System

Abstract

An object of a system according to an embodiment is to predict an appropriate timing, content, and stock quantity of an event based on past records and sales data of each region and store, and to propose a new action.SOLUTION: A system includes a data collection unit, an analysis unit, a prediction unit, and a proposal unit. The data collection unit collects data of past results of each region or each store, the number of home appliances sold in each region, and past event contents or results. The analysis unit analyzes the data collected by the data collection unit. The prediction unit predicts an appropriate timing of an event, a recommended event content, and an appropriate number of stocks based on the data analyzed by the analysis unit. The proposal unit proposes a new action on the basis of the content predicted by the prediction unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately predict the appropriate timing, content, and inventory levels of events based on past performance and sales data for each region and store, so there is room for improvement.

[0005] The system according to the embodiment aims to predict the optimal timing, content, and inventory levels of events based on past performance and sales data for each region and store, and to propose new actions. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, an analysis unit, a prediction unit, and a proposal unit. The data collection unit collects data on past performance of each region or each store, the number of home appliances sold in each region, and past event details or performance. The analysis unit analyzes the data collected by the data collection unit. The prediction unit predicts appropriate event timing, recommended event details, and appropriate inventory quantities based on the data analyzed by the analysis unit. The proposal unit proposes new actions based on the details predicted by the prediction unit. [Effects of the Invention]

[0007] The system according to the embodiment can predict the optimal timing, content, and inventory levels of events based on past performance and sales data for each region and store, and can propose new actions. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The customer needs prediction system according to an embodiment of the present invention is a system that identifies potential customer needs and uses a generation AI to make predictions. This system analyzes data such as the past performance of each region and each store, the number of home appliances sold in each region, and past event content and performance, and predicts the optimal timing for events, recommended event content, and optimal inventory levels. This allows the customer needs prediction system to identify potential customer needs, hold appropriate events at the appropriate time, and optimize inventory.

[0029] A customer needs prediction system according to an embodiment includes a data collection unit, an analysis unit, a prediction unit, and a proposal unit. The data collection unit collects data on past performance of each region or each store, the number of home appliances sold in each region, and the details or results of past events. For example, the data collection unit collects past performance data such as sales data, the number of customers, and the number of event participants. The data collection unit can also collect home appliance sales figures, such as the number of sales of a specific home appliance and the number of sales per period. The data collection unit can also collect past event details and results, such as the type of event, the number of participants, and sales results. The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit analyzes the data based on an algorithm to identify customer behavior patterns and trends. The analysis unit can also analyze correlations in the data to identify potential customer needs. The analysis unit can also cluster the data to identify customer segments. The prediction unit predicts the appropriate timing for an event, recommended event content, and appropriate inventory levels based on the data analyzed by the analysis unit. For example, the prediction unit predicts what types of events are likely to be successful at a specific time based on past event data. The prediction unit can also create new event content by taking customer preferences and trends into consideration. The prediction unit can also predict how much a particular home appliance will sell at what time and optimize inventory based on that prediction. The suggestion unit proposes new actions based on the content predicted by the prediction unit. For example, the suggestion unit can propose new event planning and promotion methods, methods of approaching customers, etc. The suggestion unit can also propose new marketing measures to attract customer interest. The suggestion unit can also propose measures to increase customer repeat business. As a result, the customer needs prediction system according to the embodiment can grasp customers' latent needs, hold appropriate events at appropriate times, and optimize inventory. For example, by holding an event in accordance with a period when home appliance sales in a specific area increase and appropriately managing inventory, sales can be maximized. Furthermore, by proposing new actions, customer interest can be attracted and repeat business can be increased.

[0030] The data collection unit can use a wider data set for analysis, including customer social media activity or online reviews. For example, the data collection unit collects customer social media activity and uses it for analysis. For example, it analyzes posts on Twitter (registered trademark) or Instagram (registered trademark) to understand customer interests. The data collection unit also collects data from online review sites and uses it for analysis. For example, it analyzes reviews on Amazon or Yelp to reflect customer ratings and feedback. The data collection unit also integrates social media activity and online reviews to build a system that uses a wider data set for analysis. For example, it collects data from multiple platforms and analyzes it in an integrated manner. This allows a wider data set to be used for analysis, thereby improving the accuracy of the analysis.

[0031] The data collection unit can use the generation AI to automatically detect abnormal values ​​and outliers in the data, improving the accuracy of the analysis. For example, the data collection unit uses the generation AI to develop an algorithm that automatically detects abnormal values ​​and outliers in the data. For example, it detects abnormally high and low values ​​in sales data and excludes them from the analysis. The data collection unit also sets criteria for detecting abnormal values ​​and outliers, and the generation AI filters the data based on those criteria. For example, it identifies abnormal values ​​based on standard deviation. The data collection unit also builds a system that detects abnormal values ​​and outliers in the data and improves the accuracy of the analysis. For example, it adds a function to automatically correct abnormal values. This automatically detects abnormal values ​​and outliers in the data, improving the accuracy of the analysis.

[0032] The data collection unit can use multimodal information, including voice data or image data, for analysis. The data collection unit, for example, collects voice data and uses it for analysis. For example, it analyzes customer inquiries to understand their needs and problems. The data collection unit also collects image data and uses it for analysis. For example, it analyzes product photos posted by customers to understand product usage and reviews. The data collection unit also integrates voice data and image data to build a system that uses multimodal information for analysis. For example, it combines voice and images to comprehensively analyze customer needs. In this way, the accuracy of the analysis is improved by using multimodal information, including voice data and image data, for analysis.

[0033] The data collection unit can collect data from different industries or fields and perform analysis from a cross-industry perspective. The data collection unit, for example, collects data from different industries and uses it for analysis. For example, data from the home appliance industry and the fashion industry can be integrated to comprehensively analyze customer lifestyles. The data collection unit also collects data from different fields and performs analysis from a cross-industry perspective. For example, medical data and consumer data can be combined and analyzed. The data collection unit also builds a system that integrates data from different industries or fields and uses it for analysis. For example, data can be collected from multiple data sources and analyzed in an integrated manner. This allows data from different industries or fields to be used for analysis, thereby improving the accuracy of the analysis.

[0034] The prediction unit can also take into account external factors such as season or weather when predicting the appropriate timing for an event. For example, the prediction unit takes into account external factors such as season and weather when predicting the appropriate timing for an event. For example, the prediction unit reflects the tendency for outdoor events to be preferred in the summer. The prediction unit also collects seasonal and weather data and builds a system that predicts the appropriate timing for an event. For example, the event schedule is adjusted based on weather forecast data. The prediction unit also develops an algorithm that predicts the appropriate timing for an event taking into account external factors. For example, the prediction unit analyzes past weather data and the success rate of the event to identify the optimal timing. This makes it possible to predict the appropriate timing for an event taking into account external factors such as season and weather.

[0035] The prediction unit can use the generation AI to perform a detailed analysis of the success factors of an event and identify elements that will increase the probability of success. For example, the prediction unit uses the generation AI to perform a detailed analysis of the success factors from past event data. For example, it identifies success factors based on the number of participants and feedback. The prediction unit also builds a system that analyzes the success factors of an event and identifies elements that will increase the probability of success. For example, it extracts elements that contribute to the success of a specific event format or content. The prediction unit also uses the generation AI to develop an algorithm that analyzes the success factors of an event and identifies elements that will increase the probability of success. For example, it optimizes the event content based on the success factors. This makes it possible to perform a detailed analysis of the success factors of an event and identify elements that will increase the probability of success.

[0036] The prediction unit can analyze event data from different regions and cultural spheres and propose event content from a global perspective. For example, the prediction unit collects event data from different regions and cultural spheres and uses it for analysis. For example, it compares event data from Asia and Europe and proposes event content from a global perspective. The prediction unit also analyzes event data from different cultural spheres and builds a system that proposes event content that takes cultural differences into account. For example, it reflects the culture and customs of each region. The prediction unit also develops an algorithm that integrates and analyzes data from different regions to propose event content from a global perspective. For example, it optimizes event content based on success factors for each region. This makes it possible to analyze event data from different regions and cultural spheres and propose event content from a global perspective.

[0037] The prediction unit can take into account competitors' event schedules when predicting the appropriate timing for an event. For example, the prediction unit collects competitors' event schedules and takes them into account when predicting the appropriate timing for an event. For example, the prediction unit adjusts the schedule so that the event does not overlap with a competitor's event. The prediction unit also analyzes competitors' event schedules and builds a system that identifies the optimal event timing. For example, the prediction unit adjusts the schedule based on the success rate of competitors' events. The prediction unit also develops an algorithm that predicts the event timing taking into account competitors' event schedules. For example, the prediction unit identifies the optimal timing based on competitors' event data. This makes it possible to predict the appropriate timing for an event taking into account competitors' event schedules.

[0038] The forecasting unit can also take into account external factors such as seasons or trends when forecasting inventory. For example, the forecasting unit takes into account external factors such as seasons and trends when forecasting inventory. For example, it increases inventory of air conditioning equipment in the summer. The forecasting unit also collects seasonal and trend data and builds a system that uses it for inventory forecasting. For example, it adjusts inventory quantities based on past trend data. The forecasting unit also develops an algorithm that performs inventory forecasting that takes into account external factors. For example, it optimizes inventory quantities based on seasonal sales data. This makes it possible to forecast inventory that takes into account external factors such as seasons and trends.

[0039] The prediction unit uses the generation AI to automatically detect inventory surpluses and shortages and can adjust inventory in real time. For example, the prediction unit uses the generation AI to build a system that automatically detects inventory surpluses and shortages. For example, it issues an alert when inventory levels exceed a certain threshold. The prediction unit also develops an algorithm that detects inventory surpluses and shortages in real time and adjusts inventory. For example, it automatically places an order when inventory levels are low. The prediction unit also uses the generation AI to build a system that detects inventory surpluses and shortages in real time and adjusts inventory. For example, it holds a sale when inventory levels are high. This makes it possible to automatically detect inventory surpluses and shortages and adjust inventory in real time.

[0040] The forecasting unit analyzes inventory data from different industries and fields and can perform inventory forecasts from a cross-industry perspective. For example, the forecasting unit collects inventory data from different industries and uses it for analysis. For example, inventory data from the home appliance industry and the food industry is integrated to perform inventory forecasts. The forecasting unit also analyzes inventory data from different fields and builds a system that performs inventory forecasts from a cross-industry perspective. For example, inventory data from medical equipment and consumer goods is combined and analyzed. The forecasting unit also develops algorithms that integrate inventory data from different industries and fields and use them for analysis. For example, data is collected from multiple data sources and analyzed in an integrated manner. This makes it possible to analyze inventory data from different industries and fields and perform inventory forecasts from a cross-industry perspective.

[0041] The forecasting unit can also take into account external factors such as the supply chain situation or logistics delays when making inventory forecasts. For example, the forecasting unit takes into account external factors such as the supply chain situation and logistics delays when making inventory forecasts. For example, it increases inventory when logistics delays are predicted. The forecasting unit also collects supply chain data and builds a system that uses it for inventory forecasts. For example, it monitors the supply chain situation in real time and adjusts inventory levels. The forecasting unit also develops an algorithm that makes inventory forecasts that take external factors into account. For example, it optimizes inventory levels based on logistics delay data. This makes it possible to make inventory forecasts that take into account external factors such as the supply chain situation and logistics delays.

[0042] The suggestion unit can analyze the customer's lifestyle or preferences in detail when proposing a new action. For example, the suggestion unit analyzes the customer's lifestyle and preferences in detail when proposing a new action. For example, it proposes an action based on the customer's purchase history and preference data. The suggestion unit also collects customer lifestyle data and builds a system that uses it to propose new actions. For example, it reflects the customer's lifestyle habits and hobbies. The suggestion unit also analyzes the customer's preferences in detail and develops an algorithm that proposes new actions. For example, it proposes promotions and events that match the customer's preferences. In this way, by analyzing the customer's lifestyle and preferences in detail, it becomes possible to propose more appropriate actions.

[0043] The suggestion unit can use the generation AI to predict the success probability of the proposed action and identify the most effective action. The suggestion unit, for example, uses the generation AI to build a system that predicts the success probability of the proposed action. For example, it calculates the success probability based on past data. The suggestion unit also develops an algorithm that predicts the success probability of the proposed action and identifies the most effective action. For example, it preferentially proposes actions with a high success probability. The suggestion unit also uses the generation AI to build a system that predicts the success probability of the proposed action and identifies the most effective action. For example, it optimizes the action based on success factors. This makes it possible to predict the success probability of the proposed action and identify the most effective action.

[0044] The proposal unit can analyze action data from different industries and fields and propose new actions from a cross-industry perspective. For example, the proposal unit collects action data from different industries and uses it for analysis. For example, it integrates action data from the home appliance industry and the fashion industry to propose new actions. The proposal unit also analyzes action data from different fields and builds a system that proposes new actions from a cross-industry perspective. For example, it combines action data from the medical field and consumer goods and analyzes it. The proposal unit also develops algorithms that integrate action data from different industries and fields and use them for analysis. For example, it collects data from multiple data sources and analyzes it in an integrated manner. This makes it possible to analyze action data from different industries and fields and propose new actions from a cross-industry perspective.

[0045] The suggestion unit can take competitors' actions into consideration when proposing new actions. For example, the suggestion unit collects competitors' action data and takes it into consideration when proposing new actions. For example, it refers to competitors' promotions and events. The suggestion unit also analyzes competitors' action data and builds a system that proposes optimal actions. For example, it proposes actions based on competitors' success stories. The suggestion unit also develops an algorithm that proposes new actions taking competitors' action data into consideration. For example, it identifies optimal actions based on competitors' data. This makes it possible to propose new actions that take competitors' actions into consideration.

[0046] The system can compare the predictive accuracy of a simple AI and a generative AI and quantitatively demonstrate the superiority of the generative AI. For example, the system conducts an experiment to compare the predictive accuracy of the simple AI and the generative AI. For example, it evaluates the predictive accuracy of both based on past data. The system also compares the predictive accuracy of the simple AI and the generative AI and creates a report that quantitatively demonstrates the superiority of the generative AI. For example, it displays the difference in predictive accuracy in a graph or table. The system also compares the predictive accuracy of the generative AI with the simple AI and builds a system that quantitatively demonstrates its superiority. For example, it displays the difference in predictive accuracy in real time. This makes it possible to compare the predictive accuracy of the simple AI and the generative AI and quantitatively demonstrate the superiority of the generative AI.

[0047] The system can perform a detailed analysis of how the generative AI incorporates creative elements that are not considered by simple AI. For example, the system compares the prediction results of the simple AI and the generative AI to analyze how the generative AI incorporates creative elements. For example, it analyzes how the generative AI proposes new event content. The system also builds a system that performs a detailed analysis of the process by which the generative AI incorporates creative elements. For example, it visualizes how the generative AI analyzes data and generates new ideas. The system also performs a detailed analysis of the differences between the simple AI and the generative AI, and creates a report that shows how the generative AI incorporates creative elements. For example, it analyzes the generative AI's algorithm and evaluates its creativity. This makes it possible to perform a detailed analysis of how the generative AI incorporates creative elements that are not considered by simple AI.

[0048] The system can use generative AI to develop new prediction methods that go beyond the limits of simple AI. For example, the system uses generative AI to develop new prediction methods that go beyond the limits of simple AI. For example, the generative AI makes predictions that incorporate creative elements. The system also improves the generative AI's algorithm to develop new prediction methods that go beyond the limits of simple AI. For example, the generative AI analyzes more data and improves accuracy. The system also builds a system that uses generative AI to develop new prediction methods that go beyond the limits of simple AI. For example, the generative AI analyzes data and makes predictions in real time. This makes it possible to use generative AI to develop new prediction methods that go beyond the limits of simple AI.

[0049] The system can verify the comparative results between simple AI and generative AI in different industries and fields, demonstrating the versatility of generative AI. For example, the system verifies the comparative results between simple AI and generative AI in different industries. For example, it compares the prediction accuracy in the home appliance industry and the fashion industry. The system also verifies the comparative results between simple AI and generative AI in different fields, building a system that demonstrates the versatility of generative AI. For example, it compares the prediction accuracy in the medical field and the consumer goods field. The system also creates a report that verifies the comparative results between simple AI and generative AI in different industries and fields, showing the difference in prediction accuracy across multiple industries. This makes it possible to verify the comparative results between simple AI and generative AI in different industries and fields, demonstrating the versatility of generative AI.

[0050] The system can specifically demonstrate how the generative AI proposes new actions based on the prediction results of the simple AI. For example, the system specifically demonstrates the process by which the generative AI proposes new actions based on the prediction results of the simple AI. For example, the generative AI proposes new event content based on the predictions of the simple AI. The system also builds a system in which the generative AI proposes new actions based on the prediction results of the simple AI. For example, the generative AI generates an action using the predictions of the simple AI as input. The system also creates a report that specifically demonstrates how the generative AI proposes new actions based on the prediction results of the simple AI. For example, it shows how the generative AI analyzes data and proposes new actions. This makes it possible to specifically demonstrate how the generative AI proposes new actions based on the prediction results of the simple AI.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0053] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0054] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0055] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0056] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The data collection unit collects data on past performance of each region or each store, the number of home appliances sold in each region, and the details and results of past events. For example, it collects past performance data such as sales data, number of customers, and number of event participants, and collects home appliance sales figures such as the number of specific home appliances sold and the number of sales per period. It also collects past event details and results such as the type of event, number of participants, and sales results. Step 2: The analysis department analyzes the data collected by the data collection department. For example, it analyzes the data based on the algorithms used to understand customer behavior patterns and trends. It also analyzes correlations in the data, identifies potential customer needs, clusters the data, and identifies customer segments. Step 3: The forecasting unit predicts the optimal timing for events, recommended event content, and optimal inventory levels based on the data analyzed by the analysis unit. For example, it predicts what types of events are likely to be successful at specific times based on past event data, and creates new event content taking into account customer preferences and trends. It also predicts how much a particular home appliance will sell at what time, and optimizes inventory based on that prediction. Step 4: The proposal department proposes new actions based on the predictions made by the prediction department. For example, they propose new event planning and promotion methods, ways to approach customers, etc. They also propose new marketing measures to attract customer interest and measures to increase repeat customer visits.

[0059] (Example 2) The customer needs prediction system according to an embodiment of the present invention is a system that identifies potential customer needs and uses a generation AI to make predictions. This system analyzes data such as the past performance of each region and each store, the number of home appliances sold in each region, and past event content and performance, and predicts the optimal timing for events, recommended event content, and optimal inventory levels. This allows the customer needs prediction system to identify potential customer needs, hold appropriate events at the appropriate time, and optimize inventory.

[0060] A customer needs prediction system according to an embodiment includes a data collection unit, an analysis unit, a prediction unit, and a proposal unit. The data collection unit collects data on past performance of each region or each store, the number of home appliances sold in each region, and the details or results of past events. For example, the data collection unit collects past performance data such as sales data, the number of customers, and the number of event participants. The data collection unit can also collect home appliance sales figures, such as the number of sales of a specific home appliance and the number of sales per period. The data collection unit can also collect past event details and results, such as the type of event, the number of participants, and sales results. The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit analyzes the data based on an algorithm to identify customer behavior patterns and trends. The analysis unit can also analyze correlations in the data to identify potential customer needs. The analysis unit can also cluster the data to identify customer segments. The prediction unit predicts the appropriate timing for an event, recommended event content, and appropriate inventory levels based on the data analyzed by the analysis unit. For example, the prediction unit predicts what types of events are likely to be successful at a specific time based on past event data. The prediction unit can also create new event content by taking customer preferences and trends into consideration. The prediction unit can also predict how much a particular home appliance will sell at what time and optimize inventory based on that prediction. The suggestion unit proposes new actions based on the content predicted by the prediction unit. For example, the suggestion unit can propose new event planning and promotion methods, methods of approaching customers, etc. The suggestion unit can also propose new marketing measures to attract customer interest. The suggestion unit can also propose measures to increase customer repeat business. As a result, the customer needs prediction system according to the embodiment can grasp customers' latent needs, hold appropriate events at appropriate times, and optimize inventory. For example, by holding an event in accordance with a period when home appliance sales in a specific area increase and appropriately managing inventory, sales can be maximized. Furthermore, by proposing new actions, customer interest can be attracted and repeat business can be increased.

[0061] The data collection unit performs sentiment analysis on each data point and can reflect the customer's emotional response based on the analysis. The data collection unit, for example, performs sentiment analysis on each data point and quantifies the customer's emotional response based on the sentiment score. For example, it analyzes customer reviews and feedback and prioritizes data with strong positive sentiment in the analysis. The data collection unit also collects customers' social media posts and online reviews and performs sentiment analysis. For example, if there is a lot of positive sentiment toward a particular product, it can reflect this in the sales strategy for that product. The data collection unit also uses sentiment analysis to build a system that reflects the customer's emotional response in the analysis. For example, it analyzes customer purchase history and inquiry content and calculates a sentiment score. This makes it possible to analyze data that takes the customer's emotional response into account.

[0062] The data collection unit can use a wider data set for analysis, including customer social media activity or online reviews. For example, the data collection unit collects customer social media activity and uses it for analysis. For example, it analyzes posts on Twitter (registered trademark) or Instagram (registered trademark) to understand customer interests. The data collection unit also collects data from online review sites and uses it for analysis. For example, it analyzes reviews on Amazon or Yelp to reflect customer ratings and feedback. The data collection unit also integrates social media activity and online reviews to build a system that uses a wider data set for analysis. For example, it collects data from multiple platforms and analyzes it in an integrated manner. This allows a wider data set to be used for analysis, thereby improving the accuracy of the analysis.

[0063] The data collection unit can use the generation AI to automatically detect abnormal values ​​and outliers in the data, improving the accuracy of the analysis. For example, the data collection unit uses the generation AI to develop an algorithm that automatically detects abnormal values ​​and outliers in the data. For example, it detects abnormally high and low values ​​in sales data and excludes them from the analysis. The data collection unit also sets criteria for detecting abnormal values ​​and outliers, and the generation AI filters the data based on those criteria. For example, it identifies abnormal values ​​based on standard deviation. The data collection unit also builds a system that detects abnormal values ​​and outliers in the data and improves the accuracy of the analysis. For example, it adds a function to automatically correct abnormal values. This automatically detects abnormal values ​​and outliers in the data, improving the accuracy of the analysis.

[0064] The data collection unit can use multimodal information, including voice data or image data, for analysis. The data collection unit, for example, collects voice data and uses it for analysis. For example, it analyzes customer inquiries to understand their needs and problems. The data collection unit also collects image data and uses it for analysis. For example, it analyzes product photos posted by customers to understand product usage and reviews. The data collection unit also integrates voice data and image data to build a system that uses multimodal information for analysis. For example, it combines voice and images to comprehensively analyze customer needs. In this way, the accuracy of the analysis is improved by using multimodal information, including voice data and image data, for analysis.

[0065] The data collection unit can collect data from different industries or fields and perform analysis from a cross-industry perspective. The data collection unit, for example, collects data from different industries and uses it for analysis. For example, data from the home appliance industry and the fashion industry can be integrated to comprehensively analyze customer lifestyles. The data collection unit also collects data from different fields and performs analysis from a cross-industry perspective. For example, medical data and consumer data can be combined and analyzed. The data collection unit also builds a system that integrates data from different industries or fields and uses it for analysis. For example, data can be collected from multiple data sources and analyzed in an integrated manner. This allows data from different industries or fields to be used for analysis, thereby improving the accuracy of the analysis.

[0066] The data collection unit can use the emotion estimation function to analyze the customer's emotions during data collection in real time and propose a data collection method that elicits positive emotions. The data collection unit, for example, uses the emotion estimation function to analyze the customer's emotions during data collection in real time. For example, it analyzes the customer's facial expressions and voice and calculates an emotion score. The data collection unit also analyzes the customer's emotions in real time and proposes a data collection method that elicits positive emotions. For example, it designs questions and questionnaires that evoke positive emotions in the customer. The data collection unit also uses the emotion estimation function to analyze the customer's emotions during data collection and provide an interface for eliciting positive emotions. For example, it presents encouraging messages and success stories. This makes it possible to analyze the customer's emotions in real time and propose a data collection method that elicits positive emotions.

[0067] The prediction unit can use generative AI to analyze customers' emotional responses from past event data and predict event content based on emotions. For example, the prediction unit uses generative AI to analyze customers' emotional responses from past event data. For example, it analyzes feedback and reviews from event participants to identify event content that has strong positive emotions. The prediction unit also analyzes customers' emotional responses based on past event data and predicts event content based on emotions. For example, if a particular event format was well received by customers, it will re-propose that format. The prediction unit also uses sentiment analysis to analyze customers' emotional responses from past event data and build a system that predicts event content based on emotions. For example, it adjusts the event content based on the sentiment score. This makes it possible to predict event content that takes customers' emotional responses into account.

[0068] The prediction unit can also take into account external factors such as season or weather when predicting the appropriate timing for an event. For example, the prediction unit takes into account external factors such as season and weather when predicting the appropriate timing for an event. For example, the prediction unit reflects the tendency for outdoor events to be preferred in the summer. The prediction unit also collects seasonal and weather data and builds a system that predicts the appropriate timing for an event. For example, the event schedule is adjusted based on weather forecast data. The prediction unit also develops an algorithm that predicts the appropriate timing for an event taking into account external factors. For example, the prediction unit analyzes past weather data and the success rate of the event to identify the optimal timing. This makes it possible to predict the appropriate timing for an event taking into account external factors such as season and weather.

[0069] The prediction unit can use the generation AI to perform a detailed analysis of the success factors of an event and identify elements that will increase the probability of success. For example, the prediction unit uses the generation AI to perform a detailed analysis of the success factors from past event data. For example, it identifies success factors based on the number of participants and feedback. The prediction unit also builds a system that analyzes the success factors of an event and identifies elements that will increase the probability of success. For example, it extracts elements that contribute to the success of a specific event format or content. The prediction unit also uses the generation AI to develop an algorithm that analyzes the success factors of an event and identifies elements that will increase the probability of success. For example, it optimizes the event content based on the success factors. This makes it possible to perform a detailed analysis of the success factors of an event and identify elements that will increase the probability of success.

[0070] The prediction unit can analyze event data from different regions and cultural spheres and propose event content from a global perspective. For example, the prediction unit collects event data from different regions and cultural spheres and uses it for analysis. For example, it compares event data from Asia and Europe and proposes event content from a global perspective. The prediction unit also analyzes event data from different cultural spheres and builds a system that proposes event content that takes cultural differences into account. For example, it reflects the culture and customs of each region. The prediction unit also develops an algorithm that integrates and analyzes data from different regions to propose event content from a global perspective. For example, it optimizes event content based on success factors for each region. This makes it possible to analyze event data from different regions and cultural spheres and propose event content from a global perspective.

[0071] The prediction unit can take into account competitors' event schedules when predicting the appropriate timing for an event. For example, the prediction unit collects competitors' event schedules and takes them into account when predicting the appropriate timing for an event. For example, the prediction unit adjusts the schedule so that the event does not overlap with a competitor's event. The prediction unit also analyzes competitors' event schedules and builds a system that identifies the optimal event timing. For example, the prediction unit adjusts the schedule based on the success rate of competitors' events. The prediction unit also develops an algorithm that predicts the event timing taking into account competitors' event schedules. For example, the prediction unit identifies the optimal timing based on competitors' event data. This makes it possible to predict the appropriate timing for an event taking into account competitors' event schedules.

[0072] The prediction unit uses the emotion estimation function to monitor customers' emotional reactions to the event content in real time and can continuously adjust the optimal event content. The prediction unit, for example, uses the emotion estimation function to build a system that monitors customers' emotional reactions to the event content in real time. For example, it analyzes customers' facial expressions and voices and calculates an emotion score. The prediction unit also analyzes customers' emotional reactions in real time and continuously adjusts the optimal event content. For example, it prioritizes the adoption of content that evokes strong positive emotions. The prediction unit also develops a system that adjusts the event content in real time based on the emotion estimation data. For example, it dynamically changes the event content in response to changes in customers' emotions. This makes it possible to monitor customers' emotional reactions to the event content in real time and continuously adjust the optimal event content.

[0073] The prediction unit uses generative AI to analyze customers' emotional responses from past sales data and can make inventory predictions based on emotions. For example, the prediction unit uses generative AI to analyze customers' emotional responses from past sales data. For example, if there is strong positive emotion toward a particular product, the prediction unit increases the inventory of that product. The prediction unit also analyzes customers' emotional responses based on past sales data and builds a system that makes inventory predictions based on emotions. For example, it adjusts inventory quantities based on emotion scores. The prediction unit also uses emotion analysis to analyze customers' emotional responses from past sales data and develops an algorithm that makes inventory predictions based on emotions. For example, it prioritizes securing inventory for products with strong positive emotions. This makes it possible to make inventory predictions that take customers' emotional responses into account.

[0074] The forecasting unit can also take into account external factors such as seasons or trends when forecasting inventory. For example, the forecasting unit takes into account external factors such as seasons and trends when forecasting inventory. For example, it increases inventory of air conditioning equipment in the summer. The forecasting unit also collects seasonal and trend data and builds a system that uses it for inventory forecasting. For example, it adjusts inventory quantities based on past trend data. The forecasting unit also develops an algorithm that performs inventory forecasting that takes into account external factors. For example, it optimizes inventory quantities based on seasonal sales data. This makes it possible to forecast inventory that takes into account external factors such as seasons and trends.

[0075] The prediction unit uses the generation AI to automatically detect inventory surpluses and shortages and can adjust inventory in real time. For example, the prediction unit uses the generation AI to build a system that automatically detects inventory surpluses and shortages. For example, it issues an alert when inventory levels exceed a certain threshold. The prediction unit also develops an algorithm that detects inventory surpluses and shortages in real time and adjusts inventory. For example, it automatically places an order when inventory levels are low. The prediction unit also uses the generation AI to build a system that detects inventory surpluses and shortages in real time and adjusts inventory. For example, it holds a sale when inventory levels are high. This makes it possible to automatically detect inventory surpluses and shortages and adjust inventory in real time.

[0076] The forecasting unit analyzes inventory data from different industries and fields and can perform inventory forecasts from a cross-industry perspective. For example, the forecasting unit collects inventory data from different industries and uses it for analysis. For example, inventory data from the home appliance industry and the food industry is integrated to perform inventory forecasts. The forecasting unit also analyzes inventory data from different fields and builds a system that performs inventory forecasts from a cross-industry perspective. For example, inventory data from medical equipment and consumer goods is combined and analyzed. The forecasting unit also develops algorithms that integrate inventory data from different industries and fields and use them for analysis. For example, data is collected from multiple data sources and analyzed in an integrated manner. This makes it possible to analyze inventory data from different industries and fields and perform inventory forecasts from a cross-industry perspective.

[0077] The forecasting unit can also take into account external factors such as the supply chain situation or logistics delays when making inventory forecasts. For example, the forecasting unit takes into account external factors such as the supply chain situation and logistics delays when making inventory forecasts. For example, it increases inventory when logistics delays are predicted. The forecasting unit also collects supply chain data and builds a system that uses it for inventory forecasts. For example, it monitors the supply chain situation in real time and adjusts inventory levels. The forecasting unit also develops an algorithm that makes inventory forecasts that take external factors into account. For example, it optimizes inventory levels based on logistics delay data. This makes it possible to make inventory forecasts that take into account external factors such as the supply chain situation and logistics delays.

[0078] The prediction unit can use the emotion estimation function to monitor customers' emotional reactions to the appropriate inventory quantity in real time and continuously adjust the optimal inventory quantity. The prediction unit, for example, uses the emotion estimation function to build a system that monitors customers' emotional reactions to the appropriate inventory quantity in real time. For example, it analyzes customers' facial expressions and voices and calculates an emotion score. The prediction unit also analyzes customers' emotional reactions in real time and continuously adjusts the optimal inventory quantity. For example, it increases the inventory of products that evoke strong positive emotions. The prediction unit also develops a system that adjusts inventory quantities in real time based on the emotion estimation data. For example, it dynamically changes the inventory quantity in response to changes in customers' emotions. This makes it possible to monitor customers' emotional reactions to the appropriate inventory quantity in real time and continuously adjust the optimal inventory quantity.

[0079] The suggestion unit can use a generation AI to analyze customers' emotional responses from past action data and propose new actions based on their emotions. For example, the suggestion unit uses a generation AI to analyze customers' emotional responses from past action data. For example, if there is strong positive emotion toward a particular promotion, the suggestion unit re-proposes that promotion. The suggestion unit also analyzes customers' emotional responses based on past action data and builds a system that proposes new actions based on their emotions. For example, it adjusts actions based on emotion scores. The suggestion unit also uses emotion analysis to analyze customers' emotional responses from past action data and develops an algorithm that proposes new actions based on their emotions. For example, it prioritizes proposing actions that evoke strong positive emotions. This makes it possible to propose new actions that take into account the customers' emotional responses.

[0080] The suggestion unit can analyze the customer's lifestyle or preferences in detail when proposing a new action. For example, the suggestion unit analyzes the customer's lifestyle and preferences in detail when proposing a new action. For example, it proposes an action based on the customer's purchase history and preference data. The suggestion unit also collects customer lifestyle data and builds a system that uses it to propose new actions. For example, it reflects the customer's lifestyle habits and hobbies. The suggestion unit also analyzes the customer's preferences in detail and develops an algorithm that proposes new actions. For example, it proposes promotions and events that match the customer's preferences. In this way, by analyzing the customer's lifestyle and preferences in detail, it becomes possible to propose more appropriate actions.

[0081] The suggestion unit can use the generation AI to predict the success probability of the proposed action and identify the most effective action. The suggestion unit, for example, uses the generation AI to build a system that predicts the success probability of the proposed action. For example, it calculates the success probability based on past data. The suggestion unit also develops an algorithm that predicts the success probability of the proposed action and identifies the most effective action. For example, it preferentially proposes actions with a high success probability. The suggestion unit also uses the generation AI to build a system that predicts the success probability of the proposed action and identifies the most effective action. For example, it optimizes the action based on success factors. This makes it possible to predict the success probability of the proposed action and identify the most effective action.

[0082] The proposal unit can analyze action data from different industries and fields and propose new actions from a cross-industry perspective. For example, the proposal unit collects action data from different industries and uses it for analysis. For example, it integrates action data from the home appliance industry and the fashion industry to propose new actions. The proposal unit also analyzes action data from different fields and builds a system that proposes new actions from a cross-industry perspective. For example, it combines action data from the medical field and consumer goods and analyzes it. The proposal unit also develops algorithms that integrate action data from different industries and fields and use them for analysis. For example, it collects data from multiple data sources and analyzes it in an integrated manner. This makes it possible to analyze action data from different industries and fields and propose new actions from a cross-industry perspective.

[0083] The suggestion unit can take competitors' actions into consideration when proposing new actions. For example, the suggestion unit collects competitors' action data and takes it into consideration when proposing new actions. For example, it refers to competitors' promotions and events. The suggestion unit also analyzes competitors' action data and builds a system that proposes optimal actions. For example, it proposes actions based on competitors' success stories. The suggestion unit also develops an algorithm that proposes new actions taking competitors' action data into consideration. For example, it identifies optimal actions based on competitors' data. This makes it possible to propose new actions that take competitors' actions into consideration.

[0084] The suggestion unit can use the emotion estimation function to monitor the customer's emotional response to a new action in real time and continuously adjust the optimal action. The suggestion unit, for example, uses the emotion estimation function to build a system that monitors the customer's emotional response to a new action in real time. For example, it analyzes the customer's facial expressions and voice and calculates an emotion score. The suggestion unit also analyzes the customer's emotional response in real time and continuously adjusts the optimal action. For example, it prioritizes the adoption of actions that evoke strong positive emotions. The suggestion unit also develops a system that adjusts new actions in real time based on the emotion estimation data. For example, it dynamically changes the action in response to changes in the customer's emotions. This makes it possible to monitor the customer's emotional response to a new action in real time and continuously adjust the optimal action.

[0085] The system can compare the predictive accuracy of a simple AI and a generative AI and quantitatively demonstrate the superiority of the generative AI. For example, the system conducts an experiment to compare the predictive accuracy of the simple AI and the generative AI. For example, it evaluates the predictive accuracy of both based on past data. The system also compares the predictive accuracy of the simple AI and the generative AI and creates a report that quantitatively demonstrates the superiority of the generative AI. For example, it displays the difference in predictive accuracy in a graph or table. The system also compares the predictive accuracy of the generative AI with the simple AI and builds a system that quantitatively demonstrates its superiority. For example, it displays the difference in predictive accuracy in real time. This makes it possible to compare the predictive accuracy of the simple AI and the generative AI and quantitatively demonstrate the superiority of the generative AI.

[0086] The system can perform a detailed analysis of how the generative AI incorporates creative elements that are not considered by simple AI. For example, the system compares the prediction results of the simple AI and the generative AI to analyze how the generative AI incorporates creative elements. For example, it analyzes how the generative AI proposes new event content. The system also builds a system that performs a detailed analysis of the process by which the generative AI incorporates creative elements. For example, it visualizes how the generative AI analyzes data and generates new ideas. The system also performs a detailed analysis of the differences between the simple AI and the generative AI, and creates a report that shows how the generative AI incorporates creative elements. For example, it analyzes the generative AI's algorithm and evaluates its creativity. This makes it possible to perform a detailed analysis of how the generative AI incorporates creative elements that are not considered by simple AI.

[0087] The system can use generative AI to develop new prediction methods that go beyond the limits of simple AI. For example, the system uses generative AI to develop new prediction methods that go beyond the limits of simple AI. For example, the generative AI makes predictions that incorporate creative elements. The system also improves the generative AI's algorithm to develop new prediction methods that go beyond the limits of simple AI. For example, the generative AI analyzes more data and improves accuracy. The system also builds a system that uses generative AI to develop new prediction methods that go beyond the limits of simple AI. For example, the generative AI analyzes data and makes predictions in real time. This makes it possible to use generative AI to develop new prediction methods that go beyond the limits of simple AI.

[0088] The system can verify the comparative results between simple AI and generative AI in different industries and fields, demonstrating the versatility of generative AI. For example, the system verifies the comparative results between simple AI and generative AI in different industries. For example, it compares the prediction accuracy in the home appliance industry and the fashion industry. The system also verifies the comparative results between simple AI and generative AI in different fields, building a system that demonstrates the versatility of generative AI. For example, it compares the prediction accuracy in the medical field and the consumer goods field. The system also creates a report that verifies the comparative results between simple AI and generative AI in different industries and fields, showing the difference in prediction accuracy across multiple industries. This makes it possible to verify the comparative results between simple AI and generative AI in different industries and fields, demonstrating the versatility of generative AI.

[0089] The system can specifically demonstrate how the generative AI proposes new actions based on the prediction results of the simple AI. For example, the system specifically demonstrates the process by which the generative AI proposes new actions based on the prediction results of the simple AI. For example, the generative AI proposes new event content based on the predictions of the simple AI. The system also builds a system in which the generative AI proposes new actions based on the prediction results of the simple AI. For example, the generative AI generates an action using the predictions of the simple AI as input. The system also creates a report that specifically demonstrates how the generative AI proposes new actions based on the prediction results of the simple AI. For example, it shows how the generative AI analyzes data and proposes new actions. This makes it possible to specifically demonstrate how the generative AI proposes new actions based on the prediction results of the simple AI.

[0090] The system can use the emotion estimation function to compare customers' emotional responses to predictions made by a simple AI and a generative AI, and demonstrate the superiority of the generative AI. For example, the system uses the emotion estimation function to compare customers' emotional responses to predictions made by a simple AI and a generative AI. For example, the system analyzes the customer's facial expressions and voice and calculates an emotion score. The system also compares customers' emotional responses to predictions made by a simple AI and a generative AI, and builds a system that demonstrates the superiority of the generative AI. For example, the system displays the difference in emotion scores in real time. The system also uses the emotion estimation function to compare customers' emotional responses to predictions made by a simple AI and a generative AI, and creates a report that demonstrates the superiority of the generative AI. For example, the system displays the difference in emotion scores in a graph or table. This makes it possible to use the emotion estimation function to compare customers' emotional responses to predictions made by a simple AI and a generative AI, and demonstrate the superiority of the generative AI.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0093] The data collection unit can analyze customers' emotional responses in real time and propose data collection methods based on their emotions. For example, it can ask for more detailed feedback on products or services for which customers have positive emotions. The data collection unit can also analyze customers' emotional responses, identify data points that indicate negative emotions, and analyze the causes. Furthermore, the data collection unit can adjust the timing and method of data collection based on customers' emotional responses, achieving more effective data collection. This makes it possible to propose data collection methods that take customer emotions into consideration and improve the quality of data.

[0094] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0095] The data collection unit can analyze customers' emotional responses in real time and propose data collection methods based on their emotions. For example, it can ask for more detailed feedback on products or services for which customers have positive emotions. The data collection unit can also analyze customers' emotional responses, identify data points that indicate negative emotions, and analyze the causes. Furthermore, the data collection unit can adjust the timing and method of data collection based on customers' emotional responses, achieving more effective data collection. This makes it possible to propose data collection methods that take customer emotions into consideration and improve the quality of data.

[0096] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0097] The data collection unit can analyze customers' emotional responses in real time and propose data collection methods based on their emotions. For example, it can ask for more detailed feedback on products or services for which customers have positive emotions. The data collection unit can also analyze customers' emotional responses, identify data points that indicate negative emotions, and analyze the causes. Furthermore, the data collection unit can adjust the timing and method of data collection based on customers' emotional responses, achieving more effective data collection. This makes it possible to propose data collection methods that take customer emotions into consideration and improve the quality of data.

[0098] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0099] The data collection unit can analyze customers' emotional responses in real time and propose data collection methods based on their emotions. For example, it can ask for more detailed feedback on products or services for which customers have positive emotions. The data collection unit can also analyze customers' emotional responses, identify data points that indicate negative emotions, and analyze the causes. Furthermore, the data collection unit can adjust the timing and method of data collection based on customers' emotional responses, achieving more effective data collection. This makes it possible to propose data collection methods that take customer emotions into consideration and improve the quality of data.

[0100] The data collection unit collects customer purchase histories and website browsing histories, enabling detailed analysis of customer behavior patterns. For example, it can propose promotions related to a particular product to customers who frequently browse that product. The data collection unit can also analyze repeat customer trends based on the customer's purchase history and provide special offers to repeat customers. Furthermore, the data collection unit can analyze the customer's website browsing history to identify products and services that the customer is interested in and make personalized proposals based on that. This allows for detailed analysis of customer behavior patterns and makes it possible to implement more effective marketing measures.

[0101] The data collection unit can analyze customers' emotional responses in real time and propose data collection methods based on their emotions. For example, it can ask for more detailed feedback on products or services for which customers have positive emotions. The data collection unit can also analyze customers' emotional responses, identify data points that indicate negative emotions, and analyze the causes. Furthermore, the data collection unit can adjust the timing and method of data collection based on customers' emotional responses, achieving more effective data collection. This makes it possible to propose data collection methods that take customer emotions into consideration and improve the quality of data.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The data collection unit collects data on past performance of each region or each store, the number of home appliances sold in each region, and the details and results of past events. For example, it collects past performance data such as sales data, number of customers, and number of event participants, and collects home appliance sales figures such as the number of specific home appliances sold and the number of sales per period. It also collects past event details and results such as the type of event, number of participants, and sales results. Step 2: The analysis department analyzes the data collected by the data collection department. For example, it analyzes the data based on the algorithms used to understand customer behavior patterns and trends. It also analyzes correlations in the data, identifies potential customer needs, clusters the data, and identifies customer segments. Step 3: The forecasting unit predicts the optimal timing for events, recommended event content, and optimal inventory levels based on the data analyzed by the analysis unit. For example, it predicts what types of events are likely to be successful at specific times based on past event data, and creates new event content taking into account customer preferences and trends. It also predicts how much a particular home appliance will sell at what time, and optimizes inventory based on that prediction. Step 4: The proposal department proposes new actions based on the predictions made by the prediction department. For example, they propose new event planning and promotion methods, ways to approach customers, etc. They also propose new marketing measures to attract customer interest and measures to increase repeat customer visits.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] 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.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] 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.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] 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.

[0163] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0164] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a data collection department that collects data on past performance of each region or each store, the number of home appliances sold in each region, and the contents or performance of past events; an analysis unit that analyzes the data collected by the data collection unit; a prediction unit that predicts an appropriate timing for an event, recommended event content, and an appropriate number of inventory items based on the data analyzed by the analysis unit; a suggestion unit that proposes a new action based on the content predicted by the prediction unit. A system characterized by:

2. The data collection unit Sentiment analysis is performed on each data point to reflect the customer's emotional response based on the analysis.

2. The system of claim 1.

3. The data collection unit Use a broader data set for analysis, including customer social media activity or online reviews 2. The system of claim 1.

4. The data collection unit Use generative AI to automatically detect abnormalities and outliers in data, improving the accuracy of your analysis.

2. The system of claim 1.

5. The data collection unit Use multimodal information, including audio or image data, for analysis 2. The system of claim 1.

6. The data collection unit Collect data from different industries or fields and analyze it from a cross-industry perspective 2. The system of claim 1.

Images