation of raw data about interactions with each customer. 【0603】 The collected data is preprocessed by the server. Specifically, this includes filtering to reduce noise, structuring facial expression data using face recognition, and formatting text data using natural language processing. This preprocessing converts the data into a format that can be analyzed. 【0604】 An emotion engine embedded in the server analyzes pre-processed data to identify the customer's emotional state. In this process, the emotion engine uses voice analysis, facial expression analysis, and text analysis to extract emotions from each type of data. 【0605】 In strategy generation, the server uses AI agents based on collected and analyzed data to formulate individual business strategies. This involves applying machine learning algorithms to evaluate and predict profitability, and then generating strategies based on the results. An example of a prompt for the generated AI model is, "Based on recent customer interaction data, please tell me what customized products should be suggested on the next visit." 【0606】 The terminal visually delivers strategies generated from the server to store staff. Specifically, it displays strategies using tablet devices or displays and provides visual feedback to enable staff to understand them intuitively. 【0607】 Store staff, who are users of the system, interact with customers based on the provided strategy. Because the strategy includes suggestions that take into account the customer's emotional state, staff can provide optimal service and responses. This improves customer satisfaction and increases sales. 【0608】 After the strategy is implemented, the terminal collects the results and returns them to the server. This allows the server to evaluate the strategy's effectiveness and receive feedback for future strategy development. This process allows the system to continuously improve and create more accurate strategies. 【0609】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0610】 Step 1: 【0611】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. Inputs for this data include movement and sound within the store, and output is customer interaction data. This data includes recordings of voice calls, text chat logs, and video data obtained through facial recognition. 【0612】 Step 2: 【0613】 The server preprocesses the collected interaction data. This process involves filtering out noisy audio data, performing facial recognition on video data, and structuring text data. The input is raw data, and the output is data in an analyzable format. This process improves the accuracy of the data and transforms it to be suitable for the next analysis step. 【0614】 Step 3: 【0615】 The emotion engine identifies customer emotions from pre-processed data. It analyzes voice tone using voice analysis, detects smiles and surprised expressions using facial expression analysis, and extracts emotional keywords through text analysis. The input data is the output of step 2 and is output as emotion data. This process provides concrete data on the customer's psychological state. 【0616】 Step 4: 【0617】 The server integrates sentiment data and other collected data, and uses an AI agent to evaluate and predict profitability. Inputs include sentiment data, communication data, and sales data, and the output generates predicted future revenue scenarios. Here, machine learning algorithms are applied to analyze data correlations and make sales predictions. 【0618】 Step 5: 【0619】 The server generates personalized business strategies based on evaluation and prediction results. This generation process uses data obtained in the previous step as input and outputs specific sales plans and service proposals for customers. A generation AI model is used here, taking prompts as input to generate specific suggestions. For example, a prompt might be, "Please tell me what customized products you should suggest on my next visit." 【0620】 Step 6: 【0621】 The terminal receives business strategies generated from the server and displays them visually to store staff. The input is strategic data, and the output is visualized information displayed on a tablet or screen. Store staff can then view this information and take specific actions based on the strategy. 【0622】 Step 7: 【0623】 Store staff, acting as users, interact with customers based on the presented strategy and obtain results from its implementation. The input is the displayed business strategy, and the output is customer feedback and sales data. The results of actual customer interactions are used in the next feedback and improvement steps. 【0624】 Step 8: 【0625】 The terminal sends data obtained after the strategy is implemented to the server. The input is the result of customer interaction, and the output is in a data format for analysis. The server analyzes this data, evaluates the effectiveness of the strategy, and makes further improvements. 【0626】 (Application Example 2) 【0627】 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." 【0628】 In modern retail and service industries, meticulous service based on customer emotions and behavior is essential. However, many businesses lack the mechanisms to accurately capture customer emotions and provide services accordingly. As a result, services that do not meet customer expectations occur, leading to decreased customer satisfaction and reduced profits. This invention aims to solve these problems and maximize profits by enabling real-time customer service support based on customer emotions. 【0629】 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. 【0630】 In this invention, the server includes means for collecting multiple types of information, including communication information, distribution information, and customer information; means for pre-processing the information and converting it into an analyzable format; and means for recognizing customer emotions and adjusting customer service methods. This enables the provision of personalized services based on customer emotions. 【0631】 "Communication information" refers to information including data and call content exchanged over a network. 【0632】 "Distribution information" refers to information regarding the sale, inventory status, and logistics processes of goods and services. 【0633】 "Customer information" refers to information about customers' personal data, purchase history, behavioral patterns, and preferences. 【0634】 "Preprocessing" refers to the operations necessary to convert raw data into an analyzable format, such as data cleaning and format conversion. 【0635】 An "analyzable format" refers to a format in which collected data is prepared in a way that is suitable for machine learning algorithms and statistical analysis. 【0636】 "Profit" refers to the economic results or income that a company earns through its activities. 【0637】 "Business strategy" refers to the policies and plans that a company formulates to achieve its business objectives. 【0638】 "Terminal device" refers to a device used to transmit or receive information, including computers and smartphones. 【0639】 "Customer emotions" refer to the psychological state or feelings a customer experiences at a particular moment. 【0640】 "Adjustment" refers to the act of changing settings or operations to suit specific conditions or purposes. 【0641】 This invention is a system for providing personalized services based on customer emotions. Specifically, it collects communication information, distribution information, and customer information, and generates business strategies based on these. The specific configuration and method for carrying out this invention are described below. 【0642】 The server uses cameras and microphones installed in the store to collect customers' facial expressions and voices in real time. Hardware includes high-resolution cameras (e.g., Logitech Brio) and high-precision microphones (e.g., Shure MV5C). The server receives the collected data and analyzes it using machine learning techniques. In this process, it utilizes Google Cloud's machine learning APIs (e.g., Cloud Speech-to-Text API and Vision AI) to identify customer emotions. 【0643】 Once the analysis is complete, the data is sent via Firebase to the store staff's terminal devices. These terminal devices are the staff's smartphones or tablets. Based on the received sentiment data, the terminals display business strategies, including customer service methods, on the screen. This enables staff to respond appropriately to customers' emotions. 【0644】 For example, if the system analyzes that a customer walking through the store has a calm expression, it will suggest to the staff, "Recommend the new product and explain the details if they are interested." Conversely, if a customer looks unhappy, it will provide instructions such as, "Respond in a calm tone and ask if they have any problems." 【0645】 This system is expected to improve the quality of service provided to each customer, and consequently, the profitability of the stores. 【0646】 Example of a prompt: 【0647】 Please describe a system that uses generative AI to analyze customers' facial expressions and tone of voice in a store in real time, and then proposes customer service strategies based on those emotions. 【0648】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0649】 Step 1: 【0650】 The server acquires customer facial expression and audio data in real time from cameras and microphones installed in the store. The cameras capture facial features as video, and the microphones record voice tone as audio. This data is then input into the server. 【0651】 Step 2: 【0652】 The server preprocesses the acquired video data using image processing software. This enhances facial features and removes noise. The preprocessed data is then used as input for analyzing the customer's facial expressions. 【0653】 Step 3: 【0654】 The server utilizes Google Cloud's Vision AI to analyze customer facial expressions from pre-processed video data. This allows it to output specific emotional states, such as whether the customer is angry or happy. 【0655】 Step 4: 【0656】 Meanwhile, the server converts the acquired audio data into text data using Google Cloud's Speech-to-Text API. This conversion analyzes the tone of voice and outputs it as additional information for recognizing emotions. 【0657】 Step 5: 【0658】 The server integrates emotion data from Vision AI and speech tone data from Speech-to-Text to evaluate overall customer sentiment. Based on this evaluation, a generative AI model is used to determine the appropriate customer service approach and generate a customer service strategy. 【0659】 Step 6: 【0660】 The generated customer service strategy is sent to the device via Firebase. The device receives this information and visually presents the strategy to the store staff. Based on the instructions displayed on the screen, the staff begins to provide appropriate service to the customer. 【0661】 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. 【0662】 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. 【0663】 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. 【0664】 [Fourth Embodiment] 【0665】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0666】 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. 【0667】 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). 【0668】 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. 【0669】 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. 【0670】 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). 【0671】 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. 【0672】 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. 【0673】 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. 【0674】 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. 【0675】 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. 【0676】 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. 【0677】 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". 【0678】 This system collects management data from each store, analyzes that data using an AI agent, and proposes the optimal revenue improvement strategy. To realize this process, the roles of the server, terminal, and user are clearly defined. 【0679】 The server first collects various data from each store in real time, such as the number of communication contracts, terminal sales, the number of optional services used, and customer feedback. Because this data is generated in large quantities at once, it is collected periodically via the network and stored centrally. 【0680】 Subsequently, before passing the collected data to the AI ​​agent, the server performs preprocessing by converting the data into a format that can be analyzed. Specifically, it imputes missing values ​​and corrects outliers, preparing the data for efficient analysis. 【0681】 Next, the server uses an AI agent to analyze the pre-processed data in detail. At this stage, it comprehensively evaluates the current revenue situation and predicts future revenue by considering historical data and market trends. Based on this analysis, the server generates specific business strategies for maximizing revenue. 【0682】 The terminals play a role in making business strategies delivered from the server visible to store staff. Each terminal has a function to display strategies in an easy-to-understand format, helping staff to quickly implement them. The terminals also have support functions that reduce the workload of staff by automating some processes. 【0683】 Store staff, as users, use the terminals to implement the provided business strategies. Specifically, they conduct promotional campaigns, propose new contracts, optimize inventory, and record the results on the terminals. The terminals then return these results to the server, which are used for analysis in subsequent operations. 【0684】 As a concrete example, if a store wants to promote a new product, the server analyzes market data related to the new product and sales data for similar products from the past, and proposes a promotional strategy tailored to the target customer segment. This strategy is notified to store staff via terminals, allowing them to quickly understand and implement it. This improves the efficiency of sales promotion activities and leads to increased profits. 【0685】 The following describes the processing flow. 【0686】 Step 1: 【0687】 The server collects data in real time from each store, including the number of communication contracts, terminal sales, optional service usage, and customer feedback. This data is automatically collected via a secure network and stored in a central database. 【0688】 Step 2: 【0689】 The server begins processing the collected raw data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. This process ensures the data is clean and suitable for AI analysis. 【0690】 Step 3: 【0691】 The server passes pre-processed data to the AI ​​agent and instructs it to perform the analysis. The AI ​​agent uses machine learning algorithms to analyze the data and evaluate the current revenue situation. It also predicts future revenue based on historical data and market trends. 【0692】 Step 4: 【0693】 The server receives the analysis results from the AI ​​agent and generates an optimal business strategy based on them. This strategy includes acquiring new contracts, sales promotion activities, and streamlining inventory management. 【0694】 Step 5: 【0695】 The server distributes the generated business strategies to the terminals in the stores. This distribution is customized to suit the characteristics and circumstances of each store. 【0696】 Step 6: 【0697】 The terminal visually presents business strategies received from the server to store staff. It clearly displays strategy details, implementation steps, and expected effects, helping staff act quickly and accurately. 【0698】 Step 7: 【0699】 Store staff, acting as users, execute business strategies instructed on their terminals. For example, they might launch a new sales promotion, adjust inventory, or engage in customer outreach activities. Users input the results of their strategy execution into the terminal, which is then sent to the server for further analysis. 【0700】 Step 8: 【0701】 The server analyzes the results from user execution and evaluates the effectiveness of the strategy. Based on this evaluation, the AI ​​agent's algorithm is adjusted to help generate the next strategy. This feedback loop continuously improves the accuracy and effectiveness of the entire system. 【0702】 (Example 1) 【0703】 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". 【0704】 For many companies, effectively formulating business strategies based on diverse data is a crucial challenge. In particular, there is a need to collect large amounts of data in real time, analyze it quickly and accurately to predict future profits, and then develop and implement concrete and actionable business strategies based on those results. However, traditional methods have suffered from the cumbersome preprocessing and analysis of individual data points, resulting in insufficient correlation with actual profit improvement. 【0705】 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. 【0706】 In this invention, the server includes means for acquiring multiple types of information, including communication data, sales data, and customer data, from each location; means for preprocessing the acquired information and converting it into a format suitable for analysis; and means for evaluating revenue and predicting future revenue based on the converted information. This enables efficient use of multifaceted data to generate management strategies, and sustainable revenue improvement through their implementation and evaluation. 【0707】 "Communication data" refers to data related to the usage status and contract information of communication services. 【0708】 "Sales data" refers to data regarding the sales status, quantity, and revenue of a product. 【0709】 "Customer data" refers to data related to customer attributes, purchase history, and feedback. 【0710】 "Preprocessing" refers to the data cleaning and formatting processes performed to convert raw data into a format suitable for analysis. 【0711】 An "analyzable format" is a structured data format necessary for machine learning and data analysis. 【0712】 "Evaluating and forecasting revenue" is the process of analyzing the current financial situation and estimating future sales and profits. 【0713】 A "business strategy" is a specific action plan that a company chooses to take in order to achieve its goals. 【0714】 An "information display device" is a device that visually displays digital data, and mainly includes monitors and tablets. 【0715】 A "generative AI model" is an artificial intelligence algorithm that learns from data to generate new information and predictions. 【0716】 To implement this system, servers, terminals, and users must work together and fulfill their respective roles. The purpose of this system is to efficiently collect and analyze management data from each location and provide optimized management strategies. 【0717】 The server acquires communication data, sales data, and customer data from each location in real time. This is done using a dedicated data collection module, securely transferring data over communication networks such as the internet. The data is preprocessed using data processing libraries such as Python's Pandas and NumPy. This process involves imputing missing values ​​and correcting outliers, formatting the data into a parseable format. 【0718】 Next, the server analyzes the preprocessed data using a generative AI model. Machine learning libraries such as TensorFlow and PyTorch are used for the AI ​​analysis. These tools are leveraged to predict future revenues, taking into account historical data and market trends. Based on the prediction results, a business strategy is generated. 【0719】 The terminal displays the generated business strategy through a user interface. Staff can visually confirm the strategic information displayed on the terminal and immediately take concrete actions based on the strategy. For example, instructions on how to implement a promotional campaign or how to optimize inventory management are displayed graphically. 【0720】 Store staff, acting as users, implement the suggested strategies using the terminals. For example, when promoting a new product, they can plan and implement promotions tailored to target customers. The results after implementation are sent back to the server via the terminals and used for future analysis. 【0721】 For example, if a store wants to promote the sale of a new product, the server analyzes past data and market trends to develop an effective promotional strategy tailored to the target audience. By inputting a prompt such as, "Analyze and propose the optimal promotional strategy for the store's new product sales," into the AI ​​model, the model derives an appropriate strategy. This allows companies to respond quickly and maximize their profits. 【0722】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0723】 Step 1: 【0724】 The server collects communication data, sales data, and customer data from each location in real time. 【0725】 The input consists of raw data sent from each location. The server retrieves this raw data via a dedicated API. Specifically, it queries the database, checks timestamps to ensure duplicates are removed and the data is up-to-date. The output is a dataset that has been organized for preprocessing. 【0726】 Step 2: 【0727】 The server preprocesses the collected data and converts it into an analyzable format. 【0728】 The input is the cleaned dataset obtained in Step 1. The server uses Python libraries such as Pandas and NumPy to impute missing values ​​and correct outliers. Specifically, it performs data cleansing and converts data types as needed. The output is a clean dataset suitable for analysis. 【0729】 Step 3: 【0730】 The server uses pre-processed data to perform detailed data analysis with an AI agent. 【0731】 The input is the clean dataset generated in Step 2. The server applies the generated AI model and leverages libraries such as TensorFlow and PyTorch to predict future revenue. Specifically, it performs trend analysis while evaluating the model's prediction accuracy. The output is the revenue forecast and insights based on that data. 【0732】 Step 4: 【0733】 The server generates the optimal business strategy based on the data analysis results. 【0734】 The input is the revenue forecast and insights created in Step 3. The server uses a rule-based engine to develop a concrete action plan. Specifically, it determines the prioritization of strategies and customizes them for each store. The output is a document outlining the specific business strategy. 【0735】 Step 5: 【0736】 The terminal visualizes the business strategy delivered from the server for store staff. 【0737】 The input is the business strategy document generated in Step 4. The terminal displays the information clearly through a user interface. Specifically, it visualizes data using graphs and charts and presents tasks in a list format. The output is information presented in a format that staff can understand and implement. 【0738】 Step 6: 【0739】 The store staff, who are the users, use the terminal to implement the suggested strategies. 【0740】 The input is the visualization information of the business strategy provided in Step 5. The user then carries out store operation improvement activities accordingly. Specific actions include implementing promotional campaigns, making proposals to new customers, and optimizing inventory management. The output is the results of the activities carried out. 【0741】 Step 7: 【0742】 The terminal records the results of the experiment and transfers them to the server. 【0743】 The input is the activity results obtained in step 6. The terminal formats the results and sends them to the server. Specifically, it extracts important indicators from the result data and aggregates them in digital format. The output is a database record for use in subsequent analyses. 【0744】 (Application Example 1) 【0745】 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". 【0746】 In store management, it is crucial to quickly and accurately formulate optimal business strategies to maximize profits. However, with conventional systems, data collection and analysis are time-consuming, and it is difficult to effectively manage the implementation status of strategies. This has led to delays in the formulation and execution of effective strategies, resulting in decreased operational efficiency. 【0747】 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. 【0748】 In this invention, the server includes means for collecting communication information, sales information, and user information; means for pre-processing the information and converting it into an analyzable format; and means for generating business strategies based on evaluation and prediction results. This enables real-time collection and analysis of various business data, rapid generation and visual presentation of optimal business strategies, and efficient management of the progress of strategy implementation. 【0749】 "Communication information" refers to data exchanged through digital networks and includes various types of information related to communication between stores and customers. 【0750】 "Sales information" refers to data related to the sale of goods and services, including sales figures, sales amounts, and customer purchase history. 【0751】 "User information" refers to various data about a store's customers, including personal attributes, behavioral history, and feedback. 【0752】 "Preprocessing" refers to the process of organizing and shaping data so that data analysis can be performed efficiently, and includes processes such as imputing missing values ​​and normalizing data. 【0753】 "Business strategy" refers to a specific action plan formulated by a company to maximize its profits, and includes sales promotion activities, securing new contracts, and streamlining inventory management. 【0754】 "Visual presentation" refers to a method of displaying information in a graphical format so that users can understand it intuitively. 【0755】 "Strategy implementation progress" is an evaluation indicator used to monitor the status of the implementation of formulated business strategies and to confirm whether they are progressing according to plan. 【0756】 In this invention, the server is responsible for collecting communication information, sales information, and user information in real time. Because the collected data is large in volume and diverse, efficient processing is required. The server preprocesses this data and converts it into an analyzable format. This preprocessing includes tasks such as imputing missing values ​​and normalizing the data. 【0757】 Pre-processed data is analyzed using a generative AI model running on the server. The purpose of this analysis is to comprehensively evaluate the current revenue situation and predict future revenue. The server considers historical data and market trends to generate the optimal business strategy. The generated strategy is then delivered to information terminals. 【0758】 The terminal visually presents the distributed business strategy to store staff. This allows staff to easily understand the strategy and implement it quickly. The terminal also provides an interface for managing the progress of strategy implementation and checking its achievement status. 【0759】 Store staff, as users, implement sales promotion activities, propose new contracts, and improve inventory management based on strategies displayed on their terminals. The results are recorded on the terminals and sent back to the server. The server uses these results for analysis in subsequent operations. 【0760】 As a concrete example, when a store introduces a new product, an AI model generates a sales promotion strategy. For instance, it might analyze weekend sales patterns and suggest running a campaign on Friday featuring a specific product. This suggestion is obtained by inputting a prompt message into the AI ​​model such as, "Based on the following sales data and feedback, please suggest the optimal sales strategy for the new product: Sales data: ..., Feedback: ...". 【0761】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0762】 Step 1: 【0763】 The server collects communication information, sales information, and user information from stores in real time. This data is obtained via the network, and the input of the collected data includes many types and formats. The output is stored as raw information for use in the next processing step. Specifically, it performs operations such as retrieving data using APIs and storing it in a database. 【0764】 Step 2: 【0765】 The server preprocesses the collected data and converts it into an analyzable format. The input is the various data collected in step 1, and the output is data with missing values ​​imputed and normalized as necessary. Specifically, it uses data cleaning techniques to correct outliers and filter the data, shaping it into a form that can be easily handled by machine learning models. 【0766】 Step 3: 【0767】 The server receives pre-processed data and analyzes it in detail using a generative AI model. The input is the data pre-processed in step 2, and the output includes revenue forecasts and the optimal business strategies for achieving them. Specifically, it uses machine learning frameworks such as Keras and TensorFlow to process the data through the model and generate prediction results. 【0768】 Step 4: 【0769】 The server distributes the generated business strategy to the information terminal. The input is the business strategy data generated in step 3, and the output is the strategy information received by the terminal. Specifically, it uses a notification API to send the strategy data to the terminal. 【0770】 Step 5: 【0771】 The terminal visually displays business strategies delivered from the server to store staff. The input is strategy data sent from the server, and the output is a clear presentation of the strategy through a visual user interface. Specifically, it uses a UI framework to display the strategy in graph and chart format. 【0772】 Step 6: 【0773】 The store staff, acting as users, perform specific tasks based on the strategy displayed on the terminal and record the results on the terminal. The input is the strategy content displayed on the terminal, and the output is data related to the results of the strategy's implementation. Specifically, they execute sales promotion measures according to the strategy and input the results into the application. 【0774】 Step 7: 【0775】 The terminal returns the results of the strategy's implementation to the server, providing data for use in subsequent analyses. The input is the implementation result data recorded by the user, and the output is the information sent to the server. Specifically, it uses a data transmission protocol to upload the result data to the server. 【0776】 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. 【0777】 This invention is a system that collects communication data, sales data, and customer data, and uses them to formulate business strategies to improve profitability. Furthermore, this system incorporates an emotion engine that recognizes user emotions and has the function of adjusting strategies while taking the user's emotional state into consideration. 【0778】 The server collects customer data in real time from customer-employee interactions at each store. This data includes customer tone of voice, changes in facial expressions, and the content of text chats. The data collected by the server is pre-processed and converted into a format that can be analyzed. 【0779】 The emotion engine uses voice analysis, facial expression analysis, and text analysis to identify customer emotions. For example, it can determine whether a customer is excited or calm from their voice tone, and facial expression recognition technology can read their smile or surprised expression. 【0780】 The server combines the acquired emotion recognition data with other collected data, evaluates revenue performance via an AI agent, and predicts future revenue. This means that newly recognized customer emotions directly influence the formulation of business strategies. Through this process, the server generates highly personalized strategies based on customer feedback. 【0781】 The terminal displays strategies delivered from the server to store staff. These visualized strategies include suggestions that take user emotions into consideration, assisting staff in providing responses and services that match customer emotions. The terminal collects the results after the strategy has been implemented and returns them to the server. 【0782】 Store staff, acting as users, take action based on the provided strategies and improve the accuracy of emotional data through interactions with customers. For example, involving staff specially trained to respond calmly to agitated customers can improve customer satisfaction. After implementing the strategy, users provide feedback on the implementation details and results via a terminal, which can then be used to improve the system for future use. 【0783】 This system achieves a higher level of revenue improvement than conventional data analysis by integrating customer data and sentiment data. 【0784】 The following describes the processing flow. 【0785】 Step 1: 【0786】 The server collects communication data, sales data, and customer data generated at each store in real time. The collection process is carried out through an automated network system, and the data is securely stored in a central database. 【0787】 Step 2: 【0788】 The server transfers data such as voice, facial expressions, and text obtained from customer interactions to the emotion engine. This emotion engine analyzes the user's emotional state and identifies emotions such as excitement, anxiety, and satisfaction. 【0789】 Step 3: 【0790】 The server combines the sentiment analysis results obtained from the sentiment engine with other collected data (communication, sales, and customer data) and passes it to the AI ​​agent. This AI agent uses a machine learning model to evaluate revenue and make future predictions. 【0791】 Step 4: 【0792】 The server generates an optimal business strategy that reflects emotional data based on the analysis results from the AI ​​agent. This strategy includes sales promotion activities and service improvements that respond to customer emotions. 【0793】 Step 5: 【0794】 The server delivers the generated business strategy to terminals in the stores. The terminals visualize the strategy in a format that is easy for staff to understand, and present the implementation steps and goals. 【0795】 Step 6: 【0796】 The terminal displays specific actions for customer service to store staff, who are the users of the device, and supports the provision of service that is appropriate to the customer's emotions. This allows staff to respond flexibly to customers' feelings. 【0797】 Step 7: 【0798】 Store staff, who are users of the system, put the strategies provided through the terminal into action. For example, they might engage in conversations that alleviate customer anxiety or offer special services to improve customer satisfaction. 【0799】 Step 8: 【0800】 The terminal then sends user feedback information back to the server. The server analyzes the received results and evaluates the effectiveness of the business strategy. This improves the accuracy of the strategy and customer service skills for future interactions. 【0801】 (Example 2) 【0802】 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". 【0803】 Traditional business strategy systems often failed to adequately consider customer emotional states, resulting in inefficient revenue evaluation and forecasting. This made it difficult to effectively improve customer satisfaction without maximizing business profitability. Furthermore, the lack of rapid and accurate feedback on the effectiveness of implemented strategies hindered continuous improvement. 【0804】 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. 【0805】 In this invention, the server includes means for collecting communication data, sales data, and customer data; means for analyzing pre-processed data and sentiment data; and means for generating and delivering personalized business strategies. This enables the development of business strategies that take customer sentiment into consideration and optimize revenue, as well as rapid feedback on their effectiveness. 【0806】 "Communication data" refers to all information sent and received over a network, including emails, messages, and call logs. 【0807】 "Sales data" refers to information related to the transactions of goods and services, and includes sales figures, sales volume, customer attributes, etc. 【0808】 "Customer data" refers to information about a specific customer, including their profile, purchase history, and inquiry history. 【0809】 "Preprocessing" refers to the preparation process for converting collected data into an analyzable format, which involves organizing, filtering, and structuring the data. 【0810】 "Emotional data" refers to information about a customer's emotional state, extracted from sources such as voice, facial expressions, and text. 【0811】 A "business strategy" refers to a plan or set of measures designed to achieve specific goals, aiming to improve revenue and customer satisfaction. 【0812】 An "information terminal" refers to a device used to receive and display data and instructions from a server, and includes tablets and personal computers. 【0813】 A "machine learning algorithm" refers to a computer program that learns patterns from large amounts of data and uses them to make predictions and classifications. 【0814】 A "generative model" refers to an algorithm that generates output based on input information, and is used for natural language generation and image generation. 【0815】 A "prompt statement" refers to an instruction statement that is input to a generative model to elicit some kind of response. 【0816】 The system of this invention aims to improve business profitability by collecting, preprocessing, analyzing, generating strategies for, and distributing data. The specific implementation method is described below. 【0817】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. This allows for the continuous accumulation of raw data about interactions with each customer. 【0818】 The collected data is preprocessed by the server. Specifically, this includes filtering to reduce noise, structuring facial expression data using face recognition, and formatting text data using natural language processing. This preprocessing converts the data into a format that can be analyzed. 【0819】 An emotion engine embedded in the server analyzes pre-processed data to identify the customer's emotional state. In this process, the emotion engine uses voice analysis, facial expression analysis, and text analysis to extract emotions from each type of data. 【0820】 In strategy generation, the server uses AI agents based on collected and analyzed data to formulate individual business strategies. This involves applying machine learning algorithms to evaluate and predict profitability, and then generating strategies based on the results. An example of a prompt for the generated AI model is, "Based on recent customer interaction data, please tell me what customized products should be suggested on the next visit." 【0821】 The terminal visually delivers strategies generated from the server to store staff. Specifically, it displays strategies using tablet devices or displays and provides visual feedback to enable staff to understand them intuitively. 【0822】 Store staff, who are users of the system, interact with customers based on the provided strategy. Because the strategy includes suggestions that take into account the customer's emotional state, staff can provide optimal service and responses. This improves customer satisfaction and increases sales. 【0823】 After the strategy is implemented, the terminal collects the results and returns them to the server. This allows the server to evaluate the strategy's effectiveness and receive feedback for future strategy development. This process allows the system to continuously improve and create more accurate strategies. 【0824】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0825】 Step 1: 【0826】 The server uses sensors, cameras, and microphones installed in each store to collect communication data, sales data, and customer data in real time. Inputs for this data include movement and sound within the store, and output is customer interaction data. This data includes recordings of voice calls, text chat logs, and video data obtained through facial recognition. 【0827】 Step 2: 【0828】 The server preprocesses the collected interaction data. This process involves filtering out noisy audio data, performing facial recognition on video data, and structuring text data. The input is raw data, and the output is data in an analyzable format. This process improves the accuracy of the data and transforms it to be suitable for the next analysis step. 【0829】 Step 3: 【0830】 The emotion engine identifies customer emotions from pre-processed data. It analyzes voice tone using voice analysis, detects smiles and surprised expressions using facial expression analysis, and extracts emotional keywords through text analysis. The input data is the output of step 2 and is output as emotion data. This process provides concrete data on the customer's psychological state. 【0831】 Step 4: 【0832】 The server integrates sentiment data and other collected data, and uses an AI agent to evaluate and predict profitability. Inputs include sentiment data, communication data, and sales data, and the output generates predicted future revenue scenarios. Here, machine learning algorithms are applied to analyze data correlations and make sales predictions. 【0833】 Step 5: 【0834】 The server generates personalized business strategies based on evaluation and prediction results. This generation process uses data obtained in the previous step as input and outputs specific sales plans and service proposals for customers. A generation AI model is used here, taking prompts as input to generate specific suggestions. For example, a prompt might be, "Please tell me what customized products you should suggest on my next visit." 【0835】 Step 6: 【0836】 The terminal receives business strategies generated from the server and displays them visually to store staff. The input is strategic data, and the output is visualized information displayed on a tablet or screen. Store staff can then view this information and take specific actions based on the strategy. 【0837】 Step 7: 【0838】 Store staff, acting as users, interact with customers based on the presented strategy and obtain results from its implementation. The input is the displayed business strategy, and the output is customer feedback and sales data. The results of actual customer interactions are used in the next feedback and improvement steps. 【0839】 Step 8: 【0840】 The terminal sends data obtained after the strategy is implemented to the server. The input is the result of customer interaction, and the output is in a data format for analysis. The server analyzes this data, evaluates the effectiveness of the strategy, and makes further improvements. 【0841】 (Application Example 2) 【0842】 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". 【0843】 In modern retail and service industries, meticulous service based on customer emotions and behavior is essential. However, many businesses lack the mechanisms to accurately capture customer emotions and provide services accordingly. As a result, services that do not meet customer expectations occur, leading to decreased customer satisfaction and reduced profits. This invention aims to solve these problems and maximize profits by enabling real-time customer service support based on customer emotions. 【0844】 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. 【0845】 In this invention, the server includes means for collecting multiple types of information, including communication information, distribution information, and customer information; means for pre-processing the information and converting it into an analyzable format; and means for recognizing customer emotions and adjusting customer service methods. This enables the provision of personalized services based on customer emotions. 【0846】 "Communication information" refers to information including data and call content exchanged over a network. 【0847】 "Distribution information" refers to information regarding the sale, inventory status, and logistics processes of goods and services. 【0848】 "Customer information" refers to information about customers' personal data, purchase history, behavioral patterns, and preferences. 【0849】 "Preprocessing" refers to the operations necessary to convert raw data into an analyzable format, such as data cleaning and format conversion. 【0850】 An "analyzable format" refers to a format in which collected data is prepared in a way that is suitable for machine learning algorithms and statistical analysis. 【0851】 "Profit" refers to the economic results or income that a company earns through its activities. 【0852】 "Business strategy" refers to the policies and plans that a company formulates to achieve its business objectives. 【0853】 "Terminal device" refers to a device used to transmit or receive information, including computers and smartphones. 【0854】 "Customer emotions" refer to the psychological state or feelings a customer experiences at a particular moment. 【0855】 "Adjustment" refers to the act of changing settings or operations to suit specific conditions or purposes. 【0856】 This invention is a system for providing personalized services based on customer emotions. Specifically, it collects communication information, distribution information, and customer information, and generates business strategies based on these. The specific configuration and method for carrying out this invention are described below. 【0857】 The server uses cameras and microphones installed in the store to collect customers' facial expressions and voices in real time. Hardware includes high-resolution cameras (e.g., Logitech Brio) and high-precision microphones (e.g., Shure MV5C). The server receives the collected data and analyzes it using machine learning techniques. In this process, it utilizes Google Cloud's machine learning APIs (e.g., Cloud Speech-to-Text API and Vision AI) to identify customer emotions. 【0858】 Once the analysis is complete, the data is sent via Firebase to the store staff's terminal devices. These terminal devices are the staff's smartphones or tablets. Based on the received sentiment data, the terminals display business strategies, including customer service methods, on the screen. This enables staff to respond appropriately to customers' emotions. 【0859】 For example, if the system analyzes that a customer walking through the store has a calm expression, it will suggest to the staff, "Recommend the new product and explain the details if they are interested." Conversely, if a customer looks unhappy, it will provide instructions such as, "Respond in a calm tone and ask if they have any problems." 【0860】 This system is expected to improve the quality of service provided to each customer, and consequently, the profitability of the stores. 【0861】 Example of a prompt: 【0862】 Please describe a system that uses generative AI to analyze customers' facial expressions and tone of voice in a store in real time, and then proposes customer service strategies based on those emotions. 【0863】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0864】 Step 1: 【0865】 The server acquires customer facial expression and audio data in real time from cameras and microphones installed in the store. The cameras capture facial features as video, and the microphones record voice tone as audio. This data is then input into the server. 【0866】 Step 2: 【0867】 The server preprocesses the acquired video data using image processing software. This enhances facial features and removes noise. The preprocessed data is then used as input for analyzing the customer's facial expressions. 【0868】 Step 3: 【0869】 The server utilizes Google Cloud's Vision AI to analyze customer facial expressions from pre-processed video data. This allows it to output specific emotional states, such as whether the customer is angry or happy. 【0870】 Step 4: 【0871】 Meanwhile, the server converts the acquired audio data into text data using Google Cloud's Speech-to-Text API. This conversion analyzes the tone of voice and outputs it as additional information for recognizing emotions. 【0872】 Step 5: 【0873】 The server integrates emotion data from Vision AI and speech tone data from Speech-to-Text to evaluate overall customer sentiment. Based on this evaluation, a generative AI model is used to determine the appropriate customer service approach and generate a customer service strategy. 【0874】 Step 6: 【0875】 The generated customer service strategy is sent to the device via Firebase. The device receives this information and visually presents the strategy to the store staff. Based on the instructions displayed on the screen, the staff begins to provide appropriate service to the customer. 【0876】 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. 【0877】 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. 【0878】 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. 【0879】 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. 【0880】 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. 【0881】 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. 【0882】 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. 【0883】 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. 【0884】 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." 【0885】 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. 【0886】 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. 【0887】 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. 【0888】 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. 【0889】 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. 【0890】 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. 【0891】 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. 【0892】 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. 【0893】 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. 【0894】 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. 【0895】 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. 【0896】 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 to be incorporated by reference. 【0897】 The following is further disclosed regarding the embodiments described above. 【0898】 (Claim 1) 【0899】 A means of collecting multiple types of data, including communication data, sales data, and customer data, 【0900】 Means for preprocessing the aforementioned data and converting it into an analyzable format, 【0901】 A means for evaluating and predicting revenue based on the aforementioned preprocessed data, 【0902】 A means for generating an optimal business strategy based on the aforementioned evaluation and prediction results, 【0903】 A means for distributing the generated strategy to an information terminal, 【0904】 Means for collecting and analyzing the results of the implementation of the aforementioned strategy, 【0905】 A system that includes this. 【0906】 (Claim 2) 【0907】 The system according to claim 1, characterized in that the aforementioned business strategy includes sales promotion activities, acquisition of new contracts, and improvement of inventory management. 【0908】 (Claim 3) 【0909】 The system according to claim 1, characterized in that a machine learning algorithm is used on the data in the aforementioned analyzable format. 【0910】 "Example 1" 【0911】 (Claim 1) 【0912】 A means of acquiring multiple types of information from each location, including communication data, sales data, and customer data. 【0913】 Means for preprocessing the acquired information and converting it into a format suitable for analysis, 【0914】 A means for evaluating revenue and predicting future revenue based on the information converted to the aforementioned format, 【0915】 A means for generating an optimal business strategy based on the aforementioned evaluation and prediction results, 【0916】 A means for distributing the generated strategy to an information display device and presenting it visually, 【0917】 A means for obtaining and analyzing the results of the execution of the aforementioned strategy, 【0918】 A system that includes this. 【0919】 (Claim 2) 【0920】 The system according to claim 1, characterized in that the aforementioned business strategy includes sales promotion activities, acquisition of new contracts, and optimization of inventory management. 【0921】 (Claim 3) 【0922】 The system according to claim 1, characterized in that a generative AI model is used for information in a format suitable for the aforementioned analysis. 【0923】 "Application Example 1" 【0924】 (Claim 1) 【0925】 Means for collecting a wide variety of information, including communication information, sales information, and user information, 【0926】 Means for preprocessing the aforementioned information and converting it into an analyzable format, 【0927】 A means for evaluating and predicting profits based on the aforementioned preprocessed information, 【0928】 A means for generating an optimal business strategy based on the aforementioned evaluation and prediction results, 【0929】 A means for distributing the generated strategy to an information terminal and presenting it visually, 【0930】 A means for managing the progress of the implementation of the aforementioned strategy and confirming its achievement status, 【0931】 A system that includes this. 【0932】 (Claim 2) 【0933】 The system according to claim 1, characterized in that the aforementioned business strategy includes sales promotion activities, conclusion of new contracts, and efficiency improvements in inventory management. 【0934】 (Claim 3) 【0935】 The system according to claim 1, characterized in that it uses a machine learning algorithm on the information in the aforementioned analyzable format and uses a generative AI model to predict future business strategies. 【0936】 "Example 2 of combining an emotion engine" 【0937】 (Claim 1) 【0938】 A means of collecting multiple types of data, including communication data, sales data, and customer data, 【0939】 Means for preprocessing the aforementioned data and converting it into an analyzable format, 【0940】 A means of recognizing emotional states from voice, facial expressions, and text, 【0941】 Means for evaluating and predicting revenue based on the aforementioned preprocessed data and sentiment data, 【0942】 Means for generating a personalized business strategy based on the aforementioned evaluation and prediction results, 【0943】 A means for distributing the generated strategy to an information terminal and displaying it visually, 【0944】 Means for collecting and analyzing the results of the implementation of the aforementioned strategy, 【0945】 A system that includes this. 【0946】 (Claim 2) 【0947】 The system according to claim 1, characterized in that the business strategy includes sales promotion activities, acquisition of new contracts, and improvement of inventory management, as well as proposals based on the emotional state of the customer. 【0948】 (Claim 3) 【0949】 The system according to claim 1, characterized by using a machine learning algorithm on the data in the aforementioned analyzable format, and in addition, generating prompt sentences using a generative model. 【0950】 "Application example 2 when combining with an emotional engine" 【0951】 (Claim 1) 【0952】 A means of collecting multiple types of information, including communication information, distribution information, and customer information, 【0953】 Means for preprocessing the aforementioned information and converting it into an analyzable format, 【0954】 A means for evaluating and predicting profits based on the aforementioned preprocessed information, 【0955】 A means for generating an optimal business strategy based on the aforementioned evaluation and prediction results, 【0956】 Means for distributing the generated strategy to a terminal device, 【0957】 Means for collecting and analyzing the results of the implementation of the aforementioned strategy, 【0958】 A means of recognizing customer emotions and adjusting customer service methods, 【0959】 A system that includes this. 【0960】 (Claim 2) 【0961】 The system according to claim 1, wherein the aforementioned business strategy includes sales promotion activities, acquisition of new business, and improvement of inventory management, and further analyzes customer emotions from facial expressions and voice to propose customer service guidelines. 【0962】 (Claim 3) 【0963】 The system according to claim 1, characterized in that it uses machine learning techniques to analyze customer sentiment data on the aforementioned analyzable information. [Explanation of symbols] 【0964】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A means of collecting multiple types of data, including communication data, sales data, and customer data, Means for preprocessing the aforementioned data and converting it into an analyzable format, A means for evaluating and predicting revenue based on the aforementioned preprocessed data, A means for generating an optimal business strategy based on the aforementioned evaluation and prediction results, A means for distributing the generated strategy to an information terminal, Means for collecting and analyzing the results of the implementation of the aforementioned strategy, A system that includes this. [Claim 2] The system according to claim 1, characterized in that the aforementioned business strategy includes sales promotion activities, acquisition of new contracts, and improvement of inventory management. [Claim 3] The system according to claim 1, characterized in that a machine learning algorithm is used on the data in the aforementioned analyzable format.

Images