system

Abstract

Provide a system. 【Solution means】 Means for collecting information from a communication terminal, Means for preprocessing the collected information, Means for predicting future performance based on the preprocessed information, Means for generating an action plan based on the prediction result, Means for providing the generated action plan to the user, Means for collecting the results from the user and optimizing the system, Means for receiving information in real time and presenting an optimal business strategy to store staff using an artificial intelligence model, A system including.

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, revenue management in retail stores has become more complex, and real-time data analysis and rapid strategic planning are required. However, in many stores, manual analysis is still the mainstream, making it difficult to make efficient and effective decisions. To solve this problem, it is essential to introduce a system that can quickly analyze revenue data and propose and execute optimal strategies.

Means for Solving the Problems

[0005] This invention provides a system that preprocesses data collected from stores and uses an AI model to predict sales based on that data. This system includes means for collecting data from a communication device, data preprocessing, prediction, strategy generation, notification, and execution result collection, thereby improving the efficiency of revenue management in stores. Furthermore, a retraining function for the prediction model enables continuous improvement of accuracy and allows for the provision of real-time actionable strategies. This results in efficient revenue management and rapid decision-making.

[0006] "Communication equipment" refers to devices equipped with the function of transmitting data from each store, and specifically plays a role in collecting sales information and inventory status.

[0007] "Data acquisition means" refers to a technical configuration for acquiring data transmitted from a communication device and converting it into a format usable within the system.

[0008] "Preprocessing means" refers to the process of cleaning and correcting collected data to prepare it for analysis.

[0009] "Predictive tools" refer to AI models and algorithms that estimate future sales and revenues using pre-processed data.

[0010] A "strategy proposal generation method" refers to a system that creates specific proposals regarding sales promotion and inventory management in stores based on information provided by a forecasting method.

[0011] "Notification means" refers to the technical means of communicating strategic proposals to users, and in this system, it specifically uses the form of real-time alerts.

[0012] "Execution result collection means" refers to a technical configuration for collecting data on the results of strategies implemented by users and using it for future analysis and improvement.

[0013] The "retraining function" refers to a continuous learning process that improves the accuracy of the AI ​​model based on the collected execution result data. [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 combined with an emotion engine.

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), etc.

[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] To implement the system of this invention, there are three main roles: server, terminal, and user.

[0036] The server centrally manages diverse data collected from all stores via communication devices. This data includes the number of communication contracts, terminal sales, and usage status of optional services at each store. The server acquires this data in real time and stores it in the appropriate database.

[0037] The acquired data first undergoes preprocessing on the server. This preprocessing involves cleaning and correcting the data. For example, missing data is supplemented based on past data, and outliers are corrected to an appropriate range based on other values.

[0038] Next, the pre-processed data is input into the AI ​​model. The server activates this model, which utilizes machine learning techniques, to predict future sales and revenues. The AI ​​model makes predictions based on past data and current trends, indicating the timing and products that are likely to see increased sales in the future.

[0039] Next, the server generates a strategic proposal based on the prediction results. This strategic proposal includes specific action plans, such as which products should be prioritized for sale and what campaigns should be launched.

[0040] The generated strategy proposals are notified to store staff, who are the users, via a terminal. The notification is a real-time alert, which users can review and incorporate into their work. For example, the terminal can support store activities by sending specific instructions to staff, such as "Implement a campaign to boost new terminal sales next week."

[0041] User feedback is sent back to the server via the device. Data such as actual sales performance, campaign effectiveness, and customer reactions are collected and analyzed by the server to help retrain the AI ​​model. This feedback loop allows the system to improve its accuracy daily and develop more effective strategies.

[0042] Through this series of steps, the present invention automates revenue management for each store, enabling efficient and rapid strategic execution.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server connects to the communication devices at each store and collects real-time data on the number of contracts, sales figures, and usage of optional services. This data is processed quickly, providing the foundational information necessary for effective decision-making.

[0046] Step 2:

[0047] The server preprocesses the collected data. This includes data cleaning, imputing missing values, and detecting and correcting outliers. For example, if an unnatural value is detected, it is compared with past data and corrected to an appropriate range.

[0048] Step 3:

[0049] The server inputs pre-processed data into a machine learning algorithm to predict future sales and revenue. The AI ​​model identifies the timing of increases and decreases in sales, taking into account past trends and real-time data.

[0050] Step 4:

[0051] Based on the prediction results, the server generates a sales strategy proposal. This strategy is designed to include methods for focusing sales on specific products, appropriate campaign timing, and inventory management techniques.

[0052] Step 5:

[0053] The terminal notifies store staff, who are the users, of the generated strategy proposals. This notification is in the form of a real-time alert, allowing staff to immediately review the strategy and incorporate it into their work.

[0054] Step 6:

[0055] Users collect the results of their actions according to the strategy and feed them back to the server via their devices. This data includes actual sales, campaign effectiveness, and customer feedback.

[0056] Step 7:

[0057] The server analyzes the collected feedback data and uses it to retrain the AI ​​model. This creates a loop that improves the accuracy of future predictions and strategic proposals.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] Effective information management and operation require the rapid and accurate formulation of strategies based on real-time collected data, and the notification of those strategies in an actionable format. However, existing methods suffer from delays in information processing and notification, as well as insufficient accuracy. This invention aims to improve these problems, streamline the process from information gathering to strategy execution, and optimize revenue management at each level.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for acquiring information from a communication device, means for organizing the acquired information, means for predicting future revenue based on the organized information, means for creating a strategic design using generation technology, means for notifying users of the created strategic design, means for acquiring execution results from users and improving the structure, and means for executing predictions using the generated commands. This enables rapid and highly accurate data processing and strategic planning.

[0063] A "communication device" is a device or a device that has the function of sending and receiving information with other devices or systems.

[0064] "Information" is a general term for data that is collected, managed, and analyzed within a system.

[0065] "Preparation" refers to the act of appropriately processing collected information and transforming it into a format suitable for analysis and prediction.

[0066] "Revenue" refers to the economic gain or projected gain derived from business activities.

[0067] "Generative technology" refers to technologies that automatically create new information or results based on existing data and models.

[0068] "Strategic design" refers to specific policies and action plans designed to achieve a particular objective.

[0069] A "beneficiary" refers to a user of a system or a person who benefits from a system.

[0070] "Notification" refers to the act of notifying or transmitting specific information.

[0071] "Immediate warning" refers to an alert function that provides important information in real time without delay.

[0072] A "command" refers to a set of instructions or prompts generated by a system to trigger a specific action.

[0073] This invention is a system for streamlining store operations, in which three entities—a server, terminals, and users—work together. The server is the central entity that acquires and manages data from the communication devices of each store. The data includes the number of communication contracts, the number of terminals sold, and the usage status of optional services. The server stores this data in a database management system and processes the data using Python and Pandas. The processed data is supplied to a machine learning model utilizing TENSORFLOW® to predict future revenue.

[0074] The terminal is responsible for informing the user of the generated strategy design, providing real-time, immediate warnings. This enables the user to make quick decisions in the field. The user sends their operational results and customer feedback back to the server for further learning and improvement.

[0075] As a concrete example, the server generates a prompt message saying, "Forecast next week's sales and identify the three main products," and inputs it into the TensorFlow model. Based on this prompt message, the system designs a strategy for prioritizing products and provides information to the user in real time. This allows the user to receive specific instructions, such as, "Focus on selling smartphone X next week and run a 20% off campaign on related accessories."

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server retrieves data from the communication device. At this stage, the server receives data such as the number of communication contracts, terminal sales, and usage status of optional services for each store as input data. This data is stored in a database in preparation for subsequent processing. For example, database software is used to save the data as monthly data for each store.

[0079] Step 2:

[0080] The system processes the data acquired by the server. Specifically, it converts the data into a dataframe format using Python and the Pandas library, and imputes missing values ​​with the average of past data. Z-scores are used to detect outliers and correct human errors. The input to this process is the data stored in the aforementioned database, and the output is pre-processed, clean data. For example, if an abnormal sales figure is detected, it is replaced with the average value.

[0081] Step 3:

[0082] The server uses prepared data to predict revenue. This prepared data is input into a generative AI model built with TensorFlow to predict which products and when sales are expected to increase. This process generates prompts such as "Predict next week's sales and identify the top three products." The output provides the prediction results, indicating which products are expected to see increased sales. For example, it can generate a list of products for which demand is predicted to rise.

[0083] Step 4:

[0084] The server creates a strategy design based on the forecast results. It generates specific proposals for products to prioritize selling and campaigns to implement, according to the predicted demand. The input is the forecast results from step 3, and the output is the proposed strategy design. For example, it might formulate a specific strategy such as, "Focus on smartphone X and run a 20% off campaign on related accessories."

[0085] Step 5:

[0086] The terminal notifies the user of the strategic design. The terminal notifies the user of the strategic design as a real-time alert, prompting immediate action. The input is the strategic design draft created in step 4, and the output is the notification received by the user. For example, the terminal may display specific advertising placement instructions to store staff.

[0087] Step 6:

[0088] The user provides feedback on the results of their actions to the server. The user reports actual sales performance and campaign effectiveness, and sends the data back to the server. The user's input is directly incorporated into the server and used to retrain the AI ​​model for the next iteration. For example, the user might input the campaign's sales achievement rate and send it to the server.

[0089] (Application Example 1)

[0090] 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."

[0091] To improve the accuracy of sales strategies in retail stores and enhance performance, real-time data processing and forecasting are necessary. However, existing systems have problems such as insufficient information gathering from stores, which makes strategy formulation and implementation time-consuming and hinders effective business improvement.

[0092] 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.

[0093] In this invention, the server includes means for collecting information from communication terminals, means for pre-processing the collected information, and means for predicting future performance based on the pre-processed information. This enables real-time information reception and the rapid presentation of optimal business strategies using artificial intelligence models.

[0094] A "communication terminal" is an electronic device used to send and receive data, and includes devices such as smartphones and tablets.

[0095] "Information" refers to data collected through communication terminals, such as the number of communication contracts, sales figures, and usage status of optional services.

[0096] "Preprocessing" refers to the process of cleaning and correcting raw data to make it suitable for analysis.

[0097] "Performance" refers to indicators of a store's sales and profits over a specific period, and represents the success of the business.

[0098] "Prediction" is the act of estimating future fluctuations in sales and profits based on past and present information.

[0099] An "action plan" is a specific plan for implementing sales strategies and campaigns that are formulated based on predictions.

[0100] "Provision" refers to the act of informing the store staff, who are the users, of the generated action plan.

[0101] "Optimization" is the process of improving a system's performance and making it function more effectively.

[0102] "Real-time" refers to the property of performing information processing and communication instantly without delay.

[0103] An "artificial intelligence model" is a computational model that uses machine learning algorithms to analyze large amounts of data and perform pattern recognition and prediction.

[0104] The system implementing this invention consists of three components: a server, terminals, and users. The server is responsible for collecting information in real time from the communication terminals of each store and centrally managing it in a database. The collected data is first pre-processed to correct for deficiencies and anomalies before being used for analysis. The pre-processed data is then input into an artificial intelligence model on the server. This model predicts future sales and profits based on past and present data.

[0105] The server generates an optimal action plan based on the prediction results. The generated plan is provided to the store staff (users) via a terminal. This allows users to review and implement sales strategies at the appropriate time. For example, if the AI ​​model predicts that "sales of product A should be intensified next week," users can take immediate action.

[0106] This server and terminal function using specific software. The software used includes a Flask-based web server, which forms the interface for real-time data reception and information provision. Additionally, an artificial intelligence model built using machine learning algorithms is implemented using programming languages ​​such as Python.

[0107] Furthermore, to improve the system's accuracy, the server collects execution results from users and uses them for retraining. This feedback loop allows the artificial intelligence model to continuously improve its performance.

[0108] For example, if sales of a new product B fall below expectations, the system can propose a price discount campaign for product B and instruct the store to rearrange the product's placement, thereby recovering sales in a short period of time.

[0109] An example of a prompt to input into a generating AI model is, "Regarding how to sell new product B, suggest the best strategy to increase sales."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects information in real time from the communication terminals of each store. It receives raw data from the communication terminals as input and stores it in a database. Specifically, it retrieves data from the communication terminals via an API and stores it in the corresponding database table.

[0113] Step 2:

[0114] The server preprocesses the collected data. It uses raw data as input and performs data manipulation such as imputing missing data and correcting outliers. The output is a clean, analyzable dataset. Specifically, it uses libraries like Python's pandas library to correct data inconsistencies.

[0115] Step 3:

[0116] The server inputs pre-processed data into the AI ​​model. Using clean data as input, the model performs data calculations to predict future performance based on past and present data trends. The output includes forecasts for future sales and recommended action options. Specifically, the model performs inference using machine learning libraries such as scikit-learn.

[0117] Step 4:

[0118] The server generates an optimal action plan based on prediction results obtained from the AI ​​model. Using the prediction data as input, it formulates a specific sales strategy that maximizes sales. The output is an actionable plan. Specifically, the strategy is described in natural language and stored in JSON format or another format.

[0119] Step 5:

[0120] The server generates an action plan and notifies store staff via their terminals. The input is the generated strategy plan, and the output is the notification to the staff. Specifically, the system sends real-time alerts through terminal applications such as smartphone apps.

[0121] Step 6:

[0122] The user takes action based on an action plan provided by the server and feeds the results back to the server. The input consists of the actions taken and their results, while the output is data necessary for system improvement. The specific operation involves inputting the results within the application and sending them to the server.

[0123] Step 7:

[0124] The server retrains the AI ​​model based on user feedback. It uses the feedback data as input to update the AI ​​model's training dataset and performs data calculations to improve accuracy. The output is a new, improved AI model. Specifically, it performs a retraining process to update the model to the latest state.

[0125] 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.

[0126] This invention provides a system that combines a server, terminal, user, and emotion engine to improve efficiency in store revenue management.

[0127] The server collects various store data from communication devices. This includes contract numbers, sales figures, and usage of optional services, and is processed in real time. The server preprocesses this data and uses machine learning algorithms to predict future sales. The strategic proposals generated based on these predictions include which products to sell and how, and when to implement campaigns and price adjustments.

[0128] The terminal notifies users of strategic proposals received from the server as real-time alerts. Store staff, who are the users, can then incorporate these notifications into their work. This allows users to efficiently implement strategies based on predictions.

[0129] Furthermore, the system incorporates an emotion engine to collect user feedback. This emotion engine analyzes the emotional nuances of user feedback. For example, it senses how satisfied users are with the strategy and what aspects they are dissatisfied with, and provides this information to the server. This information is then used to customize the strategy proposals.

[0130] Through retraining, the server's AI model improves accuracy and gains a deeper understanding for future predictions and strategy generation. The entire system continuously improves by evaluating how effectively users implemented the suggested strategies and how that resulted in improved revenue.

[0131] Thus, this system encompasses a complete workflow from data collection and analysis to strategic proposal notification, feedback, and retraining. Furthermore, by introducing an emotion engine, it is possible to capture not only numerical data but also emotional nuances, thereby further improving the accuracy and effectiveness of strategic proposals.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server collects revenue-related data from each store via communication devices. This data includes the number of contracts, the number of devices sold, and the usage status of optional services, and is acquired in real time.

[0135] Step 2:

[0136] The server preprocesses the collected data. Specifically, it cleans the data to correct outliers and missing values ​​and converts it into a format that machine learning models can easily handle. This ensures data consistency and accuracy.

[0137] Step 3:

[0138] The server uses pre-processed data to perform predictions with an AI model. The AI ​​model has learned from historical data and can accurately forecast future sales trends and demand. These predictions form the foundation for strategic proposals.

[0139] Step 4:

[0140] The server generates strategic proposals based on the predictions of the AI ​​model. These proposals include measures to prioritize the sale of specific products and campaign plans for acquiring and retaining customers.

[0141] Step 5:

[0142] The terminal notifies the user of strategic proposals provided by the server. The terminal uses real-time alerts to create an environment where users can immediately review and implement the strategies.

[0143] Step 6:

[0144] The user implements the proposed strategy and observes the results. Furthermore, an emotion engine collects emotional responses and feedback on the strategy's implementation and transmits them to the server via the device.

[0145] Step 7:

[0146] The server retrains its AI model using user feedback and analysis results from the emotion engine. This loop improves the model's accuracy, which is then reflected in future predictions. The server continues to improve its system to propose better strategies, taking user emotions into account.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0149] In today's commercial environment, data-driven revenue forecasting and strategic planning are essential for effective store operations. However, traditional methods have limitations in terms of real-time capabilities and accuracy, and optimizing strategies to take into account actual user reactions and emotional feedback is difficult. Furthermore, the process of improving systems based on feedback is often done manually, resulting in a time-consuming and labor-intensive process.

[0150] 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.

[0151] In this invention, the server includes means for acquiring information from a data collection medium, means for organizing the acquired information, and means for estimating future revenue based on the organized information. This makes it possible to perform highly accurate revenue forecasts in real time and to automatically optimize strategies by integrating the emotional responses of users.

[0152] "Information collection media" refers to communication devices and database systems used to obtain necessary data from stores and related facilities.

[0153] "Means of organizing acquired information" refers to data processing processes that convert raw data into a format suitable for analysis and inference, such as data cleansing and transformation.

[0154] "Methods for estimating future revenue based on organized information" refers to technologies that use machine learning and statistical analysis techniques to predict future sales and profits based on past and present information.

[0155] "Means for generating strategies" refers to a process that automatically creates sales strategies and marketing plans based on revenue forecasts.

[0156] "Means of communication to users" refers to a system for notifying users, such as store staff, of the generated strategies in real time, for example, by providing information via digital devices or apps.

[0157] "Means of collecting user feedback and improving the system" refers to the process of collecting the results of strategy implementation and user feedback to help improve the system.

[0158] "Emotional analysis technology" is a technology that analyzes the emotional nuances contained in the feedback provided by users and extracts them as numerical data or information.

[0159] "Using immediate warnings" is a process that displays a warning to immediately attract the user's attention and encourage prompt action when a generated policy is implemented.

[0160] This invention is a system that combines a server, terminal, user, and sentiment analysis technology, with the aim of improving the operational efficiency of stores. The server acquires various store data from information-gathering media. Specifically, it collects information such as the number of contracts, sales figures, and usage status of optional services via communication devices and database systems. This data is then organized by performing data cleansing and transformation using the Python Pandas library.

[0161] Using organized information, the server leverages machine learning frameworks such as TensorFlow to estimate future revenue. By training a Long-Term Short-Term Memory (LSTM) model based on historical sales data, it accurately predicts next month's or quarter's sales. Based on these results, the server uses a generative AI model to generate appropriate strategies. An example of a specific prompt is, "Please suggest the optimal campaign strategy for next month."

[0162] The terminal immediately notifies the user of the measures sent from the server as an alert. This is done using digital devices such as smartphones and tablets to communicate the measures through notifications and voice alerts.

[0163] Users adjust their tasks based on the suggested strategies and provide further feedback. This feedback is analyzed using sentiment analysis technology and provided to the server. This technology quantifies the user's emotional response and uses it to generate future strategies.

[0164] Each element of this system works in conjunction to continuously provide data-driven, rational, and emotionally nuanced strategies. As a result, it enables the creation of an environment that supports improved operational efficiency and maximized profits.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The server retrieves the necessary data from the information gathering medium. Inputs include the number of store contracts, sales figures, and usage status of optional services. The output is raw data. This operation involves accessing a database server and executing SQL queries to aggregate the required information. Specifically, the server runs a scheduled job every hour to retrieve the latest data.

[0168] Step 2:

[0169] The server organizes the acquired raw data. The input is the raw data obtained in step 1, and the output is cleaned and formatted data. This process checks for missing values ​​in the data and formats the data using the Pandas library. It also handles outliers and encodes categorical variables.

[0170] Step 3:

[0171] The server uses formatted data to estimate future revenue. The input is pre-formatted data, and the output is a future prediction. This process uses an LSTM model with TensorFlow. Specifically, it applies the model to the data using a prediction algorithm to forecast next month's sales.

[0172] Step 4:

[0173] The server generates policies based on the prediction results. The input is the prediction results, and the output is a proposal of feasible policies. In this process, the predictive data is input as prompts to the generating AI model, and strategic proposals are generated. As a concrete example, the prompt statement "Please propose the optimal campaign strategy for next month" is used.

[0174] Step 5:

[0175] The terminal immediately notifies the user of the generated policy as an alert. The input is the policy sent from the server, and the output is the notified policy information. Here, the notification system is activated and sends an alert. The terminal receives the policy information and notifies the user in real time with display and audio alerts.

[0176] Step 6:

[0177] The user implements the proposed strategy and provides feedback. The input is strategy information from the terminal, and the output is feedback information to the system. The user enters the results and impressions of the implemented strategy into a feedback form and sends it to the server.

[0178] Step 7:

[0179] The server receives feedback information and uses sentiment analysis technology. The input is user feedback, and the output is analyzed sentiment data. A sentiment text analysis tool is used to quantify emotional elements such as positive and negative. The results are saved as data for improving future strategies.

[0180] (Application Example 2)

[0181] 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".

[0182] In modern brick-and-mortar stores, real-time data processing and rapid feedback to employees are essential for improving the efficiency of revenue management. However, current systems have a fragmented process from data collection to analysis and feedback, and lack effective means of utilizing emotional feedback from customers. As a result, there are limitations in improving predictive accuracy and the quality of strategic proposals.

[0183] 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.

[0184] In this invention, the server includes means for collecting data from a communication device, means for preprocessing the collected data, means for predicting future sales based on the preprocessed data, means for generating strategic proposals based on the prediction results, means for notifying the user of the generated strategic proposals, means for analyzing the user's emotional feedback, and means for collecting execution results from the user and improving the system based on the emotional analysis results. This enables the generation of strategic proposals that take user emotions into consideration and continuous system improvement.

[0185] A "communication device" is a device used to send and receive information and to collect data.

[0186] "Data preprocessing" is the process of organizing and processing collected raw data and converting it into a format that can be used in the next step.

[0187] "Sales forecasting method" refers to an algorithm or model that uses pre-processed data to predict future sales.

[0188] A "strategy proposal generation method" is a system or process for proposing efficient sales methods and measures based on sales forecast results.

[0189] A "notification method" is a means of informing users of the generated strategy draft, and typically includes a function to transmit information in real time.

[0190] "Emotional feedback analysis methods" refer to technologies for analyzing emotional responses from users and understanding them in the form of numbers, categories, and other numerical data.

[0191] The "implementation result collection method" is a function that collects the results of users executing strategic proposals and uses them to further improve the system.

[0192] The system implementing this invention mainly consists of a server, terminals, and users. The server collects various data using communication devices installed in stores, including sales figures and usage status of optional services. This data is collected in real time and preprocessed. Preprocessing includes data cleaning and normalization, and these tasks are usually performed using programming languages ​​such as Python and libraries such as Pandas.

[0193] The preprocessed data is input into a model that predicts future sales using machine learning libraries such as TensorFlow and PyTorch. Based on this data, the generative AI model generates strategic proposals, such as which products to sell, how to sell them, and the optimal timing for pricing and campaigns.

[0194] The terminal receives strategic proposals generated from the server in real time and notifies store staff. These notifications are sent via smartphones and tablets, allowing staff to optimize their operations based on the information. An emotion engine is also integrated into the terminal, emotionally analyzing staff feedback. This includes information such as the staff's level of satisfaction with the strategic proposals.

[0195] Users (store staff) send feedback through an emotion engine, which is then analyzed by the server. This analysis is used to improve the system and to retrain it to enhance the accuracy of future sales forecasts and strategic proposals.

[0196] As a concrete example, there is a case where store staff received a strategic proposal to identify the optimal timing for launching seasonal product promotions, and as a result of implementing it, sales increased significantly. In this case, based on the staff's feedback, a prompt message was sent to the server stating, "Please provide a strategic proposal to optimize the timing of seasonal product promotions. Please provide specific steps based on predictions that take into account past data and current trends."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server collects various store data in real time from communication devices. Input data includes sales figures and usage status of optional services. The collected data is stored on the server as raw data.

[0200] Step 2:

[0201] The server preprocesses the collected raw data. The raw data collected in step 1 is used as input. Specifically, the data is cleaned (missing values ​​are imputed, outliers are removed) and normalized to format it in a way that is suitable for the predictive model. The output is the preprocessed data.

[0202] Step 3:

[0203] The server predicts future sales based on pre-processed data. The input is the pre-processed data obtained in step 2. A machine learning model using TensorFlow or PyTorch processes the data and outputs the prediction results. The output is the future sales forecast.

[0204] Step 4:

[0205] The server generates strategic proposals based on sales forecasts. The forecast results obtained in step 3 are used as input. The generating AI model creates strategic proposals that include which products to sell, how to sell them, price adjustments, and campaign timing. The output is the generated strategic proposal.

[0206] Step 5:

[0207] The terminal notifies the user in real time of the strategy proposal received from the server. The strategy proposal generated in step 4 is used as input. Alerts are displayed on the store staff's smartphones or tablets, providing actionable instructions. The output is the content of the notification to the user.

[0208] Step 6:

[0209] The user executes the proposed strategy and provides the execution results and feedback through the terminal. The input is the proposed strategy received in step 5 and the execution results at the store. The terminal's emotion engine emotionally analyzes the feedback. The output is the execution results and emotional feedback sent to the server.

[0210] Step 7:

[0211] The server improves the system based on the execution results and sentiment feedback collected from the user. The information collected in step 6 is used as input. The system improves the accuracy of the predictive model through retraining. The output is the improved predictive model for the next prediction.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] To implement the system of this invention, there are three main roles: server, terminal, and user.

[0229] The server centrally manages diverse data collected from all stores via communication devices. This data includes the number of communication contracts, terminal sales, and usage status of optional services at each store. The server acquires this data in real time and stores it in the appropriate database.

[0230] The acquired data first undergoes preprocessing on the server. This preprocessing involves cleaning and correcting the data. For example, missing data is supplemented based on past data, and outliers are corrected to an appropriate range based on other values.

[0231] Next, the pre-processed data is input into the AI ​​model. The server activates this model, which utilizes machine learning techniques, to predict future sales and revenues. The AI ​​model makes predictions based on past data and current trends, indicating the timing and products that are likely to see increased sales in the future.

[0232] Next, the server generates a strategic proposal based on the prediction results. This strategic proposal includes specific action plans, such as which products should be prioritized for sale and what campaigns should be launched.

[0233] The generated strategy proposals are notified to store staff, who are the users, via a terminal. The notification is a real-time alert, which users can review and incorporate into their work. For example, the terminal can support store activities by sending specific instructions to staff, such as "Implement a campaign to boost new terminal sales next week."

[0234] User feedback is sent back to the server via the device. Data such as actual sales performance, campaign effectiveness, and customer reactions are collected and analyzed by the server to help retrain the AI ​​model. This feedback loop allows the system to improve its accuracy daily and develop more effective strategies.

[0235] Through this series of steps, the present invention automates revenue management for each store, enabling efficient and rapid strategic execution.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server connects to the communication devices at each store and collects real-time data on the number of contracts, sales figures, and usage of optional services. This data is processed quickly, providing the foundational information necessary for effective decision-making.

[0239] Step 2:

[0240] The server preprocesses the collected data. This includes data cleaning, imputing missing values, and detecting and correcting outliers. For example, if an unnatural value is detected, it is compared with past data and corrected to an appropriate range.

[0241] Step 3:

[0242] The server inputs pre-processed data into a machine learning algorithm to predict future sales and revenue. The AI ​​model identifies the timing of increases and decreases in sales, taking into account past trends and real-time data.

[0243] Step 4:

[0244] Based on the prediction results, the server generates a sales strategy proposal. This strategy is designed to include methods for focusing sales on specific products, appropriate campaign timing, and inventory management techniques.

[0245] Step 5:

[0246] The terminal notifies store staff, who are the users, of the generated strategy proposals. This notification is in the form of a real-time alert, allowing staff to immediately review the strategy and incorporate it into their work.

[0247] Step 6:

[0248] Users collect the results of their actions according to the strategy and feed them back to the server via their devices. This data includes actual sales, campaign effectiveness, and customer feedback.

[0249] Step 7:

[0250] The server analyzes the collected feedback data and uses it to retrain the AI ​​model. This creates a loop that improves the accuracy of future predictions and strategic proposals.

[0251] (Example 1)

[0252] 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."

[0253] Effective information management and operation require the rapid and accurate formulation of strategies based on real-time collected data, and the notification of those strategies in an actionable format. However, existing methods suffer from delays in information processing and notification, as well as insufficient accuracy. This invention aims to improve these problems, streamline the process from information gathering to strategy execution, and optimize revenue management at each level.

[0254] 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.

[0255] In this invention, the server includes means for acquiring information from a communication device, means for organizing the acquired information, means for predicting future revenue based on the organized information, means for creating a strategic design using generation technology, means for notifying users of the created strategic design, means for acquiring execution results from users and improving the structure, and means for executing predictions using the generated commands. This enables rapid and highly accurate data processing and strategic planning.

[0256] A "communication device" is a device or a device that has the function of sending and receiving information with other devices or systems.

[0257] "Information" is a general term for data that is collected, managed, and analyzed within a system.

[0258] "Preparation" refers to the act of appropriately processing collected information and transforming it into a format suitable for analysis and prediction.

[0259] "Revenue" refers to the economic gain or projected gain derived from business activities.

[0260] "Generative technology" refers to technologies that automatically create new information or results based on existing data and models.

[0261] "Strategic design" refers to specific policies and action plans formulated to achieve a particular objective.

[0262] A "beneficiary" refers to a user of a system or a person who benefits from a system.

[0263] "Notification" refers to the act of notifying or transmitting specific information.

[0264] "Immediate warning" refers to an alert function that provides important information in real time without delay.

[0265] A "command" refers to a set of instructions or prompts generated by a system to trigger a specific action.

[0266] This invention is a system for streamlining store operations, in which three entities—a server, terminals, and users—work together. The server is the central entity that acquires and manages data from the communication devices of each store. The data includes the number of communication contracts, the number of terminals sold, and the usage status of optional services. The server stores this data in a database management system and processes the data using Python and Pandas. The processed data is then supplied to a machine learning model utilizing TensorFlow to predict future revenue.

[0267] The terminal is responsible for informing the user of the generated strategy design, providing real-time, immediate warnings. This enables the user to make quick decisions in the field. The user sends their operational results and customer feedback back to the server for further learning and improvement.

[0268] As a concrete example, the server generates a prompt message saying, "Forecast next week's sales and identify the three main products," and inputs it into the TensorFlow model. Based on this prompt message, the system designs a strategy for prioritizing products and provides information to the user in real time. This allows the user to receive specific instructions, such as, "Focus on selling smartphone X next week and run a 20% off campaign on related accessories."

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] The server retrieves data from the communication device. At this stage, the server receives data such as the number of communication contracts, terminal sales, and usage status of optional services for each store as input data. This data is stored in a database in preparation for subsequent processing. For example, database software is used to save the data as monthly data for each store.

[0272] Step 2:

[0273] The system processes the data acquired by the server. Specifically, it converts the data into a dataframe format using Python and the Pandas library, and imputes missing values ​​with the average of past data. Z-scores are used to detect outliers and correct human errors. The input to this process is the data stored in the aforementioned database, and the output is pre-processed, clean data. For example, if an abnormal sales figure is detected, it is replaced with the average value.

[0274] Step 3:

[0275] The server uses prepared data to predict revenue. This prepared data is input into a generative AI model built with TensorFlow to predict which products and when sales are expected to increase. This process generates prompts such as "Predict next week's sales and identify the top three products." The output provides the prediction results, indicating which products are expected to see increased sales. For example, it can generate a list of products for which demand is predicted to rise.

[0276] Step 4:

[0277] The server creates a strategy design based on the forecast results. It generates specific proposals for products to prioritize selling and campaigns to implement, according to the predicted demand. The input is the forecast results from step 3, and the output is the proposed strategy design. For example, it might formulate a specific strategy such as, "Focus on smartphone X and run a 20% off campaign on related accessories."

[0278] Step 5:

[0279] The terminal notifies the user of the strategic design. The terminal notifies the user of the strategic design as a real-time alert, prompting immediate action. The input is the strategic design draft created in step 4, and the output is the notification received by the user. For example, the terminal may display specific advertising placement instructions to store staff.

[0280] Step 6:

[0281] The user provides feedback on the results of their actions to the server. The user reports actual sales performance and campaign effectiveness, and sends the data back to the server. The user's input is directly incorporated into the server and used to retrain the AI ​​model for the next iteration. For example, the user might input the campaign's sales achievement rate and send it to the server.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0284] In order to improve the accuracy of sales strategies in retail stores and enhance business performance, real-time data processing and prediction are necessary. However, existing systems have problems such as insufficient information collection from stores, time-consuming strategy formulation and implementation, and difficulty in effective business improvement.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes means for collecting information from communication terminals, means for preprocessing the collected information, and means for predicting future performance based on the preprocessed information. This enables real-time information reception and rapid presentation of optimal business strategies using artificial intelligence models.

[0287] A "communication terminal" is an electronic device for transmitting and receiving data, including devices such as smartphones and tablets.

[0288] "Information" refers to data such as the number of communication contracts, sales volume, and usage status of optional services collected through communication terminals.

[0289] "Preprocessing" is a process of cleaning and correcting raw data to make it analyzable.

[0290] "Performance" is an indicator of a store's sales and revenue during a specific period and indicates the results of management.

[0291] "Prediction" is an act of estimating future sales and revenue fluctuations based on past and current information.

[0292] An "action plan" is a specific implementation plan for sales strategies and campaigns formulated based on predictions.

[0293] "Provision" refers to the act of informing the store staff, who are the users, of the generated action plan.

[0294] "Optimization" is the process of improving a system's performance and making it function more effectively.

[0295] "Real-time" refers to the property of performing information processing and communication instantly without delay.

[0296] An "artificial intelligence model" is a computational model that uses machine learning algorithms to analyze large amounts of data and perform pattern recognition and prediction.

[0297] The system implementing this invention consists of three components: a server, terminals, and users. The server is responsible for collecting information in real time from the communication terminals of each store and centrally managing it in a database. The collected data is first pre-processed to correct for deficiencies and anomalies before being used for analysis. The pre-processed data is then input into an artificial intelligence model on the server. This model predicts future sales and profits based on past and present data.

[0298] The server generates an optimal action plan based on the prediction results. The generated plan is provided to the store staff (users) via a terminal. This allows users to review and implement sales strategies at the appropriate time. For example, if the AI ​​model predicts that "sales of product A should be intensified next week," users can take immediate action.

[0299] This server and terminal function using specific software. The software used includes a Flask-based web server, which forms the interface for real-time data reception and information provision. Additionally, an artificial intelligence model built using machine learning algorithms is implemented using programming languages ​​such as Python.

[0300] Furthermore, to improve the accuracy of the system, the server collects the execution results from the user and performs re-learning. Through this feedback loop, the AI model can continuously improve its performance.

[0301] As a specific example, when the sales of the new product B are lower than expected, the system can propose a price discount campaign for product B and instruct to change the product placement at the storefront, thereby recovering the sales in a short period.

[0302] As an example of the prompt sentence input to the generative AI model, "Regarding the method of selling the new product B, propose the optimal strategy to increase sales." can be cited.

[0303] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0304] Step 1:

[0305] The server collects information from the communication terminals of each store in real time. It receives raw data from the communication terminals as input and stores this in the database. As a specific operation, it obtains data from the communication terminals via the API and stores it in the corresponding database table.

[0306] Step 2:

[0307] The server performs preprocessing on the collected data. Using the raw data as input, it conducts data processing such as complementing missing data and correcting outliers. As output, it obtains a clean and analyzable dataset. As a specific operation, it uses libraries such as the pandas library in Python to correct data inconsistencies.

[0308] Step 3:

[0309] The server inputs pre-processed data into the AI ​​model. Using clean data as input, the model performs data calculations to predict future performance based on past and present data trends. The output includes forecasts for future sales and recommended action options. Specifically, the model performs inference using machine learning libraries such as scikit-learn.

[0310] Step 4:

[0311] The server generates an optimal action plan based on prediction results obtained from the AI ​​model. Using the prediction data as input, it formulates a specific sales strategy that maximizes sales. The output is an actionable plan. Specifically, the strategy is described in natural language and stored in JSON format or another format.

[0312] Step 5:

[0313] The server generates an action plan and notifies store staff via their terminals. The input is the generated strategy plan, and the output is the notification to the staff. Specifically, the system sends real-time alerts through terminal applications such as smartphone apps.

[0314] Step 6:

[0315] The user takes action based on an action plan provided by the server and feeds the results back to the server. The input consists of the actions taken and their results, while the output is data necessary for system improvement. The specific operation involves inputting the results within the application and sending them to the server.

[0316] Step 7:

[0317] The server retrains the AI ​​model based on user feedback. It uses the feedback data as input to update the AI ​​model's training dataset and performs data calculations to improve accuracy. The output is a new, improved AI model. Specifically, it performs a retraining process to update the model to the latest state.

[0318] 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.

[0319] This invention provides a system that combines a server, terminal, user, and emotion engine to improve efficiency in store revenue management.

[0320] The server collects various store data from communication devices. This includes contract numbers, sales figures, and usage of optional services, and is processed in real time. The server preprocesses this data and uses machine learning algorithms to predict future sales. The strategic proposals generated based on these predictions include which products to sell and how, and when to implement campaigns and price adjustments.

[0321] The terminal notifies users of strategic proposals received from the server as real-time alerts. Store staff, who are the users, can then incorporate these notifications into their work. This allows users to efficiently implement strategies based on predictions.

[0322] Furthermore, the system incorporates an emotion engine to collect user feedback. This emotion engine analyzes the emotional nuances of user feedback. For example, it senses how satisfied users are with the strategy and what aspects they are dissatisfied with, and provides this information to the server. This information is then used to customize the strategy proposals.

[0323] Through retraining, the server's AI model improves accuracy and gains a deeper understanding for future predictions and strategy generation. The entire system continuously improves by evaluating how effectively users implemented the suggested strategies and how that resulted in improved revenue.

[0324] Thus, this system encompasses a complete workflow from data collection and analysis to strategic proposal notification, feedback, and retraining. Furthermore, by introducing an emotion engine, it is possible to capture not only numerical data but also emotional nuances, thereby further improving the accuracy and effectiveness of strategic proposals.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The server collects revenue-related data from each store via communication devices. This data includes the number of contracts, the number of devices sold, and the usage status of optional services, and is acquired in real time.

[0328] Step 2:

[0329] The server preprocesses the collected data. Specifically, it cleans the data to correct outliers and missing values ​​and converts it into a format that machine learning models can easily handle. This ensures data consistency and accuracy.

[0330] Step 3:

[0331] The server uses pre-processed data to perform predictions with an AI model. The AI ​​model has learned from historical data and can accurately forecast future sales trends and demand. These predictions form the foundation for strategic proposals.

[0332] Step 4:

[0333] The server generates strategic proposals based on the predictions of the AI ​​model. These proposals include measures to prioritize the sale of specific products and campaign plans for acquiring and retaining customers.

[0334] Step 5:

[0335] The terminal notifies the user of strategic proposals provided by the server. The terminal uses real-time alerts to create an environment where users can immediately review and implement the strategies.

[0336] Step 6:

[0337] The user implements the proposed strategy and observes the results. Furthermore, an emotion engine collects emotional responses and feedback on the strategy's implementation and transmits them to the server via the device.

[0338] Step 7:

[0339] The server retrains its AI model using user feedback and analysis results from the emotion engine. This loop improves the model's accuracy, which is then reflected in future predictions. The server continues to improve its system to propose better strategies, taking user emotions into account.

[0340] (Example 2)

[0341] 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".

[0342] In today's commercial environment, data-driven revenue forecasting and strategic planning are essential for effective store operations. However, traditional methods have limitations in terms of real-time capabilities and accuracy, and optimizing strategies to take into account actual user reactions and emotional feedback is difficult. Furthermore, the process of improving systems based on feedback is often done manually, resulting in a time-consuming and labor-intensive process.

[0343] 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.

[0344] In this invention, the server includes means for acquiring information from a data collection medium, means for organizing the acquired information, and means for estimating future revenue based on the organized information. This makes it possible to perform highly accurate revenue forecasts in real time and to automatically optimize strategies by integrating the emotional responses of users.

[0345] "Information collection media" refers to communication devices and database systems used to obtain necessary data from stores and related facilities.

[0346] "Means of organizing acquired information" refers to data processing processes that convert raw data into a format suitable for analysis and inference, such as data cleansing and transformation.

[0347] "Methods for estimating future revenue based on organized information" refers to technologies that use machine learning and statistical analysis techniques to predict future sales and profits based on past and present information.

[0348] "Means for generating strategies" refers to a process that automatically creates sales strategies and marketing plans based on revenue forecasts.

[0349] "Means of communication to users" refers to a system for notifying users, such as store staff, of the generated strategies in real time, for example, by providing information via digital devices or apps.

[0350] "Means of collecting user feedback and improving the system" refers to the process of collecting the results of strategy implementation and user feedback to help improve the system.

[0351] "Emotional analysis technology" is a technology that analyzes the emotional nuances contained in the feedback provided by users and extracts them as numerical data or information.

[0352] "Using immediate warnings" is a process that displays warnings to immediately attract the user's attention and encourage prompt action when a generated policy is implemented.

[0353] This invention is a system that combines a server, terminal, user, and sentiment analysis technology, with the aim of improving the operational efficiency of stores. The server acquires various store data from information-gathering media. Specifically, it collects information such as the number of contracts, sales figures, and usage status of optional services via communication devices and database systems. This data is then organized by performing data cleansing and transformation using the Python Pandas library.

[0354] Using organized information, the server leverages machine learning frameworks such as TensorFlow to estimate future revenue. By training a Long-Term Short-Term Memory (LSTM) model based on historical sales data, it accurately predicts next month's or quarter's sales. Based on these results, the server uses a generative AI model to generate appropriate strategies. An example of a specific prompt is, "Please suggest the optimal campaign strategy for next month."

[0355] The terminal immediately notifies the user of the measures sent from the server as an alert. This is done using digital devices such as smartphones and tablets to communicate the measures through notifications and voice alerts.

[0356] Users adjust their tasks based on the suggested strategies and provide further feedback. This feedback is analyzed using sentiment analysis technology and provided to the server. This technology quantifies the user's emotional response and uses it to generate future strategies.

[0357] Each element of this system works in conjunction to continuously provide data-driven, rational, and emotionally nuanced strategies. As a result, it enables the creation of an environment that supports improved operational efficiency and maximized profits.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The server retrieves the necessary data from the information gathering medium. Inputs include the number of store contracts, sales figures, and usage status of optional services. The output is raw data. This operation involves accessing a database server and executing SQL queries to aggregate the required information. Specifically, the server runs a scheduled job every hour to retrieve the latest data.

[0361] Step 2:

[0362] The server organizes the acquired raw data. The input is the raw data obtained in step 1, and the output is cleaned and formatted data. This process checks for missing values ​​in the data and formats the data using the Pandas library. It also handles outliers and encodes categorical variables.

[0363] Step 3:

[0364] The server uses formatted data to estimate future revenue. The input is pre-formatted data, and the output is a future prediction. This process uses an LSTM model with TensorFlow. Specifically, it applies the model to the data using a prediction algorithm to forecast next month's sales.

[0365] Step 4:

[0366] The server generates policies based on the prediction results. The input is the prediction results, and the output is a proposal of feasible policies. In this process, the predictive data is input as prompts to the generating AI model, and strategic proposals are generated. As a concrete example, the prompt statement "Please propose the optimal campaign strategy for next month" is used.

[0367] Step 5:

[0368] The terminal immediately notifies the user of the generated policy as an alert. The input is the policy sent from the server, and the output is the notified policy information. Here, the notification system is activated and sends an alert. The terminal receives the policy information and notifies the user in real time with display and audio alerts.

[0369] Step 6:

[0370] The user implements the proposed strategy and provides feedback. The input is strategy information from the terminal, and the output is feedback information to the system. The user enters the results and impressions of the implemented strategy into a feedback form and sends it to the server.

[0371] Step 7:

[0372] The server receives feedback information and uses sentiment analysis technology. The input is user feedback, and the output is analyzed sentiment data. A sentiment text analysis tool is used to quantify emotional elements such as positive and negative. The results are saved as data for improving future strategies.

[0373] (Application Example 2)

[0374] 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 as the "terminal".

[0375] In modern brick-and-mortar stores, real-time data processing and rapid feedback to employees are essential for improving the efficiency of revenue management. However, current systems have a fragmented process from data collection to analysis and feedback, and lack effective means of utilizing emotional feedback from customers. As a result, there are limitations in improving predictive accuracy and the quality of strategic proposals.

[0376] 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.

[0377] In this invention, the server includes means for collecting data from a communication device, means for preprocessing the collected data, means for predicting future sales based on the preprocessed data, means for generating strategic proposals based on the prediction results, means for notifying the user of the generated strategic proposals, means for analyzing the user's emotional feedback, and means for collecting execution results from the user and improving the system based on the emotional analysis results. This enables the generation of strategic proposals that take user emotions into consideration and continuous system improvement.

[0378] A "communication device" is a device used to send and receive information and to collect data.

[0379] "Data preprocessing" is the process of organizing and processing collected raw data and converting it into a format that can be used in the next step.

[0380] "Sales forecasting method" refers to an algorithm or model that uses pre-processed data to predict future sales.

[0381] A "strategy proposal generation method" is a system or process for proposing efficient sales methods and measures based on sales forecast results.

[0382] A "notification method" is a means of informing users of the generated strategy draft, and typically includes a function to transmit information in real time.

[0383] "Emotional feedback analysis methods" refer to technologies for analyzing emotional responses from users and understanding them in the form of numbers, categories, and other numerical data.

[0384] The "implementation result collection method" is a function that collects the results of users executing strategic proposals and uses them to further improve the system.

[0385] The system implementing this invention mainly consists of a server, terminals, and users. The server collects various data using communication devices installed in stores, including sales figures and usage status of optional services. This data is collected in real time and preprocessed. Preprocessing includes data cleaning and normalization, and these tasks are usually performed using programming languages ​​such as Python and libraries such as Pandas.

[0386] The preprocessed data is input into a model that predicts future sales using machine learning libraries such as TensorFlow and PyTorch. Based on this data, the generative AI model generates strategic proposals, such as which products to sell, how to sell them, and the optimal timing for pricing and campaigns.

[0387] The terminal receives strategic proposals generated from the server in real time and notifies store staff. These notifications are sent via smartphones and tablets, allowing staff to optimize their operations based on the information. An emotion engine is also integrated into the terminal, emotionally analyzing staff feedback. This includes information such as the staff's level of satisfaction with the strategic proposals.

[0388] Users (store staff) send feedback through an emotion engine, which is then analyzed by the server. This analysis is used to improve the system and to retrain it to enhance the accuracy of future sales forecasts and strategic proposals.

[0389] As a concrete example, there is a case where store staff received a strategic proposal to identify the optimal timing for launching seasonal product promotions, and as a result of implementing it, sales increased significantly. In this case, based on the staff's feedback, a prompt message was sent to the server stating, "Please provide a strategic proposal to optimize the timing of seasonal product promotions. Please provide specific steps based on predictions that take into account past data and current trends."

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The server collects various store data in real time from communication devices. Input data includes sales figures and usage status of optional services. The collected data is stored on the server as raw data.

[0393] Step 2:

[0394] The server preprocesses the collected raw data. The raw data collected in step 1 is used as input. Specifically, the data is cleaned (missing values ​​are imputed, outliers are removed) and normalized to format it in a way that is suitable for the predictive model. The output is the preprocessed data.

[0395] Step 3:

[0396] The server predicts future sales based on pre-processed data. The input is the pre-processed data obtained in step 2. A machine learning model using TensorFlow or PyTorch processes the data and outputs the prediction results. The output is the future sales forecast.

[0397] Step 4:

[0398] The server generates strategic proposals based on sales forecasts. The forecast results obtained in step 3 are used as input. The generating AI model creates strategic proposals that include which products to sell, how to sell them, price adjustments, and campaign timing. The output is the generated strategic proposal.

[0399] Step 5:

[0400] The terminal notifies the user in real time of the strategy proposal received from the server. The strategy proposal generated in step 4 is used as input. Alerts are displayed on the store staff's smartphones or tablets, providing actionable instructions. The output is the content of the notification to the user.

[0401] Step 6:

[0402] The user executes the proposed strategy and provides the execution results and feedback through the terminal. The input is the proposed strategy received in step 5 and the execution results at the store. The terminal's emotion engine emotionally analyzes the feedback. The output is the execution results and emotional feedback sent to the server.

[0403] Step 7:

[0404] The server improves the system based on the execution results and sentiment feedback collected from the user. The information collected in step 6 is used as input. The system improves the accuracy of the predictive model through retraining. The output is the improved predictive model for the next prediction.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] [Third Embodiment]

[0409] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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".

[0421] To implement the system of this invention, there are three main roles: server, terminal, and user.

[0422] The server centrally manages diverse data collected from all stores via communication devices. This data includes the number of communication contracts, terminal sales, and usage status of optional services at each store. The server acquires this data in real time and stores it in the appropriate database.

[0423] The acquired data first undergoes preprocessing on the server. This preprocessing involves cleaning and correcting the data. For example, missing data is supplemented based on past data, and outliers are corrected to an appropriate range based on other values.

[0424] Next, the pre-processed data is input into the AI ​​model. The server activates this model, which utilizes machine learning techniques, to predict future sales and revenues. The AI ​​model makes predictions based on past data and current trends, indicating the timing and products that are likely to see increased sales in the future.

[0425] Next, the server generates a strategic proposal based on the prediction results. This strategic proposal includes specific action plans, such as which products should be prioritized for sale and what campaigns should be launched.

[0426] The generated strategy proposals are notified to store staff, who are the users, via a terminal. The notification is a real-time alert, which users can review and incorporate into their work. For example, the terminal can support store activities by sending specific instructions to staff, such as "Implement a campaign to boost new terminal sales next week."

[0427] User feedback is sent back to the server via the device. Data such as actual sales performance, campaign effectiveness, and customer reactions are collected and analyzed by the server to help retrain the AI ​​model. This feedback loop allows the system to improve its accuracy daily and develop more effective strategies.

[0428] Through this series of steps, the present invention automates revenue management for each store, enabling efficient and rapid strategic execution.

[0429] The following describes the processing flow.

[0430] Step 1:

[0431] The server connects to the communication devices at each store and collects real-time data on the number of contracts, sales figures, and usage of optional services. This data is processed quickly, providing the foundational information necessary for effective decision-making.

[0432] Step 2:

[0433] The server preprocesses the collected data. This includes data cleaning, imputing missing values, and detecting and correcting outliers. For example, if an unnatural value is detected, it is compared with past data and corrected to an appropriate range.

[0434] Step 3:

[0435] The server inputs pre-processed data into a machine learning algorithm to predict future sales and revenue. The AI ​​model identifies the timing of increases and decreases in sales, taking into account past trends and real-time data.

[0436] Step 4:

[0437] Based on the prediction results, the server generates a sales strategy proposal. This strategy is designed to include methods for focusing sales on specific products, appropriate campaign timing, and inventory management techniques.

[0438] Step 5:

[0439] The terminal notifies store staff, who are the users, of the generated strategy proposals. This notification is in the form of a real-time alert, allowing staff to immediately review the strategy and incorporate it into their work.

[0440] Step 6:

[0441] Users collect the results of their actions according to the strategy and feed them back to the server via their devices. This data includes actual sales, campaign effectiveness, and customer feedback.

[0442] Step 7:

[0443] The server analyzes the collected feedback data and uses it to retrain the AI ​​model. This creates a loop that improves the accuracy of future predictions and strategic proposals.

[0444] (Example 1)

[0445] 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."

[0446] Effective information management and operation require the rapid and accurate formulation of strategies based on real-time collected data, and the notification of those strategies in an actionable format. However, existing methods suffer from delays in information processing and notification, as well as insufficient accuracy. This invention aims to improve these problems, streamline the process from information gathering to strategy execution, and optimize revenue management at each level.

[0447] 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.

[0448] In this invention, the server includes means for acquiring information from a communication device, means for organizing the acquired information, means for predicting future revenue based on the organized information, means for creating a strategic design using generation technology, means for notifying users of the created strategic design, means for acquiring execution results from users and improving the structure, and means for executing predictions using the generated commands. This enables rapid and highly accurate data processing and strategic planning.

[0449] A "communication device" is a device or a device that has the function of sending and receiving information with other devices or systems.

[0450] "Information" is a general term for data that is collected, managed, and analyzed within a system.

[0451] "Preparation" refers to the act of appropriately processing collected information and transforming it into a format suitable for analysis and prediction.

[0452] "Revenue" refers to the economic gain or projected gain derived from business activities.

[0453] "Generative technology" refers to technologies that automatically create new information or results based on existing data and models.

[0454] "Strategic design" refers to specific policies and action plans formulated to achieve a particular objective.

[0455] A "beneficiary" refers to a user of a system or a person who benefits from a system.

[0456] "Notification" refers to the act of notifying or transmitting specific information.

[0457] "Immediate warning" refers to an alert function that provides important information in real time without delay.

[0458] A "command" refers to a set of instructions or prompts generated by a system to trigger a specific action.

[0459] This invention is a system for streamlining store operations, in which three entities—a server, terminals, and users—work together. The server is the central entity that acquires and manages data from the communication devices of each store. The data includes the number of communication contracts, the number of terminals sold, and the usage status of optional services. The server stores this data in a database management system and processes the data using Python and Pandas. The processed data is then supplied to a machine learning model utilizing TensorFlow to predict future revenue.

[0460] The terminal is responsible for informing the user of the generated strategy design, providing real-time, immediate warnings. This enables the user to make quick decisions in the field. The user sends their operational results and customer feedback back to the server for further learning and improvement.

[0461] As a concrete example, the server generates a prompt message saying, "Forecast next week's sales and identify the three main products," and inputs it into the TensorFlow model. Based on this prompt message, the system designs a strategy for prioritizing products and provides information to the user in real time. This allows the user to receive specific instructions, such as, "Focus on selling smartphone X next week and run a 20% off campaign on related accessories."

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The server retrieves data from the communication device. At this stage, the server receives data such as the number of communication contracts, terminal sales, and usage status of optional services for each store as input data. This data is stored in a database in preparation for subsequent processing. For example, database software is used to save the data as monthly data for each store.

[0465] Step 2:

[0466] The system processes the data acquired by the server. Specifically, it converts the data into a dataframe format using Python and the Pandas library, and imputes missing values ​​with the average of past data. Z-scores are used to detect outliers and correct human errors. The input to this process is the data stored in the aforementioned database, and the output is pre-processed, clean data. For example, if an abnormal sales figure is detected, it is replaced with the average value.

[0467] Step 3:

[0468] The server uses prepared data to predict revenue. This prepared data is input into a generative AI model built with TensorFlow to predict which products and when sales are expected to increase. This process generates prompts such as "Predict next week's sales and identify the top three products." The output provides the prediction results, indicating which products are expected to see increased sales. For example, it can generate a list of products for which demand is predicted to rise.

[0469] Step 4:

[0470] The server creates a strategy design based on the forecast results. It generates specific proposals for products to prioritize selling and campaigns to implement, according to the predicted demand. The input is the forecast results from step 3, and the output is the proposed strategy design. For example, it might formulate a specific strategy such as, "Focus on smartphone X and run a 20% off campaign on related accessories."

[0471] Step 5:

[0472] The terminal notifies the user of the strategic design. The terminal notifies the user of the strategic design as a real-time alert, prompting immediate action. The input is the strategic design draft created in step 4, and the output is the notification received by the user. For example, the terminal may display specific advertising placement instructions to store staff.

[0473] Step 6:

[0474] The user provides feedback on the results of their actions to the server. The user reports actual sales performance and campaign effectiveness, and sends the data back to the server. The user's input is directly incorporated into the server and used to retrain the AI ​​model for the next iteration. For example, the user might input the campaign's sales achievement rate and send it to the server.

[0475] (Application Example 1)

[0476] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0477] To improve the accuracy of sales strategies in retail stores and enhance performance, real-time data processing and forecasting are necessary. However, existing systems have problems such as insufficient information gathering from stores, which makes strategy formulation and implementation time-consuming and hinders effective business improvement.

[0478] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0479] In this invention, the server includes means for collecting information from communication terminals, means for pre-processing the collected information, and means for predicting future performance based on the pre-processed information. This enables real-time information reception and the rapid presentation of optimal business strategies using artificial intelligence models.

[0480] A "communication terminal" is an electronic device used to send and receive data, and includes devices such as smartphones and tablets.

[0481] "Information" refers to data collected through communication terminals, such as the number of communication contracts, sales figures, and usage status of optional services.

[0482] "Preprocessing" refers to the process of cleaning and correcting raw data to make it suitable for analysis.

[0483] "Performance" refers to indicators of a store's sales and profits over a specific period, and represents the success of the business.

[0484] "Prediction" is the act of estimating future fluctuations in sales and profits based on past and present information.

[0485] An "action plan" is a specific plan for implementing sales strategies and campaigns that are formulated based on predictions.

[0486] "Provision" refers to the act of informing the store staff, who are the users, of the generated action plan.

[0487] "Optimization" is the process of improving a system's performance and making it function more effectively.

[0488] "Real-time" refers to the property of performing information processing and communication instantly without delay.

[0489] An "artificial intelligence model" is a computational model that uses machine learning algorithms to analyze large amounts of data and perform pattern recognition and prediction.

[0490] The system implementing this invention consists of three components: a server, terminals, and users. The server is responsible for collecting information in real time from the communication terminals of each store and centrally managing it in a database. The collected data is first pre-processed to correct for deficiencies and anomalies before being used for analysis. The pre-processed data is then input into an artificial intelligence model on the server. This model predicts future sales and profits based on past and present data.

[0491] The server generates an optimal action plan based on the prediction results. The generated plan is provided to the store staff (users) via a terminal. This allows users to review and implement sales strategies at the appropriate time. For example, if the AI ​​model predicts that "sales of product A should be intensified next week," users can take immediate action.

[0492] This server and terminal function using specific software. The software used includes a Flask-based web server, which forms the interface for real-time data reception and information provision. Additionally, an artificial intelligence model built using machine learning algorithms is implemented using programming languages ​​such as Python.

[0493] Furthermore, to improve the system's accuracy, the server collects execution results from users and uses them for retraining. This feedback loop allows the artificial intelligence model to continuously improve its performance.

[0494] For example, if sales of a new product B fall below expectations, the system can propose a price discount campaign for product B and instruct the store to rearrange the product's placement, thereby recovering sales in a short period of time.

[0495] An example of a prompt to input into a generating AI model is, "Regarding how to sell new product B, suggest the best strategy to increase sales."

[0496] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0497] Step 1:

[0498] The server collects information in real time from the communication terminals of each store. It receives raw data from the communication terminals as input and stores it in a database. Specifically, it retrieves data from the communication terminals via an API and stores it in the corresponding database table.

[0499] Step 2:

[0500] The server preprocesses the collected data. It uses raw data as input and performs data manipulation such as imputing missing data and correcting outliers. The output is a clean, analyzable dataset. Specifically, it uses libraries like Python's pandas library to correct data inconsistencies.

[0501] Step 3:

[0502] The server inputs pre-processed data into the AI ​​model. Using clean data as input, the model performs data calculations to predict future performance based on past and present data trends. The output includes forecasts for future sales and recommended action options. Specifically, the model performs inference using machine learning libraries such as scikit-learn.

[0503] Step 4:

[0504] The server generates an optimal action plan based on prediction results obtained from the AI ​​model. Using the prediction data as input, it formulates a specific sales strategy that maximizes sales. The output is an actionable plan. Specifically, the strategy is described in natural language and stored in JSON format or another format.

[0505] Step 5:

[0506] The server generates an action plan and notifies store staff via their terminals. The input is the generated strategy plan, and the output is the notification to the staff. Specifically, the system sends real-time alerts through terminal applications such as smartphone apps.

[0507] Step 6:

[0508] The user takes action based on an action plan provided by the server and feeds the results back to the server. The input consists of the actions taken and their results, while the output is data necessary for system improvement. The specific operation involves inputting the results within the application and sending them to the server.

[0509] Step 7:

[0510] The server retrains the AI ​​model based on user feedback. It uses the feedback data as input to update the AI ​​model's training dataset and performs data calculations to improve accuracy. The output is a new, improved AI model. Specifically, it performs a retraining process to update the model to the latest state.

[0511] 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.

[0512] This invention provides a system that combines a server, terminal, user, and emotion engine to improve efficiency in store revenue management.

[0513] The server collects various store data from communication devices. This includes contract numbers, sales figures, and usage of optional services, and is processed in real time. The server preprocesses this data and uses machine learning algorithms to predict future sales. The strategic proposals generated based on these predictions include which products to sell and how, and when to implement campaigns and price adjustments.

[0514] The terminal notifies users of strategic proposals received from the server as real-time alerts. Store staff, who are the users, can then incorporate these notifications into their work. This allows users to efficiently implement strategies based on predictions.

[0515] Furthermore, the system incorporates an emotion engine to collect user feedback. This emotion engine analyzes the emotional nuances of user feedback. For example, it senses how satisfied users are with the strategy and what aspects they are dissatisfied with, and provides this information to the server. This information is then used to customize the strategy proposals.

[0516] Through retraining, the server's AI model improves accuracy and gains a deeper understanding for future predictions and strategy generation. The entire system continuously improves by evaluating how effectively users implemented the suggested strategies and how that resulted in improved revenue.

[0517] Thus, this system encompasses a complete workflow from data collection and analysis to strategic proposal notification, feedback, and retraining. Furthermore, by introducing an emotion engine, it is possible to capture not only numerical data but also emotional nuances, thereby further improving the accuracy and effectiveness of strategic proposals.

[0518] The following describes the processing flow.

[0519] Step 1:

[0520] The server collects revenue-related data from each store via communication devices. This data includes the number of contracts, the number of devices sold, and the usage status of optional services, and is acquired in real time.

[0521] Step 2:

[0522] The server preprocesses the collected data. Specifically, it cleans the data to correct outliers and missing values ​​and converts it into a format that machine learning models can easily handle. This ensures data consistency and accuracy.

[0523] Step 3:

[0524] The server uses pre-processed data to perform predictions with an AI model. The AI ​​model has learned from historical data and can accurately forecast future sales trends and demand. These predictions form the foundation for strategic proposals.

[0525] Step 4:

[0526] The server generates strategic proposals based on the predictions of the AI ​​model. These proposals include measures to prioritize the sale of specific products and campaign plans for acquiring and retaining customers.

[0527] Step 5:

[0528] The terminal notifies the user of strategic proposals provided by the server. The terminal uses real-time alerts to create an environment where users can immediately review and implement the strategies.

[0529] Step 6:

[0530] The user implements the proposed strategy and observes the results. Furthermore, an emotion engine collects emotional responses and feedback on the strategy's implementation and transmits them to the server via the device.

[0531] Step 7:

[0532] The server retrains its AI model using user feedback and analysis results from the emotion engine. This loop improves the model's accuracy, which is then reflected in future predictions. The server continues to improve its system to propose better strategies, taking user emotions into account.

[0533] (Example 2)

[0534] 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."

[0535] In today's commercial environment, data-driven revenue forecasting and strategic planning are essential for effective store operations. However, traditional methods have limitations in terms of real-time capabilities and accuracy, and optimizing strategies to take into account actual user reactions and emotional feedback is difficult. Furthermore, the process of improving systems based on feedback is often done manually, resulting in a time-consuming and labor-intensive process.

[0536] 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.

[0537] In this invention, the server includes means for acquiring information from a data collection medium, means for organizing the acquired information, and means for estimating future revenue based on the organized information. This makes it possible to perform highly accurate revenue forecasts in real time and to automatically optimize strategies by integrating the emotional responses of users.

[0538] "Information collection media" refers to communication devices and database systems used to obtain necessary data from stores and related facilities.

[0539] "Means of organizing acquired information" refers to data processing processes that convert raw data into a format suitable for analysis and inference, such as data cleansing and transformation.

[0540] "Methods for estimating future revenue based on organized information" refers to technologies that use machine learning and statistical analysis techniques to predict future sales and profits based on past and present information.

[0541] "Means for generating strategies" refers to a process that automatically creates sales strategies and marketing plans based on revenue forecasts.

[0542] "Means of communication to users" refers to a system for notifying users, such as store staff, of the generated strategies in real time, for example, by providing information via digital devices or apps.

[0543] "Means of collecting user feedback and improving the system" refers to the process of collecting the results of strategy implementation and user feedback to help improve the system.

[0544] "Emotional analysis technology" is a technology that analyzes the emotional nuances contained in the feedback provided by users and extracts them as numerical data or information.

[0545] "Using immediate warnings" is a process that displays warnings to immediately attract the user's attention and encourage prompt action when a generated policy is implemented.

[0546] This invention is a system that combines a server, terminal, user, and sentiment analysis technology, with the aim of improving the operational efficiency of stores. The server acquires various store data from information-gathering media. Specifically, it collects information such as the number of contracts, sales figures, and usage status of optional services via communication devices and database systems. This data is then organized by performing data cleansing and transformation using the Python Pandas library.

[0547] Using organized information, the server leverages machine learning frameworks such as TensorFlow to estimate future revenue. By training a Long-Term Short-Term Memory (LSTM) model based on historical sales data, it accurately predicts next month's or quarter's sales. Based on these results, the server uses a generative AI model to generate appropriate strategies. An example of a specific prompt is, "Please suggest the optimal campaign strategy for next month."

[0548] The terminal immediately notifies the user of the measures sent from the server as an alert. This is done using digital devices such as smartphones and tablets to communicate the measures through notifications and voice alerts.

[0549] Users adjust their tasks based on the suggested strategies and provide further feedback. This feedback is analyzed using sentiment analysis technology and provided to the server. This technology quantifies the user's emotional response and uses it to generate future strategies.

[0550] Each element of this system works in conjunction to continuously provide data-driven, rational, and emotionally nuanced strategies. As a result, it enables the creation of an environment that supports improved operational efficiency and maximized profits.

[0551] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0552] Step 1:

[0553] The server retrieves the necessary data from the information gathering medium. Inputs include the number of store contracts, sales figures, and usage status of optional services. The output is raw data. This operation involves accessing a database server and executing SQL queries to aggregate the required information. Specifically, the server runs a scheduled job every hour to retrieve the latest data.

[0554] Step 2:

[0555] The server organizes the acquired raw data. The input is the raw data obtained in step 1, and the output is cleaned and formatted data. This process checks for missing values ​​in the data and formats the data using the Pandas library. It also handles outliers and encodes categorical variables.

[0556] Step 3:

[0557] The server uses formatted data to estimate future revenue. The input is pre-formatted data, and the output is a future prediction. This process uses an LSTM model with TensorFlow. Specifically, it applies the model to the data using a prediction algorithm to forecast next month's sales.

[0558] Step 4:

[0559] The server generates policies based on the prediction results. The input is the prediction results, and the output is a proposal of feasible policies. In this process, the predictive data is input as prompts to the generating AI model, and strategic proposals are generated. As a concrete example, the prompt statement "Please propose the optimal campaign strategy for next month" is used.

[0560] Step 5:

[0561] The terminal immediately notifies the user of the generated policy as an alert. The input is the policy sent from the server, and the output is the notified policy information. Here, the notification system is activated and sends an alert. The terminal receives the policy information and notifies the user in real time with display and audio alerts.

[0562] Step 6:

[0563] The user implements the proposed strategy and provides feedback. The input is strategy information from the terminal, and the output is feedback information to the system. The user enters the results and impressions of the implemented strategy into a feedback form and sends it to the server.

[0564] Step 7:

[0565] The server receives feedback information and uses sentiment analysis technology. The input is user feedback, and the output is analyzed sentiment data. A sentiment text analysis tool is used to quantify emotional elements such as positive and negative. The results are saved as data for improving future strategies.

[0566] (Application Example 2)

[0567] 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."

[0568] In modern brick-and-mortar stores, real-time data processing and rapid feedback to employees are essential for improving the efficiency of revenue management. However, current systems have a fragmented process from data collection to analysis and feedback, and lack effective means of utilizing emotional feedback from customers. As a result, there are limitations in improving predictive accuracy and the quality of strategic proposals.

[0569] 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.

[0570] In this invention, the server includes means for collecting data from a communication device, means for preprocessing the collected data, means for predicting future sales based on the preprocessed data, means for generating strategic proposals based on the prediction results, means for notifying the user of the generated strategic proposals, means for analyzing the user's emotional feedback, and means for collecting execution results from the user and improving the system based on the emotional analysis results. This enables the generation of strategic proposals that take user emotions into consideration and continuous system improvement.

[0571] A "communication device" is a device used to send and receive information and to collect data.

[0572] "Data preprocessing" is the process of organizing and processing collected raw data and converting it into a format that can be used in the next step.

[0573] "Sales forecasting method" refers to an algorithm or model that uses pre-processed data to predict future sales.

[0574] A "strategy proposal generation method" is a system or process for proposing efficient sales methods and measures based on sales forecast results.

[0575] A "notification method" is a means of informing users of the generated strategy draft, and typically includes a function to transmit information in real time.

[0576] "Emotional feedback analysis methods" refer to technologies for analyzing emotional responses from users and understanding them in the form of numerical data or categories.

[0577] The "implementation result collection method" is a function that collects the results of users executing strategic proposals and uses them to further improve the system.

[0578] The system implementing this invention mainly consists of a server, terminals, and users. The server collects various data using communication devices installed in stores, including sales figures and usage status of optional services. This data is collected in real time and preprocessed. Preprocessing includes data cleaning and normalization, and these tasks are usually performed using programming languages ​​such as Python and libraries such as Pandas.

[0579] The pre-processed data is input into a model that predicts future sales using machine learning libraries such as TensorFlow and PyTorch. Based on this data, the generative AI model generates strategic proposals, such as which products to sell and how, as well as the optimal timing for pricing adjustments and campaigns.

[0580] The terminal receives strategic proposals generated from the server in real time and notifies store staff. These notifications are sent via smartphones and tablets, allowing staff to optimize their operations based on the information. An emotion engine is also integrated into the terminal, emotionally analyzing staff feedback. This includes information such as the staff's level of satisfaction with the strategic proposals.

[0581] Users (store staff) send feedback through the emotion engine, which is then analyzed by the server. This analysis is used to improve the system and to retrain it to improve the accuracy of future sales forecasts and strategic proposals.

[0582] As a concrete example, there is a case where store staff received a strategic proposal to identify the optimal timing for launching seasonal product promotions, and as a result of implementing it, sales increased significantly. In this case, based on the staff's feedback, a prompt message was sent to the server stating, "Please provide a strategic proposal to optimize the timing of seasonal product promotions. Please provide specific steps based on predictions that take into account past data and current trends."

[0583] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0584] Step 1:

[0585] The server collects various store data in real time from communication devices. Inputs include sales figures and usage status of optional services. The collected data is stored on the server as raw data.

[0586] Step 2:

[0587] The server preprocesses the collected raw data. The raw data collected in step 1 is used as input. Specifically, the data is cleaned (missing values ​​are imputed, outliers are removed) and normalized to format it in a way that is suitable for the predictive model. The output is the preprocessed data.

[0588] Step 3:

[0589] The server predicts future sales based on pre-processed data. The input is the pre-processed data obtained in step 2. A machine learning model using TensorFlow or PyTorch processes the data and outputs the prediction results. The output is the future sales forecast.

[0590] Step 4:

[0591] The server generates strategic proposals based on sales forecasts. The forecast results obtained in step 3 are used as input. The generating AI model creates strategic proposals that include which products to sell and how, as well as pricing adjustments and campaign timings. The output is the generated strategic proposal.

[0592] Step 5:

[0593] The terminal notifies the user in real time of the strategy proposal received from the server. The strategy proposal generated in step 4 is used as input. Alerts are displayed on the store staff's smartphones or tablets, providing actionable instructions. The output is the content of the notification to the user.

[0594] Step 6:

[0595] The user executes the proposed strategy and provides the execution results and feedback through the terminal. The input is the proposed strategy received in step 5 and the execution results at the store. The terminal's emotion engine emotionally analyzes the feedback. The output is the execution results and emotional feedback sent to the server.

[0596] Step 7:

[0597] The server improves the system based on the execution results and sentiment feedback collected from the user. The information collected in step 6 is used as input. The system improves the accuracy of the predictive model through retraining. The output is the improved predictive model for the next prediction.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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".

[0615] To implement the system of this invention, there are three main roles: server, terminal, and user.

[0616] The server centrally manages diverse data collected from all stores via communication devices. This data includes the number of communication contracts, terminal sales, and usage status of optional services at each store. The server acquires this data in real time and stores it in the appropriate database.

[0617] The acquired data first undergoes preprocessing on the server. This preprocessing involves cleaning and correcting the data. For example, missing data is supplemented based on past data, and outliers are corrected to an appropriate range based on other values.

[0618] Next, the pre-processed data is input into the AI ​​model. The server activates this model, which utilizes machine learning techniques, to predict future sales and revenues. The AI ​​model makes predictions based on past data and current trends, indicating the timing and products that are likely to see increased sales in the future.

[0619] Next, the server generates a strategic proposal based on the prediction results. This strategic proposal includes specific action plans, such as which products should be prioritized for sale and what campaigns should be launched.

[0620] The generated strategy proposals are notified to store staff, who are the users, via a terminal. The notification is a real-time alert, which users can review and incorporate into their work. For example, the terminal can support store activities by sending specific instructions to staff, such as "Implement a campaign to boost new terminal sales next week."

[0621] User feedback is sent back to the server via the device. Data such as actual sales performance, campaign effectiveness, and customer reactions are collected and analyzed by the server to help retrain the AI ​​model. This feedback loop allows the system to improve its accuracy daily and develop more effective strategies.

[0622] Through this series of steps, the present invention automates revenue management for each store, enabling efficient and rapid strategic execution.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] The server connects to the communication devices at each store and collects real-time data on the number of contracts, sales figures, and usage of optional services. This data is processed quickly, providing the foundational information necessary for effective decision-making.

[0626] Step 2:

[0627] The server preprocesses the collected data. This includes data cleaning, imputing missing values, and detecting and correcting outliers. For example, if an unnatural value is detected, it is compared with past data and corrected to an appropriate range.

[0628] Step 3:

[0629] The server inputs pre-processed data into a machine learning algorithm to predict future sales and revenue. The AI ​​model identifies the timing of increases and decreases in sales, taking into account past trends and real-time data.

[0630] Step 4:

[0631] Based on the prediction results, the server generates a sales strategy proposal. This strategy is designed to include methods for focusing sales on specific products, appropriate campaign timing, and inventory management techniques.

[0632] Step 5:

[0633] The terminal notifies store staff, who are the users, of the generated strategy proposals. This notification is in the form of a real-time alert, allowing staff to immediately review the strategy and incorporate it into their work.

[0634] Step 6:

[0635] Users collect the results of their actions according to the strategy and feed them back to the server via their devices. This data includes actual sales, campaign effectiveness, and customer feedback.

[0636] Step 7:

[0637] The server analyzes the collected feedback data and uses it to retrain the AI ​​model. This creates a loop that improves the accuracy of future predictions and strategic proposals.

[0638] (Example 1)

[0639] 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".

[0640] Effective information management and operation require the rapid and accurate formulation of strategies based on real-time collected data, and the notification of those strategies in an actionable format. However, existing methods suffer from delays in information processing and notification, as well as insufficient accuracy. This invention aims to improve these problems, streamline the process from information gathering to strategy execution, and optimize revenue management at each level.

[0641] 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.

[0642] In this invention, the server includes means for acquiring information from a communication device, means for organizing the acquired information, means for predicting future revenue based on the organized information, means for creating a strategic design using generation technology, means for notifying users of the created strategic design, means for acquiring execution results from users and improving the structure, and means for executing predictions using the generated commands. This enables rapid and highly accurate data processing and strategic planning.

[0643] A "communication device" is a device or a device that has the function of sending and receiving information with other devices or systems.

[0644] "Information" is a general term for data that is collected, managed, and analyzed within a system.

[0645] "Preparation" refers to the act of appropriately processing collected information and transforming it into a format suitable for analysis and prediction.

[0646] "Revenue" refers to the economic gain or projected gain derived from business activities.

[0647] "Generative technology" refers to technologies that automatically create new information or results based on existing data and models.

[0648] "Strategic design" refers to specific policies and action plans formulated to achieve a particular objective.

[0649] A "beneficiary" refers to a user of a system or a person who benefits from a system.

[0650] "Notification" refers to the act of notifying or transmitting specific information.

[0651] "Immediate warning" refers to an alert function that provides important information in real time without delay.

[0652] A "command" refers to a set of instructions or prompts generated by a system to trigger a specific action.

[0653] This invention is a system for streamlining store operations, in which three entities—a server, terminals, and users—work together. The server is the central entity that acquires and manages data from the communication devices of each store. The data includes the number of communication contracts, the number of terminals sold, and the usage status of optional services. The server stores this data in a database management system and processes the data using Python and Pandas. The processed data is then supplied to a machine learning model utilizing TensorFlow to predict future revenue.

[0654] The terminal is responsible for informing the user of the generated strategy design, providing real-time, immediate warnings. This enables the user to make quick decisions in the field. The user sends their operational results and customer feedback back to the server for further learning and improvement.

[0655] As a concrete example, the server generates a prompt message saying, "Forecast next week's sales and identify the three main products," and inputs it into the TensorFlow model. Based on this prompt message, the system designs a strategy for prioritizing products and provides information to the user in real time. This allows the user to receive specific instructions, such as, "Focus on selling smartphone X next week and run a 20% off campaign on related accessories."

[0656] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0657] Step 1:

[0658] The server retrieves data from the communication device. At this stage, the server receives data such as the number of communication contracts, terminal sales, and usage status of optional services for each store as input data. This data is stored in a database in preparation for subsequent processing. For example, database software is used to save the data as monthly data for each store.

[0659] Step 2:

[0660] The system processes the data acquired by the server. Specifically, it converts the data into a dataframe format using Python and the Pandas library, and imputes missing values ​​with the average of past data. Z-scores are used to detect outliers and correct human errors. The input to this process is the data stored in the aforementioned database, and the output is pre-processed, clean data. For example, if an abnormal sales figure is detected, it is replaced with the average value.

[0661] Step 3:

[0662] The server uses prepared data to predict revenue. This prepared data is input into a generative AI model built with TensorFlow to predict which products and when sales are expected to increase. This process generates prompts such as "Predict next week's sales and identify the top three products." The output provides the prediction results, indicating which products are expected to see increased sales. For example, it can generate a list of products for which demand is predicted to rise.

[0663] Step 4:

[0664] The server creates a strategy design based on the forecast results. It generates specific proposals for products to prioritize selling and campaigns to implement, according to the predicted demand. The input is the forecast results from step 3, and the output is the proposed strategy design. For example, it might formulate a specific strategy such as, "Focus on smartphone X and run a 20% off campaign on related accessories."

[0665] Step 5:

[0666] The terminal notifies the user of the strategic design. The terminal notifies the user of the strategic design as a real-time alert, prompting immediate action. The input is the strategic design draft created in step 4, and the output is the notification received by the user. For example, the terminal may display specific advertising placement instructions to store staff.

[0667] Step 6:

[0668] The user provides feedback on the results of their actions to the server. The user reports actual sales performance and campaign effectiveness, and sends the data back to the server. The user's input is directly incorporated into the server and used to retrain the AI ​​model for the next iteration. For example, the user might input the campaign's sales achievement rate and send it to the server.

[0669] (Application Example 1)

[0670] 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".

[0671] To improve the accuracy of sales strategies in retail stores and enhance performance, real-time data processing and forecasting are necessary. However, existing systems have problems such as insufficient information gathering from stores, which makes strategy formulation and implementation time-consuming and hinders effective business improvement.

[0672] 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.

[0673] In this invention, the server includes means for collecting information from communication terminals, means for pre-processing the collected information, and means for predicting future performance based on the pre-processed information. This enables real-time information reception and the rapid presentation of optimal business strategies using artificial intelligence models.

[0674] A "communication terminal" is an electronic device used to send and receive data, and includes devices such as smartphones and tablets.

[0675] "Information" refers to data collected through communication terminals, such as the number of communication contracts, sales figures, and usage status of optional services.

[0676] "Preprocessing" refers to the process of cleaning and correcting raw data to make it suitable for analysis.

[0677] "Performance" refers to indicators of a store's sales and profits over a specific period, and represents the success of the business.

[0678] "Prediction" is the act of estimating future fluctuations in sales and profits based on past and present information.

[0679] An "action plan" is a specific plan for implementing sales strategies and campaigns that are formulated based on predictions.

[0680] "Provision" refers to the act of informing the store staff, who are the users, of the generated action plan.

[0681] "Optimization" is the process of improving a system's performance and making it function more effectively.

[0682] "Real-time" refers to the property of performing information processing and communication instantly without delay.

[0683] An "artificial intelligence model" is a computational model that uses machine learning algorithms to analyze large amounts of data and perform pattern recognition and prediction.

[0684] The system implementing this invention consists of three components: a server, terminals, and users. The server is responsible for collecting information in real time from the communication terminals of each store and centrally managing it in a database. The collected data is first pre-processed to correct for deficiencies and anomalies before being used for analysis. The pre-processed data is then input into an artificial intelligence model on the server. This model predicts future sales and profits based on past and present data.

[0685] The server generates an optimal action plan based on the prediction results. The generated plan is provided to the store staff (users) via a terminal. This allows users to review and implement sales strategies at the appropriate time. For example, if the AI ​​model predicts that "sales of product A should be intensified next week," users can take immediate action.

[0686] This server and terminal function using specific software. The software used includes a Flask-based web server, which forms the interface for real-time data reception and information provision. Additionally, an artificial intelligence model built using machine learning algorithms is implemented using programming languages ​​such as Python.

[0687] Furthermore, to improve the system's accuracy, the server collects execution results from users and uses them for retraining. This feedback loop allows the artificial intelligence model to continuously improve its performance.

[0688] For example, if sales of a new product B fall below expectations, the system can propose a price discount campaign for product B and instruct the store to rearrange the product's placement, thereby recovering sales in a short period of time.

[0689] An example of a prompt to input into a generating AI model is, "Regarding how to sell new product B, suggest the best strategy to increase sales."

[0690] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0691] Step 1:

[0692] The server collects information in real time from the communication terminals of each store. It receives raw data from the communication terminals as input and stores it in a database. Specifically, it retrieves data from the communication terminals via an API and stores it in the corresponding database table.

[0693] Step 2:

[0694] The server preprocesses the collected data. It uses raw data as input and performs data manipulation such as imputing missing data and correcting outliers. The output is a clean, analyzable dataset. Specifically, it uses libraries like Python's pandas library to correct data inconsistencies.

[0695] Step 3:

[0696] The server inputs pre-processed data into the AI ​​model. Using clean data as input, the model performs data calculations to predict future performance based on past and present data trends. The output includes forecasts for future sales and recommended action options. Specifically, the model performs inference using machine learning libraries such as scikit-learn.

[0697] Step 4:

[0698] The server generates an optimal action plan based on prediction results obtained from the AI ​​model. Using the prediction data as input, it formulates a specific sales strategy that maximizes sales. The output is an actionable plan. Specifically, the strategy is described in natural language and stored in JSON format or another format.

[0699] Step 5:

[0700] The server generates an action plan and notifies store staff via their terminals. The input is the generated strategy plan, and the output is the notification to the staff. Specifically, the system sends real-time alerts through terminal applications such as smartphone apps.

[0701] Step 6:

[0702] The user takes action based on an action plan provided by the server and feeds the results back to the server. The input consists of the actions taken and their results, while the output is data necessary for system improvement. The specific operation involves inputting the results within the application and sending them to the server.

[0703] Step 7:

[0704] The server retrains the AI ​​model based on user feedback. It uses the feedback data as input to update the AI ​​model's training dataset and performs data calculations to improve accuracy. The output is a new, improved AI model. Specifically, it performs a retraining process to update the model to the latest state.

[0705] 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.

[0706] This invention provides a system that combines a server, terminal, user, and emotion engine to improve efficiency in store revenue management.

[0707] The server collects various store data from communication devices. This includes contract numbers, sales figures, and usage of optional services, and is processed in real time. The server preprocesses this data and uses machine learning algorithms to predict future sales. The strategic proposals generated based on these predictions include which products to sell and how, and when to implement campaigns and price adjustments.

[0708] The terminal notifies users of strategic proposals received from the server as real-time alerts. Store staff, who are the users, can then incorporate these notifications into their work. This allows users to efficiently implement strategies based on predictions.

[0709] Furthermore, the system incorporates an emotion engine to collect user feedback. This emotion engine analyzes the emotional nuances of user feedback. For example, it senses how satisfied users are with the strategy and what aspects they are dissatisfied with, and provides this information to the server. This information is then used to customize the strategy proposals.

[0710] Through retraining, the server's AI model improves accuracy and gains a deeper understanding for future predictions and strategy generation. The entire system continuously improves by evaluating how effectively users implemented the suggested strategies and how that resulted in improved revenue.

[0711] Thus, this system encompasses a complete workflow from data collection and analysis to strategic proposal notification, feedback, and retraining. Furthermore, by introducing an emotion engine, it is possible to capture not only numerical data but also emotional nuances, thereby further improving the accuracy and effectiveness of strategic proposals.

[0712] The following describes the processing flow.

[0713] Step 1:

[0714] The server collects revenue-related data from each store via communication devices. This data includes the number of contracts, the number of devices sold, and the usage status of optional services, and is acquired in real time.

[0715] Step 2:

[0716] The server preprocesses the collected data. Specifically, it cleans the data to correct outliers and missing values ​​and converts it into a format that machine learning models can easily handle. This ensures data consistency and accuracy.

[0717] Step 3:

[0718] The server uses pre-processed data to perform predictions with an AI model. The AI ​​model has learned from historical data and can accurately forecast future sales trends and demand. These predictions form the foundation for strategic proposals.

[0719] Step 4:

[0720] The server generates strategic proposals based on the predictions of the AI ​​model. These proposals include measures to prioritize the sale of specific products and campaign plans for acquiring and retaining customers.

[0721] Step 5:

[0722] The terminal notifies the user of strategic proposals provided by the server. The terminal uses real-time alerts to create an environment where users can immediately review and implement the strategies.

[0723] Step 6:

[0724] The user implements the proposed strategy and observes the results. Furthermore, an emotion engine collects emotional responses and feedback on the strategy's implementation and transmits them to the server via the device.

[0725] Step 7:

[0726] The server retrains its AI model using user feedback and analysis results from the emotion engine. This loop improves the model's accuracy, which is then reflected in future predictions. The server continues to improve its system to propose better strategies, taking user emotions into account.

[0727] (Example 2)

[0728] 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".

[0729] In today's commercial environment, data-driven revenue forecasting and strategic planning are essential for effective store operations. However, traditional methods have limitations in terms of real-time capabilities and accuracy, and optimizing strategies to take into account actual user reactions and emotional feedback is difficult. Furthermore, the process of improving systems based on feedback is often done manually, resulting in a time-consuming and labor-intensive process.

[0730] 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.

[0731] In this invention, the server includes means for acquiring information from a data collection medium, means for organizing the acquired information, and means for estimating future revenue based on the organized information. This makes it possible to perform highly accurate revenue forecasts in real time and to automatically optimize strategies by integrating the emotional responses of users.

[0732] "Information collection media" refers to communication devices and database systems used to obtain necessary data from stores and related facilities.

[0733] "Means of organizing acquired information" refers to data processing processes that convert raw data into a format suitable for analysis and inference, such as data cleansing and transformation.

[0734] "Methods for estimating future revenue based on organized information" refers to technologies that use machine learning and statistical analysis techniques to predict future sales and profits based on past and present information.

[0735] "Means for generating strategies" refers to a process that automatically creates sales strategies and marketing plans based on revenue forecasts.

[0736] "Means of communication to users" refers to a system for notifying users, such as store staff, of the generated strategies in real time, for example, by providing information via digital devices or apps.

[0737] "Means of collecting user feedback and improving the system" refers to the process of collecting the results of strategy implementation and user feedback to help improve the system.

[0738] "Emotional analysis technology" is a technology that analyzes the emotional nuances contained in the feedback provided by users and extracts them as numerical data or information.

[0739] "Using immediate warnings" is a process that displays warnings to immediately attract the user's attention and encourage prompt action when a generated policy is implemented.

[0740] This invention is a system that combines a server, terminal, user, and sentiment analysis technology, with the aim of improving the operational efficiency of stores. The server acquires various store data from information-gathering media. Specifically, it collects information such as the number of contracts, sales figures, and usage status of optional services via communication devices and database systems. This data is then organized by performing data cleansing and transformation using the Python Pandas library.

[0741] Using organized information, the server leverages machine learning frameworks such as TensorFlow to estimate future revenue. By training a Long-Term Short-Term Memory (LSTM) model based on historical sales data, it accurately predicts next month's or quarter's sales. Based on these results, the server uses a generative AI model to generate appropriate strategies. An example of a specific prompt is, "Please suggest the optimal campaign strategy for next month."

[0742] The terminal immediately notifies the user of the measures sent from the server as an alert. This is done using digital devices such as smartphones and tablets to communicate the measures through notifications and voice alerts.

[0743] Users adjust their tasks based on the suggested strategies and provide further feedback. This feedback is analyzed using sentiment analysis technology and provided to the server. This technology quantifies the user's emotional response and uses it to generate future strategies.

[0744] Each element of this system works in conjunction to continuously provide data-driven, rational, and emotionally nuanced strategies. As a result, it enables the creation of an environment that supports improved operational efficiency and maximized profits.

[0745] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0746] Step 1:

[0747] The server retrieves the necessary data from the information gathering medium. Inputs include the number of store contracts, sales figures, and usage status of optional services. The output is raw data. This operation involves accessing a database server and executing SQL queries to aggregate the required information. Specifically, the server runs a scheduled job every hour to retrieve the latest data.

[0748] Step 2:

[0749] The server organizes the acquired raw data. The input is the raw data obtained in step 1, and the output is cleaned and formatted data. This process checks for missing values ​​in the data and formats the data using the Pandas library. It also handles outliers and encodes categorical variables.

[0750] Step 3:

[0751] The server uses formatted data to estimate future revenue. The input is pre-formatted data, and the output is a future prediction. This process uses an LSTM model with TensorFlow. Specifically, it applies the model to the data using a prediction algorithm to forecast next month's sales.

[0752] Step 4:

[0753] The server generates policies based on the prediction results. The input is the prediction results, and the output is a proposal of feasible policies. In this process, the predictive data is input as prompts to the generating AI model, and strategic proposals are generated. As a concrete example, the prompt statement "Please propose the optimal campaign strategy for next month" is used.

[0754] Step 5:

[0755] The terminal immediately notifies the user of the generated policy as an alert. The input is the policy sent from the server, and the output is the notified policy information. Here, the notification system is activated and sends an alert. The terminal receives the policy information and notifies the user in real time with display and audio alerts.

[0756] Step 6:

[0757] The user implements the proposed strategy and provides feedback. The input is strategy information from the terminal, and the output is feedback information to the system. The user enters the results and impressions of the implemented strategy into a feedback form and sends it to the server.

[0758] Step 7:

[0759] The server receives feedback information and uses sentiment analysis technology. The input is user feedback, and the output is analyzed sentiment data. A sentiment text analysis tool is used to quantify emotional elements such as positive and negative. The results are saved as data for improving future strategies.

[0760] (Application Example 2)

[0761] 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".

[0762] In modern brick-and-mortar stores, real-time data processing and rapid feedback to employees are essential for improving the efficiency of revenue management. However, current systems have a fragmented process from data collection to analysis and feedback, and lack effective means of utilizing emotional feedback from customers. As a result, there are limitations in improving predictive accuracy and the quality of strategic proposals.

[0763] 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.

[0764] In this invention, the server includes means for collecting data from a communication device, means for preprocessing the collected data, means for predicting future sales based on the preprocessed data, means for generating strategic proposals based on the prediction results, means for notifying the user of the generated strategic proposals, means for analyzing the user's emotional feedback, and means for collecting execution results from the user and improving the system based on the emotional analysis results. This enables the generation of strategic proposals that take user emotions into consideration and continuous system improvement.

[0765] A "communication device" is a device used to send and receive information and to collect data.

[0766] "Data preprocessing" is the process of organizing and processing collected raw data and converting it into a format that can be used in the next step.

[0767] "Sales forecasting method" refers to an algorithm or model that uses pre-processed data to predict future sales.

[0768] A "strategy proposal generation method" is a system or process for proposing efficient sales methods and measures based on sales forecast results.

[0769] A "notification method" is a means of informing users of the generated strategy draft, and typically includes a function to transmit information in real time.

[0770] "Emotional feedback analysis methods" refer to technologies for analyzing emotional responses from users and understanding them in the form of numerical data or categories.

[0771] The "implementation result collection method" is a function that collects the results of users executing strategic proposals and uses them to further improve the system.

[0772] The system implementing this invention mainly consists of a server, terminals, and users. The server collects various data using communication devices installed in stores, including sales figures and usage status of optional services. This data is collected in real time and preprocessed. Preprocessing includes data cleaning and normalization, and these tasks are usually performed using programming languages ​​such as Python and libraries such as Pandas.

[0773] The pre-processed data is input into a model that predicts future sales using machine learning libraries such as TensorFlow and PyTorch. Based on this data, the generative AI model generates strategic proposals, such as which products to sell and how, as well as the optimal timing for pricing adjustments and campaigns.

[0774] The terminal receives strategic proposals generated from the server in real time and notifies store staff. These notifications are sent via smartphones and tablets, allowing staff to optimize their operations based on the information. An emotion engine is also integrated into the terminal, emotionally analyzing staff feedback. This includes information such as the staff's level of satisfaction with the strategic proposals.

[0775] Users (store staff) send feedback through the emotion engine, which is then analyzed by the server. This analysis is used to improve the system and to retrain it to improve the accuracy of future sales forecasts and strategic proposals.

[0776] As a concrete example, there is a case where store staff received a strategic proposal to identify the optimal timing for launching seasonal product promotions, and as a result of implementing it, sales increased significantly. In this case, based on the staff's feedback, a prompt message was sent to the server stating, "Please provide a strategic proposal to optimize the timing of seasonal product promotions. Please provide specific steps based on predictions that take into account past data and current trends."

[0777] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0778] Step 1:

[0779] The server collects various store data in real time from communication devices. Inputs include sales figures and usage status of optional services. The collected data is stored on the server as raw data.

[0780] Step 2:

[0781] The server preprocesses the collected raw data. The raw data collected in step 1 is used as input. Specifically, the data is cleaned (missing values ​​are imputed, outliers are removed) and normalized to format it in a way that is suitable for the predictive model. The output is the preprocessed data.

[0782] Step 3:

[0783] The server predicts future sales based on pre-processed data. The input is the pre-processed data obtained in step 2. A machine learning model using TensorFlow or PyTorch processes the data and outputs the prediction results. The output is the future sales forecast.

[0784] Step 4:

[0785] The server generates strategic proposals based on sales forecasts. The forecast results obtained in step 3 are used as input. The generating AI model creates strategic proposals that include which products to sell and how, as well as pricing adjustments and campaign timings. The output is the generated strategic proposal.

[0786] Step 5:

[0787] The terminal notifies the user in real time of the strategy proposal received from the server. The strategy proposal generated in step 4 is used as input. Alerts are displayed on the store staff's smartphones or tablets, providing actionable instructions. The output is the content of the notification to the user.

[0788] Step 6:

[0789] The user executes the proposed strategy and provides the execution results and feedback through the terminal. The input is the proposed strategy received in step 5 and the execution results at the store. The terminal's emotion engine emotionally analyzes the feedback. The output is the execution results and emotional feedback sent to the server.

[0790] Step 7:

[0791] The server improves the system based on the execution results and sentiment feedback collected from the user. The information collected in step 6 is used as input. The system improves the accuracy of the predictive model through retraining. The output is the improved predictive model for the next prediction.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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."

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0813] The following is further disclosed regarding the embodiments described above.

[0814] (Claim 1)

[0815] Means for collecting data from communication devices,

[0816] A means of preprocessing the collected data,

[0817] A method for predicting future sales based on pre-processed data,

[0818] A means of generating strategic proposals based on prediction results,

[0819] A means of notifying users of the generated strategy proposals,

[0820] A means of collecting execution results from users and improving the system,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, which retrains the prediction model to improve the accuracy of the next prediction.

[0824] (Claim 3)

[0825] The system according to claim 1, which uses real-time alerts when notifying strategic proposals.

[0826] "Example 1"

[0827] (Claim 1)

[0828] Means for obtaining information from communication devices,

[0829] Means for organizing acquired information,

[0830] A means of predicting future revenue based on compiled information,

[0831] A means of creating a strategic design using generative technology,

[0832] Means of informing users of the created strategic design,

[0833] A means of obtaining execution results from users and improving the structure,

[0834] A means for performing predictions using generated instructions,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, which retrains the prediction structure to improve the accuracy of the next prediction.

[0838] (Claim 3)

[0839] The system according to claim 1, which uses immediate warning when notifying strategic design.

[0840] "Application Example 1"

[0841] (Claim 1)

[0842] Means for collecting information from communication terminals,

[0843] A means for preprocessing the collected information,

[0844] A means of predicting future performance based on pre-processed information,

[0845] Means for generating an action plan based on prediction results,

[0846] A means of providing the generated action plan to the user,

[0847] A means of collecting results from users and optimizing the system,

[0848] A means of receiving information in real time and using an artificial intelligence model to present optimal business strategies to store staff,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, which improves the accuracy of the next prediction by retraining the artificial intelligence model.

[0852] (Claim 3)

[0853] The system according to claim 1, which utilizes real-time alerts when notifying action plans.

[0854] "Example 2 of combining an emotion engine"

[0855] (Claim 1)

[0856] Means of obtaining information from information-gathering media,

[0857] A means of organizing the acquired information,

[0858] A means of estimating future earnings based on organized information,

[0859] A means for generating a policy based on the prediction results,

[0860] A means of communicating the generated strategy to the user,

[0861] A means of collecting feedback from users and improving the system,

[0862] A means of analyzing the user's emotional response using emotion analysis technology and integrating it as information,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which retrains the prediction mechanism to improve the accuracy of the next prediction.

[0866] (Claim 3)

[0867] The system according to claim 1, which uses immediate warning when communicating a policy.

[0868] "Application example 2 when combining with an emotional engine"

[0869] (Claim 1)

[0870] Means for collecting data from communication devices,

[0871] A means of preprocessing the collected data,

[0872] A method for predicting future sales based on pre-processed data,

[0873] A means of generating strategic proposals based on prediction results,

[0874] A means of notifying users of the generated strategy proposals,

[0875] A means of analyzing users' emotional feedback,

[0876] A means of collecting execution results from users and improving the system based on sentiment analysis results,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, which retrains the prediction model to improve the accuracy of the next prediction.

[0880] (Claim 3)

[0881] The system according to claim 1, which uses real-time alerts and sentiment analysis results when notifying strategic proposals. [Explanation of Symbols]

[0882] 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

1. Means for collecting information from communication terminals, A means for preprocessing the collected information, A means of predicting future performance based on pre-processed information, Means for generating an action plan based on prediction results, A means of providing the generated action plan to the user, A means of collecting results from users and optimizing the system, A means of receiving information in real time and using an artificial intelligence model to present optimal business strategies to store staff, A system that includes this.

2. The system according to claim 1, which improves the accuracy of the next prediction by retraining the artificial intelligence model.

3. The system according to claim 1, which utilizes real-time alerts when notifying action plans.

Images