System

Abstract

An object of a system according to an embodiment is to grasp deep needs of a customer in real time and generate a personalized marketing message.SOLUTION: A system according to an embodiment includes a customer data acquisition unit, a data analysis unit, and a marketing message generation unit. The customer data acquisition unit acquires customer data. The data analysis unit analyzes the customer data acquired by the customer data acquisition unit in real time. The marketing message generator may generate a personalized marketing message based on the data analyzed by the data analyzer.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 technologies have had the problem of making it difficult to understand customers' deep needs and generate effective marketing messages.

[0005] The system according to the embodiment aims to understand the deep needs of customers in real time and generate personalized marketing messages. [Means for solving the problem]

[0006] The system according to the embodiment includes a customer data acquisition unit, a data analysis unit, and a marketing message generation unit. The customer data acquisition unit acquires customer data. The data analysis unit analyzes the customer data acquired by the customer data acquisition unit in real time. The marketing message generation unit generates a personalized marketing message based on the data analyzed by the data analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can grasp the deep needs of customers in real time and generate personalized marketing messages. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) A customer understanding system according to an embodiment of the present invention is a system that analyzes customer data in real time and provides personalized marketing messages, thereby enabling the customer understanding system to grasp deep customer needs and develop effective marketing strategies.

[0029] A customer understanding system according to an embodiment includes a customer data acquisition unit, a data analysis unit, and a marketing message generation unit. The customer data acquisition unit acquires customer data. For example, the customer data acquisition unit acquires customer purchase histories from a database. The customer data acquisition unit can also collect website browsing histories. The customer data acquisition unit can also acquire social media activity data. The data analysis unit analyzes the customer data acquired by the customer data acquisition unit in real time. For example, the data analysis unit analyzes the customer data using streaming data processing technology. The data analysis unit can also analyze the customer data using a real-time database. The data analysis unit can also analyze the customer data using a machine learning algorithm. The marketing message generation unit generates a personalized marketing message based on the data analyzed by the data analysis unit. For example, the marketing message generation unit suggests promotions for related products based on the customer's past purchase history. The marketing message generation unit can also generate individual promotions based on the customer's behavioral patterns. The marketing message generation unit can also generate personalized messages based on the customer's preferences. As a result, the customer understanding system according to an embodiment can analyze customer data in real time and provide personalized marketing messages. For example, suggesting related product promotions based on a customer's purchase history can increase customer purchasing motivation. Also, generating individual promotions based on customer behavior patterns can realize marketing tailored to customer needs. And generating personalized messages based on customer preferences can improve customer satisfaction.

[0030] The data analysis unit can analyze behavioral patterns based on customer data, taking into account customer life events. For example, the data analysis unit collects life event data, such as marriage and moving, in addition to the customer's past purchasing history, and analyzes behavioral patterns using generative AI. For example, it analyzes changes in purchasing trends after marriage. The data analysis unit can also predict behavioral patterns based on customer life events. For example, it predicts purchasing behavior after moving. The data analysis unit can also develop marketing strategies based on customer life events. For example, it can propose a promotion for baby products to a customer after giving birth. This makes it possible to analyze behavioral patterns taking into account customer life events. For example, by understanding changes in purchasing trends after marriage, it is possible to strengthen promotions for related products. Furthermore, by predicting purchasing behavior after moving, it is possible to realize marketing that meets the needs of the customer at the new location. Furthermore, by proposing a promotion for baby products to a customer after giving birth, it is possible to realize marketing that meets the needs of the customer.

[0031] The data analysis unit can simulate future customer behavior based on customer data and improve prediction accuracy. For example, the data analysis unit uses generative AI to simulate future purchasing behavior based on a customer's past purchase history and website browsing history. For example, it predicts the likelihood of purchasing a specific product. The data analysis unit can also develop algorithms for simulating future customer behavior. For example, it predicts future behavior using a machine learning model. The data analysis unit can also build a system for simulating future customer behavior. For example, it simulates future behavior using the Monte Carlo method. This allows it to simulate future customer behavior and improve prediction accuracy. For example, it can strengthen promotions for customers who are likely to purchase a specific product. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, it can achieve effective marketing by formulating a marketing strategy based on the simulation results.

[0032] The data analysis unit can be applied to different industries to develop data analysis methods specific to each industry. For example, in the medical industry, the data analysis unit analyzes patients' medical history and health data in real time and uses generative AI to understand patient behavior patterns. For example, it can predict the effectiveness of a specific treatment. In the financial industry, the data analysis unit can analyze customers' transaction history and investment data to understand behavior patterns. For example, it can predict their willingness to purchase a specific investment product. In the manufacturing industry, the data analysis unit can analyze product production data and quality data to understand behavior patterns. For example, it can predict product defect rates. This allows the data analysis unit to be applied to different industries to develop data analysis methods specific to each industry. For example, in the medical industry, understanding patients' behavior patterns can help propose effective treatments. In the financial industry, predicting customers' willingness to invest can help propose appropriate investment products. In the manufacturing industry, predicting product defect rates can help strengthen quality control.

[0033] The data analysis unit can combine voice recognition technology to extract behavioral patterns from the content of customer conversations. For example, the data analysis unit analyzes the content of a customer's inquiry to customer support using voice recognition technology and extracts behavioral patterns using generative AI. For example, it predicts purchasing intent from the tone and content of the inquiry. The data analysis unit can also analyze the content of a customer's telephone conversations and extract behavioral patterns. For example, it can grasp the customer's requests and complaints. The data analysis unit can also analyze customer voice data and extract behavioral patterns. For example, it can predict purchasing intent from the content of a customer's statements. This makes it possible to extract behavioral patterns from the content of customer conversations. For example, by analyzing the content of a customer support inquiry, it is possible to grasp the customer's needs. Furthermore, by analyzing the content of a telephone conversation, it is possible to identify the customer's requests and complaints. Furthermore, by analyzing voice data, it is possible to predict a customer's purchasing intent.

[0034] The marketing message generation unit can provide more refined marketing messages by taking into account not only a customer's past purchase history but also their social media activities or online reviews. For example, the marketing message generation unit collects social media activity data in addition to a customer's past purchase history and generates marketing messages using a generation AI. For example, related products are recommended based on the content of reviews of a specific product. The marketing message generation unit can also analyze a customer's online reviews to generate refined marketing messages. For example, the content of customer reviews is analyzed to propose promotions for related products. The marketing message generation unit can also analyze a customer's social media activity data to generate refined marketing messages. For example, the content of customer posts and comments is analyzed to propose promotions for related products. This makes it possible to provide refined marketing messages that take social media and online reviews into consideration. For example, recommending related products based on the content of reviews of a specific product can increase a customer's purchasing desire. Furthermore, analyzing online reviews can realize marketing that meets customer needs. Furthermore, analyzing social media activity data can provide marketing messages that meet customer preferences.

[0035] The marketing message generation unit can predict a customer's future behavior and prepare marketing messages based on the prediction in advance. The marketing message generation unit can predict future purchasing behavior using a generation AI based on, for example, a customer's past purchase history or website browsing history, and prepare marketing messages based on the prediction in advance. For example, a promotion can be prepared for customers who are likely to purchase a specific product. The marketing message generation unit can also develop an algorithm for predicting a customer's future behavior. For example, a machine learning model can be used to predict future behavior. The marketing message generation unit can also build a system for predicting a customer's future behavior. For example, the Monte Carlo method can be used to simulate future behavior. This allows the prediction of a customer's future behavior and the preparation of marketing messages in advance. For example, preparing a promotion for customers who are likely to purchase a specific product can increase purchasing motivation. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, preparing marketing messages in advance enables quick responses and improves customer satisfaction.

[0036] The marketing message generation unit can adapt personalized marketing messages to different languages ​​and cultures to develop a global marketing strategy. The marketing message generation unit, for example, uses generation AI to automatically translate personalized marketing messages into different languages ​​and develop a global marketing strategy. For example, it translates into multiple languages, such as English, French, and Chinese. The marketing message generation unit can also generate marketing messages that are adapted to different cultures. For example, it can propose promotions that are tailored to regional cultures and corporate cultures. The marketing message generation unit can also plan marketing strategies that are adapted to different languages ​​and cultures. For example, it can formulate targeting strategies for international markets and promotion strategies for each region. This allows the development of a global marketing strategy that is adapted to different languages ​​and cultures. For example, translating into multiple languages, such as English, French, and Chinese, can adapt to international markets. Furthermore, proposing promotions that are tailored to regional cultures and corporate cultures can enable marketing that meets customer needs. Furthermore, targeting international markets and formulating promotion strategies for each region can enable effective global marketing.

[0037] The integration unit can analyze not only a customer's text messages, but also their voice data and facial expression data to generate a more refined personality. For example, the integration unit can analyze not only a customer's text messages but also their voice data and use generative AI to generate a more refined personality. For example, it can read a customer's emotions from the tone and content of their voice to generate a personality. The integration unit can also analyze a customer's facial expression data to generate a more refined personality. For example, it can read emotions from a customer's facial expressions to generate a personality. The integration unit can also analyze a customer's gesture data to generate a more refined personality. For example, it can read emotions from a customer's gestures to generate a personality. This allows for analyzing a customer's text messages, voice data, and facial expression data to generate a more refined personality. For example, reading a customer's emotions from the tone and content of their voice to generate a personality can enable marketing that meets customer needs. Furthermore, analyzing facial expression data can identify a customer's emotions and provide appropriate marketing messages. Furthermore, analyzing gesture data can identify a customer's emotions and provide appropriate marketing messages.

[0038] The integration unit can predict a customer's future behavior and generate a personality based on the prediction. For example, the integration unit uses generative AI to predict future behavior based on a customer's past purchase history and website browsing history, and generates a personality based on the prediction. For example, the integration unit generates a personality for a customer who is likely to purchase a specific product. The integration unit can also develop an algorithm for predicting a customer's future behavior. For example, it can predict future behavior using a machine learning model. The integration unit can also build a system for predicting a customer's future behavior. For example, it can simulate future behavior using the Monte Carlo method. This makes it possible to predict a customer's future behavior and generate a personality based on the prediction. For example, by generating a personality for a customer who is likely to purchase a specific product, marketing that meets the customer's needs can be realized. By predicting future behavior, marketing that meets the customer's needs can be realized. By generating a personality based on the prediction, more effective marketing can be realized.

[0039] The integration unit can combine the integration of verbal and non-verbal information with virtual reality (VR) technology to simulate customer behavior in a virtual space. For example, the integration unit integrates verbal and non-verbal information and uses generative AI to simulate customer behavior in a virtual space. For example, customer purchasing behavior is reproduced in a VR environment. The integration unit can also develop VR technology for simulating customer behavior. For example, customer behavior is reproduced using a VR headset. The integration unit can also build a virtual environment for simulating customer behavior. For example, the virtual environment can be built using 3D modeling. This allows customer behavior to be simulated in a virtual space using virtual reality technology. For example, by reproducing customer purchasing behavior in a VR environment, marketing that meets customer needs can be realized. Furthermore, VR technology can be used to understand customer behavior in detail. Furthermore, by building a virtual environment, customer behavior can be realistically reproduced and effective marketing strategies can be developed.

[0040] The response analysis unit can perform a more precise analysis by taking into account data from past marketing campaigns when analyzing the response and impact on personality groups. The response analysis unit, for example, collects data from past marketing campaigns and uses generative AI to analyze the response and impact on personality groups. For example, it evaluates a current campaign based on the success factors of past campaigns. The response analysis unit can also analyze data from past marketing campaigns and perform a more precise analysis of the response and impact. For example, it predicts the effectiveness of a current campaign based on data from past campaigns. The response analysis unit can also consider data from past marketing campaigns to develop a more precise marketing strategy. For example, it can propose effective promotions for target customers based on past data. This allows a more precise analysis of the response and impact by taking into account data from past marketing campaigns. For example, by evaluating a current campaign based on the success factors of past campaigns, an effective marketing strategy can be developed. Furthermore, by predicting the effectiveness of a current campaign based on past data, it is possible to realize marketing that meets customer needs. Furthermore, by considering past data, it is possible to propose effective promotions for target customers.

[0041] The response analysis unit can use generative AI to predict the future behavior of personality groups and analyze the response and impact based on the prediction. The response analysis unit can use generative AI to predict the future behavior of personality groups based on, for example, a customer's past purchasing history or website browsing history, and analyze the response and impact based on the prediction. For example, the response analysis unit can evaluate the response of personality groups that are likely to purchase a specific product. The response analysis unit can also develop algorithms for predicting the future behavior of personality groups. For example, it can predict future behavior using a machine learning model. The response analysis unit can also build a system for predicting the future behavior of personality groups. For example, it can simulate future behavior using the Monte Carlo method. This can predict the future behavior of personality groups and analyze the response and impact based on the prediction. For example, by evaluating the response of personality groups that are likely to purchase a specific product, the effectiveness of a marketing campaign can be understood. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, analyzing the response and impact based on the prediction can enable the development of effective marketing strategies.

[0042] The impact analysis unit can apply the analysis of impact and influence on personality groups to different industries to develop industry-specific data analysis methods. For example, in the medical industry, the impact analysis unit analyzes patient medical history and health data and uses generative AI to analyze the impact and influence on personality groups. For example, it can evaluate the effectiveness of a specific treatment. In the financial industry, the impact analysis unit can analyze customer transaction history and investment data to analyze the impact and influence on personality groups. For example, it can evaluate the willingness to purchase a specific investment product. In the manufacturing industry, the impact analysis unit can analyze product production data and quality data to analyze the impact and influence on personality groups. For example, it can evaluate the product defect rate. This can be applied to different industries to develop industry-specific data analysis methods. For example, in the medical industry, understanding patient behavior patterns can suggest effective treatments. In the financial industry, predicting customer investment intentions can suggest appropriate investment products. In the manufacturing industry, predicting product defect rates can strengthen quality control.

[0043] The response analysis unit can combine the analysis of responses and influence on personality groups with social network analysis to evaluate the influence within the network. For example, the response analysis unit uses social network analysis to have the generative AI evaluate the influence of personality groups within the network. For example, the response analysis unit analyzes the influence of a specific customer on other customers. The response analysis unit can also analyze customer social media activity data to evaluate the influence within the network. For example, the response analysis unit analyzes the customer's posts and comments to evaluate the influence within the network. The response analysis unit can also analyze customer survey results to evaluate the influence within the network. For example, the response analysis unit analyzes the customer's responses to evaluate the influence within the network. In this way, the influence within the network can be evaluated by combining social network analysis. For example, by analyzing the influence of a specific customer on other customers, the effectiveness of a marketing campaign can be understood. Furthermore, by evaluating the influence within the network, marketing that meets customer needs can be realized. Furthermore, by evaluating the influence within the network, an effective marketing strategy can be developed.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The customer understanding system may further include a health data acquisition unit that acquires customer health data. For example, data from the customer's fitness tracker or smart watch is collected to understand the customer's health condition. The health data acquisition unit may also acquire the customer's medical records. For example, the health data acquisition unit may collect the results of regular health checkups to evaluate health risks. The health data acquisition unit may also acquire the customer's diet and exercise records. For example, the health data acquisition unit may collect food logs and exercise logs to provide health management advice. This makes it possible to provide personalized marketing messages based on the customer's health condition. For example, by suggesting health foods and fitness programs to customers with high health risks, the customer's health awareness can be increased. Furthermore, by providing promotions according to the customer's health condition, customer satisfaction can be improved.

[0046] The data analysis unit can analyze a customer's hobbies and interests based on the customer's life events. For example, the data analysis unit can collect a customer's past purchase history and social media activity data to identify the customer's hobbies and interests. The data analysis unit can also predict new hobbies and interests based on the customer's life events. For example, it can predict the possibility of a customer taking up a new hobby after marriage. The data analysis unit can also develop marketing strategies tailored to the customer's hobbies and interests based on the customer's life events. For example, after a customer moves, it can suggest promotions tailored to the customer's hobbies and interests in the new area. This makes it possible to provide marketing messages based on the customer's hobbies and interests. For example, by suggesting promotions for related products to a customer who is likely to take up a new hobby after marriage, it is possible to increase the customer's purchasing motivation. Furthermore, by providing promotions tailored to the customer's hobbies and interests, it is possible to improve customer satisfaction.

[0047] The data analysis unit can simulate a customer's future behavior and predict the customer's lifestyle based on the simulation results. For example, it can use generative AI to simulate a customer's future lifestyle based on their past purchase history and website browsing history. The data analysis unit can also develop algorithms for predicting a customer's future lifestyle. For example, it can predict a future lifestyle using a machine learning model. The data analysis unit can also build a system for simulating a customer's future lifestyle. For example, it can simulate a future lifestyle using the Monte Carlo method. This makes it possible to predict a customer's future lifestyle and provide marketing messages based on the prediction. For example, strengthening promotions for customers who are likely to have a certain lifestyle can increase their purchasing motivation. Furthermore, predicting future lifestyles can enable marketing that meets customer needs. Furthermore, it is possible to implement effective marketing by formulating a marketing strategy based on the simulation results.

[0048] The data analysis unit can be applied to different industries to develop data analysis methods specific to each industry. For example, in the education industry, student learning history and grade data can be analyzed in real time to understand learning patterns using generative AI. For example, the effectiveness of a particular learning method can be predicted. In the entertainment industry, the data analysis unit can analyze customer viewing history and rating data to understand behavioral patterns. For example, it can predict preferences for specific movies and music. In the tourism industry, the data analysis unit can analyze travel history and rating data to understand behavioral patterns. For example, it can predict the popularity of a particular tourist destination. This allows the data analysis unit to be applied to different industries to develop data analysis methods specific to each industry. For example, in the education industry, understanding students' learning patterns can be used to suggest effective learning methods. In the entertainment industry, predicting customer preferences can be used to suggest appropriate content. In the tourism industry, predicting the popularity of tourist destinations can be used to suggest sightseeing plans.

[0049] The data analysis unit can combine voice recognition technology to extract behavioral patterns from the content of customer conversations. For example, the content of a customer's inquiry to customer support is analyzed using voice recognition technology, and behavioral patterns are extracted using generative AI. For example, purchasing intent is predicted from the tone and content of the inquiry. The data analysis unit can also analyze the content of a customer's telephone conversations to extract behavioral patterns. For example, it can grasp the customer's requests and complaints. The data analysis unit can also analyze customer voice data to extract behavioral patterns. For example, purchasing intent is predicted from the content of the customer's speech. This makes it possible to extract behavioral patterns from the content of customer conversations. For example, by analyzing the content of a customer support inquiry, it is possible to grasp the customer's needs. Furthermore, by analyzing the content of telephone conversations, it is possible to identify the customer's requests and complaints. Furthermore, by analyzing voice data, it is possible to predict a customer's purchasing intent.

[0050] The marketing message generation unit can provide more refined marketing messages by taking into account not only a customer's past purchase history but also their social media activities or online reviews. For example, in addition to a customer's past purchase history, social media activity data is collected and a marketing message is generated using a generation AI. For example, related products may be recommended based on the content of reviews of a specific product. The marketing message generation unit can also analyze a customer's online reviews to generate refined marketing messages. For example, the content of customer reviews may be analyzed to suggest promotions for related products. The marketing message generation unit can also analyze a customer's social media activity data to generate refined marketing messages. For example, the content of customer posts and comments may be analyzed to suggest promotions for related products. This makes it possible to provide refined marketing messages that take social media and online reviews into consideration. For example, recommending related products based on the content of reviews of a specific product can increase a customer's purchasing desire. Furthermore, analyzing online reviews can enable marketing that meets customer needs. Furthermore, analyzing social media activity data can provide marketing messages that meet customer preferences.

[0051] The marketing message generation unit can predict a customer's future behavior and prepare marketing messages based on the prediction in advance. For example, a generative AI can be used to predict future purchasing behavior based on a customer's past purchase history and website browsing history, and marketing messages based on the prediction can be prepared in advance. For example, a promotion can be prepared for customers who are likely to purchase a specific product. The marketing message generation unit can also develop an algorithm for predicting a customer's future behavior. For example, a machine learning model can be used to predict future behavior. The marketing message generation unit can also build a system for predicting a customer's future behavior. For example, the Monte Carlo method can be used to simulate future behavior. This allows a customer's future behavior to be predicted and marketing messages to be prepared in advance. For example, preparing a promotion for customers who are likely to purchase a specific product can increase purchasing motivation. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, preparing marketing messages in advance enables faster responses and improves customer satisfaction.

[0052] The marketing message generation unit can adapt personalized marketing messages to different languages ​​and cultures to develop a global marketing strategy. For example, using a generative AI, the personalized marketing messages can be automatically translated into different languages ​​to develop a global marketing strategy. For example, translation into multiple languages ​​such as English, French, and Chinese can be performed. The marketing message generation unit can also generate marketing messages that are adapted to different cultures. For example, it can propose promotions that are tailored to regional and corporate cultures. The marketing message generation unit can also plan marketing strategies that are adapted to different languages ​​and cultures. For example, it can formulate targeting strategies for international markets and promotion strategies for each region. This allows the development of a global marketing strategy that is adapted to different languages ​​and cultures. For example, translating into multiple languages ​​such as English, French, and Chinese can be adapted to the international market. Furthermore, proposing promotions that are tailored to regional and corporate cultures can enable marketing that meets customer needs. Furthermore, targeting international markets and formulating promotion strategies for each region can enable effective global marketing.

[0053] The integration unit can analyze not only a customer's text messages, but also their voice data and facial expression data to generate a more refined personality. For example, in addition to a customer's text messages, it can analyze their voice data and use generation AI to generate a more refined personality. For example, it can read a customer's emotions from the tone and content of their voice to generate a personality. The integration unit can also analyze a customer's facial expression data to generate a more refined personality. For example, it can read emotions from a customer's facial expressions to generate a personality. The integration unit can also analyze a customer's gesture data to generate a more refined personality. For example, it can read emotions from a customer's gestures to generate a personality. This allows it to analyze a customer's text messages, voice data, and facial expression data to generate a more refined personality. For example, reading a customer's emotions from the tone and content of their voice to generate a personality can enable marketing that meets customer needs. Furthermore, analyzing facial expression data can identify a customer's emotions and provide appropriate marketing messages. Furthermore, analyzing gesture data can identify a customer's emotions and provide appropriate marketing messages.

[0054] The integration unit can predict a customer's future behavior and generate a personality based on that prediction. For example, it uses generative AI to predict future behavior based on a customer's past purchase history and website browsing history, and generates a personality based on that prediction. For example, it generates a personality for a customer who is likely to purchase a specific product. The integration unit can also develop algorithms for predicting a customer's future behavior. For example, it predicts future behavior using a machine learning model. The integration unit can also build a system for predicting a customer's future behavior. For example, it can simulate future behavior using the Monte Carlo method. This makes it possible to predict a customer's future behavior and generate a personality based on that prediction. For example, by generating a personality for a customer who is likely to purchase a specific product, it is possible to realize marketing that meets customer needs. By predicting future behavior, it is possible to realize marketing that meets customer needs. By generating a personality based on the prediction, it is possible to realize more effective marketing.

[0055] The integration department can combine the integration of verbal and non-verbal information with virtual reality (VR) technology to simulate customer behavior in a virtual space. For example, it can integrate verbal and non-verbal information and use generative AI to simulate customer behavior in a virtual space. For example, it can reproduce customer purchasing behavior in a VR environment. The integration department can also develop VR technology for simulating customer behavior. For example, it can reproduce customer behavior using a VR headset. The integration department can also build a virtual environment for simulating customer behavior. For example, it can build a virtual environment using 3D modeling. This allows it to simulate customer behavior in a virtual space using virtual reality technology. For example, by reproducing customer purchasing behavior in a VR environment, it is possible to realize marketing that meets customer needs. Furthermore, VR technology can be used to understand customer behavior in detail. Furthermore, by building a virtual environment, it is possible to realistically reproduce customer behavior and develop effective marketing strategies.

[0056] The response analysis unit can perform a more precise analysis by taking into account data from past marketing campaigns when analyzing the response and impact on personality groups. For example, data from past marketing campaigns is collected and the generative AI is used to analyze the response and impact on personality groups. For example, a current campaign is evaluated based on the success factors of past campaigns. The response analysis unit can also analyze data from past marketing campaigns and perform a more precise analysis of the response and impact. For example, the effectiveness of a current campaign is predicted based on data from past campaigns. The response analysis unit can also consider data from past marketing campaigns to develop a more precise marketing strategy. For example, effective promotions for target customers are proposed based on past data. This allows a more precise analysis of the response and impact to be performed by taking into account data from past marketing campaigns. For example, by evaluating a current campaign based on the success factors of past campaigns, an effective marketing strategy can be proposed. Furthermore, by predicting the effectiveness of a current campaign based on past data, marketing that meets customer needs can be realized. Furthermore, by considering past data, effective promotions for target customers can be proposed.

[0057] The response analysis unit can use generative AI to predict the future behavior of personality groups and analyze the response and impact based on the prediction. For example, the generative AI can predict the future behavior of personality groups based on customers' past purchasing history and website browsing history, and then analyze the response and impact based on the prediction. For example, the response analysis unit can evaluate the response of personality groups that are likely to purchase a specific product. The response analysis unit can also develop algorithms for predicting the future behavior of personality groups. For example, it can predict future behavior using a machine learning model. The response analysis unit can also build a system for predicting the future behavior of personality groups. For example, it can simulate future behavior using the Monte Carlo method. This can predict the future behavior of personality groups and analyze the response and impact based on the prediction. For example, by evaluating the response of personality groups that are likely to purchase a specific product, the effectiveness of a marketing campaign can be understood. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, analyzing the response and impact based on the prediction can enable the development of effective marketing strategies.

[0058] The impact analysis unit can apply the analysis of impact and influence on personality groups to different industries to develop industry-specific data analysis methods. For example, in the medical industry, patient medical history and health data can be analyzed and generative AI can be used to analyze the impact and influence on personality groups. For example, the effectiveness of a specific treatment can be evaluated. In the financial industry, the impact analysis unit can analyze customer transaction history and investment data to analyze the impact and influence on personality groups. For example, the willingness to purchase a specific investment product can be evaluated. In the manufacturing industry, the impact analysis unit can analyze product production data and quality data to analyze the impact and influence on personality groups. For example, the defect rate of a product can be evaluated. This can be applied to different industries to develop industry-specific data analysis methods. For example, in the medical industry, understanding patient behavior patterns can suggest effective treatments. In the financial industry, predicting customer investment intentions can suggest appropriate investment products. In the manufacturing industry, predicting product defect rates can strengthen quality control.

[0059] The response analysis unit can combine the analysis of responses and influence on personality groups with social network analysis to evaluate their influence within a network. For example, using social network analysis, the generative AI evaluates the influence of personality groups within a network. For example, it analyzes the influence of a specific customer on other customers. The response analysis unit can also analyze customer social media activity data to evaluate their influence within a network. For example, it analyzes the content of customer posts and comments to evaluate their influence within a network. The response analysis unit can also analyze customer survey results to evaluate their influence within a network. For example, it analyzes the content of customer responses to evaluate their influence within a network. In this way, it is possible to combine social network analysis to evaluate their influence within a network. For example, by analyzing the influence of a specific customer on other customers, it is possible to understand the effectiveness of a marketing campaign. Furthermore, by evaluating their influence within a network, it is possible to realize marketing that meets customer needs. Furthermore, by evaluating their influence within a network, it is possible to develop effective marketing strategies.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The customer data acquisition unit acquires customer data. For example, it acquires customer purchase history from a database. The customer data acquisition unit can also collect website browsing history and social media activity data. Step 2: The data analysis unit analyzes the customer data acquired by the customer data acquisition unit in real time. For example, the customer data can be analyzed using streaming data processing technology, a real-time database, or a machine learning algorithm. Step 3: The marketing message generation unit generates personalized marketing messages based on the data analyzed by the data analysis unit. For example, it can suggest promotions for related products based on the customer's past purchase history, or generate individual promotions based on the customer's behavioral patterns and preferences.

[0062] (Example 2) A customer understanding system according to an embodiment of the present invention is a system that analyzes customer data in real time and provides personalized marketing messages, thereby enabling the customer understanding system to grasp deep customer needs and develop effective marketing strategies.

[0063] A customer understanding system according to an embodiment includes a customer data acquisition unit, a data analysis unit, and a marketing message generation unit. The customer data acquisition unit acquires customer data. For example, the customer data acquisition unit acquires customer purchase histories from a database. The customer data acquisition unit can also collect website browsing histories. The customer data acquisition unit can also acquire social media activity data. The data analysis unit analyzes the customer data acquired by the customer data acquisition unit in real time. For example, the data analysis unit analyzes the customer data using streaming data processing technology. The data analysis unit can also analyze the customer data using a real-time database. The data analysis unit can also analyze the customer data using a machine learning algorithm. The marketing message generation unit generates a personalized marketing message based on the data analyzed by the data analysis unit. For example, the marketing message generation unit suggests promotions for related products based on the customer's past purchase history. The marketing message generation unit can also generate individual promotions based on the customer's behavioral patterns. The marketing message generation unit can also generate personalized messages based on the customer's preferences. As a result, the customer understanding system according to an embodiment can analyze customer data in real time and provide personalized marketing messages. For example, suggesting related product promotions based on a customer's purchase history can increase customer purchasing motivation. Also, generating individual promotions based on customer behavior patterns can realize marketing tailored to customer needs. And generating personalized messages based on customer preferences can improve customer satisfaction.

[0064] The data analysis unit can estimate customer emotions based on customer data and perform data analysis according to changes in emotions. For example, the data analysis unit analyzes a customer's purchase history and website browsing history in real time and uses generative AI to estimate customer emotions. For example, it analyzes emotions when purchasing a specific product and tracks changes in those emotions. The data analysis unit can also analyze a customer's social media activity data to estimate changes in emotions. For example, it analyzes customer posts and comments to understand changes in emotions. The data analysis unit can also analyze customer survey results to estimate changes in emotions. For example, it analyzes customer responses and evaluates changes in emotions. This enables data analysis according to customer emotions. For example, if a customer's emotions are positive, it can strengthen promotion of related products. If a customer's emotions are negative, it can identify problems and propose improvements.

[0065] The data analysis unit can analyze behavioral patterns based on customer data, taking into account customer life events. For example, the data analysis unit collects life event data, such as marriage and moving, in addition to the customer's past purchasing history, and analyzes behavioral patterns using generative AI. For example, it analyzes changes in purchasing trends after marriage. The data analysis unit can also predict behavioral patterns based on customer life events. For example, it predicts purchasing behavior after moving. The data analysis unit can also develop marketing strategies based on customer life events. For example, it can propose a promotion for baby products to a customer after giving birth. This makes it possible to analyze behavioral patterns taking into account customer life events. For example, by understanding changes in purchasing trends after marriage, it is possible to strengthen promotions for related products. Furthermore, by predicting purchasing behavior after moving, it is possible to realize marketing that meets the needs of the customer at the new location. Furthermore, by proposing a promotion for baby products to a customer after giving birth, it is possible to realize marketing that meets the needs of the customer.

[0066] The data analysis unit can simulate future customer behavior based on customer data and improve prediction accuracy. For example, the data analysis unit uses generative AI to simulate future purchasing behavior based on a customer's past purchase history and website browsing history. For example, it predicts the likelihood of purchasing a specific product. The data analysis unit can also develop algorithms for simulating future customer behavior. For example, it predicts future behavior using a machine learning model. The data analysis unit can also build a system for simulating future customer behavior. For example, it simulates future behavior using the Monte Carlo method. This allows it to simulate future customer behavior and improve prediction accuracy. For example, it can strengthen promotions for customers who are likely to purchase a specific product. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, it can achieve effective marketing by formulating a marketing strategy based on the simulation results.

[0067] The data analysis unit can be applied to different industries to develop data analysis methods specific to each industry. For example, in the medical industry, the data analysis unit analyzes patients' medical history and health data in real time and uses generative AI to understand patient behavior patterns. For example, it can predict the effectiveness of a specific treatment. In the financial industry, the data analysis unit can analyze customers' transaction history and investment data to understand behavior patterns. For example, it can predict their willingness to purchase a specific investment product. In the manufacturing industry, the data analysis unit can analyze product production data and quality data to understand behavior patterns. For example, it can predict product defect rates. This allows the data analysis unit to be applied to different industries to develop data analysis methods specific to each industry. For example, in the medical industry, understanding patients' behavior patterns can help propose effective treatments. In the financial industry, predicting customers' willingness to invest can help propose appropriate investment products. In the manufacturing industry, predicting product defect rates can help strengthen quality control.

[0068] The data analysis unit can combine voice recognition technology to extract behavioral patterns from the content of customer conversations. For example, the data analysis unit analyzes the content of a customer's inquiry to customer support using voice recognition technology and extracts behavioral patterns using generative AI. For example, it predicts purchasing intent from the tone and content of the inquiry. The data analysis unit can also analyze the content of a customer's telephone conversations and extract behavioral patterns. For example, it can grasp the customer's requests and complaints. The data analysis unit can also analyze customer voice data and extract behavioral patterns. For example, it can predict purchasing intent from the content of a customer's statements. This makes it possible to extract behavioral patterns from the content of customer conversations. For example, by analyzing the content of a customer support inquiry, it is possible to grasp the customer's needs. Furthermore, by analyzing the content of a telephone conversation, it is possible to identify the customer's requests and complaints. Furthermore, by analyzing voice data, it is possible to predict a customer's purchasing intent.

[0069] The data analysis unit can use the emotion estimation function to monitor customer emotions in real time and propose marketing strategies in response to changes in emotions. For example, the data analysis unit can analyze a customer's purchase history and website browsing history in real time, estimate their emotions using generative AI, and propose marketing strategies in response to changes in their emotions. For example, the data analysis unit can propose specific promotions to customers with strong positive emotions. The data analysis unit can also analyze customer social media activity data and propose marketing strategies in response to changes in emotions. For example, the data analysis unit can analyze customer posts and comments and propose promotions in response to changes in emotions. The data analysis unit can also analyze customer survey results and propose marketing strategies in response to changes in emotions. For example, the data analysis unit can analyze customer responses and propose promotions in response to changes in emotions. This makes it possible to monitor customer emotions in real time and propose marketing strategies in response to changes in emotions. For example, proposing specific promotions to customers with strong positive emotions can increase purchasing motivation. Proposing promotions in response to changes in emotions can also realize marketing that meets customer needs. Proposing marketing strategies in response to changes in emotions can also improve customer satisfaction.

[0070] The marketing message generation unit can provide more refined marketing messages by taking into account not only a customer's past purchase history but also their social media activities or online reviews. For example, the marketing message generation unit collects social media activity data in addition to a customer's past purchase history and generates marketing messages using a generation AI. For example, related products are recommended based on the content of reviews of a specific product. The marketing message generation unit can also analyze a customer's online reviews to generate refined marketing messages. For example, the content of customer reviews is analyzed to propose promotions for related products. The marketing message generation unit can also analyze a customer's social media activity data to generate refined marketing messages. For example, the content of customer posts and comments is analyzed to propose promotions for related products. This makes it possible to provide refined marketing messages that take social media and online reviews into consideration. For example, recommending related products based on the content of reviews of a specific product can increase a customer's purchasing desire. Furthermore, analyzing online reviews can realize marketing that meets customer needs. Furthermore, analyzing social media activity data can provide marketing messages that meet customer preferences.

[0071] The marketing message generation unit can predict a customer's future behavior and prepare marketing messages based on the prediction in advance. The marketing message generation unit can predict future purchasing behavior using a generation AI based on, for example, a customer's past purchase history or website browsing history, and prepare marketing messages based on the prediction in advance. For example, a promotion can be prepared for customers who are likely to purchase a specific product. The marketing message generation unit can also develop an algorithm for predicting a customer's future behavior. For example, a machine learning model can be used to predict future behavior. The marketing message generation unit can also build a system for predicting a customer's future behavior. For example, the Monte Carlo method can be used to simulate future behavior. This allows the prediction of a customer's future behavior and the preparation of marketing messages in advance. For example, preparing a promotion for customers who are likely to purchase a specific product can increase purchasing motivation. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, preparing marketing messages in advance enables quick responses and improves customer satisfaction.

[0072] The marketing message generation unit can adapt personalized marketing messages to different languages ​​and cultures to develop a global marketing strategy. The marketing message generation unit, for example, uses generation AI to automatically translate personalized marketing messages into different languages ​​and develop a global marketing strategy. For example, it translates into multiple languages, such as English, French, and Chinese. The marketing message generation unit can also generate marketing messages that are adapted to different cultures. For example, it can propose promotions that are tailored to regional cultures and corporate cultures. The marketing message generation unit can also plan marketing strategies that are adapted to different languages ​​and cultures. For example, it can formulate targeting strategies for international markets and promotion strategies for each region. This allows the development of a global marketing strategy that is adapted to different languages ​​and cultures. For example, translating into multiple languages, such as English, French, and Chinese, can adapt to international markets. Furthermore, proposing promotions that are tailored to regional cultures and corporate cultures can enable marketing that meets customer needs. Furthermore, targeting international markets and formulating promotion strategies for each region can enable effective global marketing.

[0073] The marketing message generation unit uses the emotion estimation function to generate marketing messages in real time based on customer emotions, thereby enabling communication that is tailored to the customer's emotions. The marketing message generation unit uses a generation AI to estimate emotions based on, for example, a customer's purchase history or website browsing history, and generates marketing messages in real time based on those emotions. For example, the marketing message generation unit recommends a specific product to a customer with strong positive emotions. The marketing message generation unit can also analyze customer social media activity data and generate marketing messages in real time based on emotions. For example, the marketing message generation unit can analyze customer posts and comments and suggest promotions based on emotions. The marketing message generation unit can also analyze customer survey results and generate marketing messages in real time based on emotions. For example, the marketing message generation unit can analyze customer responses and suggest promotions based on emotions. This enables communication that is tailored to the customer's emotions in real time. For example, recommending a specific product to a customer with strong positive emotions can increase purchasing motivation. Furthermore, suggesting promotions based on emotions can enable marketing that meets the customer's needs. Furthermore, generating marketing messages in real time based on emotions enables quick responses and improves customer satisfaction.

[0074] The integration unit can use the emotion estimation function to estimate a customer's emotions and integrate linguistic and non-linguistic information based on the emotions. For example, the integration unit uses generative AI to estimate emotions based on a customer's text messages or voice data and integrates linguistic and non-linguistic information based on the emotions. For example, a specific expression is used for a customer with strong positive emotions. The integration unit can also analyze a customer's facial expression data and integrate linguistic and non-linguistic information based on the emotions. For example, emotions can be read from a customer's facial expressions and appropriate expressions can be used. The integration unit can also analyze a customer's gesture data and integrate linguistic and non-linguistic information based on the emotions. For example, emotions can be read from a customer's gestures and appropriate expressions can be used. This makes it possible to integrate linguistic and non-linguistic information based on a customer's emotions. For example, using a specific expression for a customer with strong positive emotions can improve customer satisfaction. Furthermore, using expressions based on emotions can enable communication that meets customer needs. Furthermore, integrating linguistic and non-linguistic information based on emotions can enable more effective marketing.

[0075] The integration unit can analyze not only a customer's text messages, but also their voice data and facial expression data to generate a more refined personality. For example, the integration unit can analyze not only a customer's text messages but also their voice data and use generative AI to generate a more refined personality. For example, it can read a customer's emotions from the tone and content of their voice to generate a personality. The integration unit can also analyze a customer's facial expression data to generate a more refined personality. For example, it can read emotions from a customer's facial expressions to generate a personality. The integration unit can also analyze a customer's gesture data to generate a more refined personality. For example, it can read emotions from a customer's gestures to generate a personality. This allows for analyzing a customer's text messages, voice data, and facial expression data to generate a more refined personality. For example, reading a customer's emotions from the tone and content of their voice to generate a personality can enable marketing that meets customer needs. Furthermore, analyzing facial expression data can identify a customer's emotions and provide appropriate marketing messages. Furthermore, analyzing gesture data can identify a customer's emotions and provide appropriate marketing messages.

[0076] The integration unit can predict a customer's future behavior and generate a personality based on the prediction. For example, the integration unit uses generative AI to predict future behavior based on a customer's past purchase history and website browsing history, and generates a personality based on the prediction. For example, the integration unit generates a personality for a customer who is likely to purchase a specific product. The integration unit can also develop an algorithm for predicting a customer's future behavior. For example, it can predict future behavior using a machine learning model. The integration unit can also build a system for predicting a customer's future behavior. For example, it can simulate future behavior using the Monte Carlo method. This makes it possible to predict a customer's future behavior and generate a personality based on the prediction. For example, by generating a personality for a customer who is likely to purchase a specific product, marketing that meets the customer's needs can be realized. By predicting future behavior, marketing that meets the customer's needs can be realized. By generating a personality based on the prediction, more effective marketing can be realized.

[0077] The integration unit can combine the integration of verbal and non-verbal information with virtual reality (VR) technology to simulate customer behavior in a virtual space. For example, the integration unit integrates verbal and non-verbal information and uses generative AI to simulate customer behavior in a virtual space. For example, customer purchasing behavior is reproduced in a VR environment. The integration unit can also develop VR technology for simulating customer behavior. For example, customer behavior is reproduced using a VR headset. The integration unit can also build a virtual environment for simulating customer behavior. For example, the virtual environment can be built using 3D modeling. This allows customer behavior to be simulated in a virtual space using virtual reality technology. For example, by reproducing customer purchasing behavior in a VR environment, marketing that meets customer needs can be realized. Furthermore, VR technology can be used to understand customer behavior in detail. Furthermore, by building a virtual environment, customer behavior can be realistically reproduced and effective marketing strategies can be developed.

[0078] The integration unit uses the emotion estimation function to integrate linguistic and non-linguistic information based on a customer's emotions in real time, thereby generating a personality that matches those emotions. For example, the integration unit uses a generative AI to estimate emotions based on a customer's purchase history or website browsing history, and then integrates linguistic and non-linguistic information based on those emotions in real time. For example, it generates a personality for a customer with strong positive emotions. The integration unit can also analyze a customer's social media activity data and integrate linguistic and non-linguistic information based on emotions in real time. For example, it can analyze a customer's posts and comments to generate a personality based on emotions. The integration unit can also analyze customer survey results and integrate linguistic and non-linguistic information based on emotions in real time. For example, it can analyze a customer's responses to generate a personality based on emotions. This allows integrating linguistic and non-linguistic information based on a customer's emotions in real time, thereby generating a personality that matches those emotions. For example, generating a personality for a customer with strong positive emotions can enable marketing that meets customer needs. Generating a personality based on emotions can also improve customer satisfaction. In addition, real-time integration allows for quick responses and the development of effective marketing strategies.

[0079] The response analysis unit can use generative AI to estimate the emotions of personality groups and analyze the response and impact based on the emotions. For example, the response analysis unit can use generative AI to estimate the emotions of personality groups toward a specific marketing campaign and analyze the response and impact based on the emotions. For example, the response analysis unit can evaluate the response of personality groups with strong positive emotions. The response analysis unit can also analyze customer social media activity data and analyze the response and impact based on emotions. For example, the response analysis unit can analyze customer posts and comments and evaluate the response based on emotions. The response analysis unit can also analyze customer survey results and analyze the response and impact based on emotions. For example, the response analysis unit can analyze customer responses and evaluate the response based on emotions. This makes it possible to analyze the response and impact based on the emotions of personality groups. For example, evaluating the response of personality groups with strong positive emotions can grasp the effectiveness of a marketing campaign. Furthermore, evaluating the response based on emotions can realize marketing that meets customer needs. Furthermore, analyzing the impact based on emotions can develop effective marketing strategies.

[0080] The response analysis unit can perform a more precise analysis by taking into account data from past marketing campaigns when analyzing the response and impact on personality groups. The response analysis unit, for example, collects data from past marketing campaigns and uses generative AI to analyze the response and impact on personality groups. For example, it evaluates a current campaign based on the success factors of past campaigns. The response analysis unit can also analyze data from past marketing campaigns and perform a more precise analysis of the response and impact. For example, it predicts the effectiveness of a current campaign based on data from past campaigns. The response analysis unit can also consider data from past marketing campaigns to develop a more precise marketing strategy. For example, it can propose effective promotions for target customers based on past data. This allows a more precise analysis of the response and impact by taking into account data from past marketing campaigns. For example, by evaluating a current campaign based on the success factors of past campaigns, an effective marketing strategy can be developed. Furthermore, by predicting the effectiveness of a current campaign based on past data, it is possible to realize marketing that meets customer needs. Furthermore, by considering past data, it is possible to propose effective promotions for target customers.

[0081] The response analysis unit can use generative AI to predict the future behavior of personality groups and analyze the response and impact based on the prediction. The response analysis unit can use generative AI to predict the future behavior of personality groups based on, for example, a customer's past purchasing history or website browsing history, and analyze the response and impact based on the prediction. For example, the response analysis unit can evaluate the response of personality groups that are likely to purchase a specific product. The response analysis unit can also develop algorithms for predicting the future behavior of personality groups. For example, it can predict future behavior using a machine learning model. The response analysis unit can also build a system for predicting the future behavior of personality groups. For example, it can simulate future behavior using the Monte Carlo method. This can predict the future behavior of personality groups and analyze the response and impact based on the prediction. For example, by evaluating the response of personality groups that are likely to purchase a specific product, the effectiveness of a marketing campaign can be understood. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, analyzing the response and impact based on the prediction can enable the development of effective marketing strategies.

[0082] The impact analysis unit can apply the analysis of impact and influence on personality groups to different industries to develop industry-specific data analysis methods. For example, in the medical industry, the impact analysis unit analyzes patient medical history and health data and uses generative AI to analyze the impact and influence on personality groups. For example, it can evaluate the effectiveness of a specific treatment. In the financial industry, the impact analysis unit can analyze customer transaction history and investment data to analyze the impact and influence on personality groups. For example, it can evaluate the willingness to purchase a specific investment product. In the manufacturing industry, the impact analysis unit can analyze product production data and quality data to analyze the impact and influence on personality groups. For example, it can evaluate the product defect rate. This can be applied to different industries to develop industry-specific data analysis methods. For example, in the medical industry, understanding patient behavior patterns can suggest effective treatments. In the financial industry, predicting customer investment intentions can suggest appropriate investment products. In the manufacturing industry, predicting product defect rates can strengthen quality control.

[0083] The response analysis unit can combine the analysis of responses and influence on personality groups with social network analysis to evaluate the influence within the network. For example, the response analysis unit uses social network analysis to have the generative AI evaluate the influence of personality groups within the network. For example, the response analysis unit analyzes the influence of a specific customer on other customers. The response analysis unit can also analyze customer social media activity data to evaluate the influence within the network. For example, the response analysis unit analyzes the customer's posts and comments to evaluate the influence within the network. The response analysis unit can also analyze customer survey results to evaluate the influence within the network. For example, the response analysis unit analyzes the customer's responses to evaluate the influence within the network. In this way, the influence within the network can be evaluated by combining social network analysis. For example, by analyzing the influence of a specific customer on other customers, the effectiveness of a marketing campaign can be understood. Furthermore, by evaluating the influence within the network, marketing that meets customer needs can be realized. Furthermore, by evaluating the influence within the network, an effective marketing strategy can be developed.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] The customer understanding system may further include a health data acquisition unit that acquires customer health data. For example, data from the customer's fitness tracker or smart watch is collected to understand the customer's health condition. The health data acquisition unit may also acquire the customer's medical records. For example, the health data acquisition unit may collect the results of regular health checkups to evaluate health risks. The health data acquisition unit may also acquire the customer's diet and exercise records. For example, the health data acquisition unit may collect food logs and exercise logs to provide health management advice. This makes it possible to provide personalized marketing messages based on the customer's health condition. For example, by suggesting health foods and fitness programs to customers with high health risks, the customer's health awareness can be increased. Furthermore, by providing promotions according to the customer's health condition, customer satisfaction can be improved.

[0086] The data analysis unit can estimate a customer's emotions and evaluate the customer's stress level based on the estimated emotions. For example, the data analysis unit can analyze a customer's purchase history and website browsing history to detect signs of stress. The data analysis unit can also analyze a customer's social media activity data to evaluate the stress level. For example, the data analysis unit can analyze a customer's posts and comments to identify signs of stress. The data analysis unit can also analyze the results of a customer survey to evaluate the stress level. For example, the data analysis unit can analyze the customer's responses to evaluate signs of stress. This makes it possible to provide marketing messages according to the customer's stress level. For example, by suggesting relaxation products and services to customers with high stress levels, the customer's stress can be reduced. Furthermore, by providing promotions according to stress levels, customer satisfaction can be improved.

[0087] The data analysis unit can analyze a customer's hobbies and interests based on the customer's life events. For example, the data analysis unit can collect a customer's past purchase history and social media activity data to identify the customer's hobbies and interests. The data analysis unit can also predict new hobbies and interests based on the customer's life events. For example, it can predict the possibility of a customer taking up a new hobby after marriage. The data analysis unit can also develop marketing strategies tailored to the customer's hobbies and interests based on the customer's life events. For example, after a customer moves, it can suggest promotions tailored to the customer's hobbies and interests in the new area. This makes it possible to provide marketing messages based on the customer's hobbies and interests. For example, by suggesting promotions for related products to a customer who is likely to take up a new hobby after marriage, it is possible to increase the customer's purchasing motivation. Furthermore, by providing promotions tailored to the customer's hobbies and interests, it is possible to improve customer satisfaction.

[0088] The data analysis unit can simulate a customer's future behavior and predict the customer's lifestyle based on the simulation results. For example, it can use generative AI to simulate a customer's future lifestyle based on their past purchase history and website browsing history. The data analysis unit can also develop algorithms for predicting a customer's future lifestyle. For example, it can predict a future lifestyle using a machine learning model. The data analysis unit can also build a system for simulating a customer's future lifestyle. For example, it can simulate a future lifestyle using the Monte Carlo method. This makes it possible to predict a customer's future lifestyle and provide marketing messages based on the prediction. For example, strengthening promotions for customers who are likely to have a certain lifestyle can increase their purchasing motivation. Furthermore, predicting future lifestyles can enable marketing that meets customer needs. Furthermore, it is possible to implement effective marketing by formulating a marketing strategy based on the simulation results.

[0089] The data analysis unit can be applied to different industries to develop data analysis methods specific to each industry. For example, in the education industry, student learning history and grade data can be analyzed in real time to understand learning patterns using generative AI. For example, the effectiveness of a particular learning method can be predicted. In the entertainment industry, the data analysis unit can analyze customer viewing history and rating data to understand behavioral patterns. For example, it can predict preferences for specific movies and music. In the tourism industry, the data analysis unit can analyze travel history and rating data to understand behavioral patterns. For example, it can predict the popularity of a particular tourist destination. This allows the data analysis unit to be applied to different industries to develop data analysis methods specific to each industry. For example, in the education industry, understanding students' learning patterns can be used to suggest effective learning methods. In the entertainment industry, predicting customer preferences can be used to suggest appropriate content. In the tourism industry, predicting the popularity of tourist destinations can be used to suggest sightseeing plans.

[0090] The data analysis unit can combine voice recognition technology to extract behavioral patterns from the content of customer conversations. For example, the content of a customer's inquiry to customer support is analyzed using voice recognition technology, and behavioral patterns are extracted using generative AI. For example, purchasing intent is predicted from the tone and content of the inquiry. The data analysis unit can also analyze the content of a customer's telephone conversations to extract behavioral patterns. For example, it can grasp the customer's requests and complaints. The data analysis unit can also analyze customer voice data to extract behavioral patterns. For example, purchasing intent is predicted from the content of the customer's speech. This makes it possible to extract behavioral patterns from the content of customer conversations. For example, by analyzing the content of a customer support inquiry, it is possible to grasp the customer's needs. Furthermore, by analyzing the content of telephone conversations, it is possible to identify the customer's requests and complaints. Furthermore, by analyzing voice data, it is possible to predict a customer's purchasing intent.

[0091] The data analysis unit can use the emotion estimation function to monitor customer emotions in real time and propose marketing strategies in response to changes in emotions. For example, the data analysis unit can analyze a customer's purchase history and website browsing history in real time, estimate their emotions using generative AI, and propose marketing strategies in response to those changes in emotions. For example, the data analysis unit can propose specific promotions to customers with strong positive emotions. The data analysis unit can also analyze customer social media activity data and propose marketing strategies in response to changes in emotions. For example, the data analysis unit can analyze customer posts and comments and propose promotions in response to changes in emotions. The data analysis unit can also analyze customer survey results and propose marketing strategies in response to changes in emotions. For example, the data analysis unit can analyze customer responses and propose promotions in response to changes in emotions. This makes it possible to monitor customer emotions in real time and propose marketing strategies in response to changes in emotions. For example, proposing specific promotions to customers with strong positive emotions can increase purchasing motivation. Proposing promotions in response to changes in emotions can also realize marketing that meets customer needs. Proposing marketing strategies in response to changes in emotions can also improve customer satisfaction.

[0092] The data analysis unit can estimate a customer's emotions and evaluate the customer's purchasing intent based on the estimated emotions. For example, it can analyze a customer's purchase history and website browsing history to detect changes in purchasing intent. The data analysis unit can also analyze a customer's social media activity data to evaluate purchasing intent. For example, it can analyze the customer's posts and comments to understand changes in purchasing intent. The data analysis unit can also analyze the results of a customer survey to evaluate purchasing intent. For example, it can analyze the customer's responses to evaluate changes in purchasing intent. This makes it possible to provide marketing messages that correspond to the customer's purchasing intent. For example, by recommending a specific product to a customer with a high purchasing intent, it is possible to further increase the customer's purchasing intent. Furthermore, by providing promotions that correspond to purchasing intent, it is possible to improve customer satisfaction.

[0093] The marketing message generation unit can provide more refined marketing messages by taking into account not only a customer's past purchase history but also their social media activities or online reviews. For example, in addition to a customer's past purchase history, social media activity data is collected and a marketing message is generated using a generation AI. For example, related products may be recommended based on the content of reviews of a specific product. The marketing message generation unit can also analyze a customer's online reviews to generate refined marketing messages. For example, the content of customer reviews may be analyzed to suggest promotions for related products. The marketing message generation unit can also analyze a customer's social media activity data to generate refined marketing messages. For example, the content of customer posts and comments may be analyzed to suggest promotions for related products. This makes it possible to provide refined marketing messages that take social media and online reviews into consideration. For example, recommending related products based on the content of reviews of a specific product can increase a customer's purchasing desire. Furthermore, analyzing online reviews can enable marketing that meets customer needs. Furthermore, analyzing social media activity data can provide marketing messages that meet customer preferences.

[0094] The marketing message generation unit can predict a customer's future behavior and prepare marketing messages based on the prediction in advance. For example, a generative AI can be used to predict future purchasing behavior based on a customer's past purchase history and website browsing history, and marketing messages based on the prediction can be prepared in advance. For example, a promotion can be prepared for customers who are likely to purchase a specific product. The marketing message generation unit can also develop an algorithm for predicting a customer's future behavior. For example, a machine learning model can be used to predict future behavior. The marketing message generation unit can also build a system for predicting a customer's future behavior. For example, the Monte Carlo method can be used to simulate future behavior. This allows a customer's future behavior to be predicted and marketing messages to be prepared in advance. For example, preparing a promotion for customers who are likely to purchase a specific product can increase purchasing motivation. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, preparing marketing messages in advance enables faster responses and improves customer satisfaction.

[0095] The marketing message generation unit can adapt personalized marketing messages to different languages ​​and cultures to develop a global marketing strategy. For example, using a generative AI, the personalized marketing messages can be automatically translated into different languages ​​to develop a global marketing strategy. For example, translation into multiple languages ​​such as English, French, and Chinese can be performed. The marketing message generation unit can also generate marketing messages that are adapted to different cultures. For example, it can propose promotions that are tailored to regional and corporate cultures. The marketing message generation unit can also plan marketing strategies that are adapted to different languages ​​and cultures. For example, it can formulate targeting strategies for international markets and promotion strategies for each region. This allows the development of a global marketing strategy that is adapted to different languages ​​and cultures. For example, translating into multiple languages ​​such as English, French, and Chinese can be adapted to the international market. Furthermore, proposing promotions that are tailored to regional and corporate cultures can enable marketing that meets customer needs. Furthermore, targeting international markets and formulating promotion strategies for each region can enable effective global marketing.

[0096] The marketing message generation unit uses the emotion estimation function to generate marketing messages in real time based on customer emotions, thereby enabling communication that is tailored to the customer's emotions. For example, the unit uses generation AI to estimate emotions based on a customer's purchase history and website browsing history, and generates marketing messages in real time based on those emotions. For example, it recommends a specific product to a customer with strong positive emotions. The marketing message generation unit can also analyze customer social media activity data and generate marketing messages in real time based on emotions. For example, it can analyze the customer's posts and comments and suggest promotions based on their emotions. The marketing message generation unit can also analyze customer survey results and generate marketing messages in real time based on their emotions. For example, it can analyze the customer's responses and suggest promotions based on their emotions. This enables communication that is tailored to the customer's emotions in real time. For example, recommending a specific product to a customer with strong positive emotions can increase their desire to purchase. Furthermore, suggesting promotions based on emotions can enable marketing that meets the customer's needs. Furthermore, generating marketing messages in real time based on emotions enables quick responses and improves customer satisfaction.

[0097] The integration unit can use the emotion estimation function to estimate a customer's emotions and integrate linguistic and non-linguistic information based on the emotions. For example, the integration unit can use generative AI to estimate emotions based on a customer's text messages or voice data and integrate linguistic and non-linguistic information based on the emotions. For example, a specific expression can be used for a customer with strong positive emotions. The integration unit can also analyze a customer's facial expression data and integrate linguistic and non-linguistic information based on the emotions. For example, it can read emotions from a customer's facial expressions and use appropriate expressions. The integration unit can also analyze a customer's gesture data and integrate linguistic and non-linguistic information based on the emotions. For example, it can read emotions from a customer's gestures and use appropriate expressions. This makes it possible to integrate linguistic and non-linguistic information based on a customer's emotions. For example, using a specific expression for a customer with strong positive emotions can improve customer satisfaction. Furthermore, using expressions based on emotions can enable communication that meets customer needs. Furthermore, integrating linguistic and non-linguistic information based on emotions can enable more effective marketing.

[0098] The integration unit can analyze not only a customer's text messages, but also their voice data and facial expression data to generate a more refined personality. For example, in addition to a customer's text messages, it can analyze their voice data and use generation AI to generate a more refined personality. For example, it can read a customer's emotions from the tone and content of their voice to generate a personality. The integration unit can also analyze a customer's facial expression data to generate a more refined personality. For example, it can read emotions from a customer's facial expressions to generate a personality. The integration unit can also analyze a customer's gesture data to generate a more refined personality. For example, it can read emotions from a customer's gestures to generate a personality. This allows it to analyze a customer's text messages, voice data, and facial expression data to generate a more refined personality. For example, reading a customer's emotions from the tone and content of their voice to generate a personality can enable marketing that meets customer needs. Furthermore, analyzing facial expression data can identify a customer's emotions and provide appropriate marketing messages. Furthermore, analyzing gesture data can identify a customer's emotions and provide appropriate marketing messages.

[0099] The integration unit can predict a customer's future behavior and generate a personality based on that prediction. For example, it uses generative AI to predict future behavior based on a customer's past purchase history and website browsing history, and generates a personality based on that prediction. For example, it generates a personality for a customer who is likely to purchase a specific product. The integration unit can also develop algorithms for predicting a customer's future behavior. For example, it predicts future behavior using a machine learning model. The integration unit can also build a system for predicting a customer's future behavior. For example, it can simulate future behavior using the Monte Carlo method. This makes it possible to predict a customer's future behavior and generate a personality based on that prediction. For example, by generating a personality for a customer who is likely to purchase a specific product, it is possible to realize marketing that meets customer needs. By predicting future behavior, it is possible to realize marketing that meets customer needs. By generating a personality based on the prediction, it is possible to realize more effective marketing.

[0100] The integration unit can estimate a customer's emotions and evaluate the customer's purchasing intent based on the estimated emotions. For example, it can analyze a customer's purchase history and website browsing history to detect changes in purchasing intent. The integration unit can also analyze a customer's social media activity data to evaluate purchasing intent. For example, it can analyze a customer's posts and comments to understand changes in purchasing intent. The integration unit can also analyze the results of a customer survey to evaluate purchasing intent. For example, it can analyze a customer's responses to evaluate changes in purchasing intent. This makes it possible to provide marketing messages that correspond to the customer's purchasing intent. For example, by recommending a specific product to a customer with a high purchasing intent, the customer's purchasing intent can be further increased. Furthermore, by providing promotions that correspond to purchasing intent, customer satisfaction can be improved.

[0101] The integration department can combine the integration of verbal and non-verbal information with virtual reality (VR) technology to simulate customer behavior in a virtual space. For example, it can integrate verbal and non-verbal information and use generative AI to simulate customer behavior in a virtual space. For example, it can reproduce customer purchasing behavior in a VR environment. The integration department can also develop VR technology for simulating customer behavior. For example, it can reproduce customer behavior using a VR headset. The integration department can also build a virtual environment for simulating customer behavior. For example, it can build a virtual environment using 3D modeling. This allows it to simulate customer behavior in a virtual space using virtual reality technology. For example, by reproducing customer purchasing behavior in a VR environment, it is possible to realize marketing that meets customer needs. Furthermore, VR technology can be used to understand customer behavior in detail. Furthermore, by building a virtual environment, it is possible to realistically reproduce customer behavior and develop effective marketing strategies.

[0102] The integration unit can use the emotion estimation function to integrate linguistic and non-linguistic information based on a customer's emotions in real time, thereby generating a personality that matches those emotions. For example, the integration unit can use a generative AI to estimate emotions based on a customer's purchase history and website browsing history, and then integrate linguistic and non-linguistic information based on those emotions in real time. For example, it can generate a personality for a customer with strong positive emotions. The integration unit can also analyze a customer's social media activity data and integrate linguistic and non-linguistic information based on emotions in real time. For example, it can analyze a customer's posts and comments to generate a personality based on emotions. The integration unit can also analyze the results of a customer survey and integrate linguistic and non-linguistic information based on emotions in real time. For example, it can analyze a customer's responses to generate a personality based on emotions. This allows integrating linguistic and non-linguistic information based on a customer's emotions in real time, thereby generating a personality that matches those emotions. For example, generating a personality for a customer with strong positive emotions can enable marketing that meets customer needs. Generating a personality based on emotions can also improve customer satisfaction. In addition, real-time integration allows for quick responses and the development of effective marketing strategies.

[0103] The response analysis unit can use generative AI to estimate the emotions of personality groups and analyze the response and impact based on those emotions. For example, generative AI can be used to estimate the emotions of personality groups toward a specific marketing campaign and analyze the response and impact based on those emotions. For example, the response of personality groups with strong positive emotions can be evaluated. The response analysis unit can also analyze customer social media activity data and analyze the response and impact based on emotions. For example, it can analyze customer posts and comments and evaluate the response based on emotions. The response analysis unit can also analyze customer survey results and analyze the response and impact based on emotions. For example, it can analyze customer responses and evaluate the response based on emotions. This makes it possible to analyze the response and impact based on the emotions of personality groups. For example, evaluating the response of personality groups with strong positive emotions can grasp the effectiveness of a marketing campaign. Furthermore, evaluating the response based on emotions can realize marketing that meets customer needs. Furthermore, analyzing the impact based on emotions can develop effective marketing strategies.

[0104] The response analysis unit can perform a more precise analysis by taking into account data from past marketing campaigns when analyzing the response and impact on personality groups. For example, data from past marketing campaigns is collected and the generative AI is used to analyze the response and impact on personality groups. For example, a current campaign is evaluated based on the success factors of past campaigns. The response analysis unit can also analyze data from past marketing campaigns and perform a more precise analysis of the response and impact. For example, the effectiveness of a current campaign is predicted based on data from past campaigns. The response analysis unit can also consider data from past marketing campaigns to develop a more precise marketing strategy. For example, effective promotions for target customers are proposed based on past data. This allows a more precise analysis of the response and impact to be performed by taking into account data from past marketing campaigns. For example, by evaluating a current campaign based on the success factors of past campaigns, an effective marketing strategy can be proposed. Furthermore, by predicting the effectiveness of a current campaign based on past data, marketing that meets customer needs can be realized. Furthermore, by considering past data, effective promotions for target customers can be proposed.

[0105] The response analysis unit can use generative AI to predict the future behavior of personality groups and analyze the response and impact based on the prediction. For example, the generative AI can predict the future behavior of personality groups based on customers' past purchasing history and website browsing history, and then analyze the response and impact based on the prediction. For example, the response analysis unit can evaluate the response of personality groups that are likely to purchase a specific product. The response analysis unit can also develop algorithms for predicting the future behavior of personality groups. For example, it can predict future behavior using a machine learning model. The response analysis unit can also build a system for predicting the future behavior of personality groups. For example, it can simulate future behavior using the Monte Carlo method. This can predict the future behavior of personality groups and analyze the response and impact based on the prediction. For example, by evaluating the response of personality groups that are likely to purchase a specific product, the effectiveness of a marketing campaign can be understood. Furthermore, predicting future behavior can enable marketing that meets customer needs. Furthermore, analyzing the response and impact based on the prediction can enable the development of effective marketing strategies.

[0106] The impact analysis unit can apply the analysis of impact and influence on personality groups to different industries to develop industry-specific data analysis methods. For example, in the medical industry, patient medical history and health data can be analyzed and generative AI can be used to analyze the impact and influence on personality groups. For example, the effectiveness of a specific treatment can be evaluated. In the financial industry, the impact analysis unit can analyze customer transaction history and investment data to analyze the impact and influence on personality groups. For example, the willingness to purchase a specific investment product can be evaluated. In the manufacturing industry, the impact analysis unit can analyze product production data and quality data to analyze the impact and influence on personality groups. For example, the defect rate of a product can be evaluated. This can be applied to different industries to develop industry-specific data analysis methods. For example, in the medical industry, understanding patient behavior patterns can suggest effective treatments. In the financial industry, predicting customer investment intentions can suggest appropriate investment products. In the manufacturing industry, predicting product defect rates can strengthen quality control.

[0107] The response analysis unit can combine the analysis of responses and influence on personality groups with social network analysis to evaluate their influence within a network. For example, using social network analysis, the generative AI evaluates the influence of personality groups within a network. For example, it analyzes the influence of a specific customer on other customers. The response analysis unit can also analyze customer social media activity data to evaluate their influence within a network. For example, it analyzes the content of customer posts and comments to evaluate their influence within a network. The response analysis unit can also analyze customer survey results to evaluate their influence within a network. For example, it analyzes the content of customer responses to evaluate their influence within a network. In this way, it is possible to combine social network analysis to evaluate their influence within a network. For example, by analyzing the influence of a specific customer on other customers, it is possible to understand the effectiveness of a marketing campaign. Furthermore, by evaluating their influence within a network, it is possible to realize marketing that meets customer needs. Furthermore, by evaluating their influence within a network, it is possible to develop effective marketing strategies.

[0108] The processing flow of the second embodiment will be briefly explained below.

[0109] Step 1: The customer data acquisition unit acquires customer data. For example, it acquires customer purchase history from a database. The customer data acquisition unit can also collect website browsing history and social media activity data. Step 2: The data analysis unit analyzes the customer data acquired by the customer data acquisition unit in real time. For example, the customer data can be analyzed using streaming data processing technology, a real-time database, or a machine learning algorithm. Step 3: The marketing message generation unit generates personalized marketing messages based on the data analyzed by the data analysis unit. For example, it can suggest promotions for related products based on the customer's past purchase history, or generate individual promotions based on the customer's behavioral patterns and preferences.

[0110] 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.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0112] 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.

[0113] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0114] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0123] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0124] 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.

[0125] 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.

[0126] 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 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.

[0127] 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.

[0128] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0138] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0139] 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.

[0140] 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.

[0141] 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 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.

[0142] 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.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0154] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0155] 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.

[0156] 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.

[0157] 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 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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]

[0177] 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 customer data acquisition unit that acquires customer data; a data analysis unit that analyzes the customer data acquired by the customer data acquisition unit in real time; a marketing message generation unit that generates a personalized marketing message based on the data analyzed by the data analysis unit. A system characterized by:

2. The data analysis unit Estimate customer emotions based on the customer data and perform data analysis according to changes in emotions. The system of claim 1 .

3. The data analysis unit Develop data analysis methods that are applied to different industries and specific to each industry The system of claim 1 .

4. The marketing message generation unit Use emotion estimation to estimate customer emotions and generate personalized marketing messages based on those emotions. The system of claim 1 .

5. The integration department Emotion estimation function is used to estimate customer emotions and integrate verbal and non-verbal information based on emotions. The system of claim 1 .

6. The echo analysis section Generative AI is used to estimate the emotions of personality groups, and to analyze the reactions and impact based on those emotions. The system of claim 1 .

7. The data analysis unit Based on the customer data, consider the customer's life events and analyze their behavioral patterns. The system of claim 1 .

8. The data analysis unit Using emotion estimation capabilities, we monitor customer emotions in real time and propose marketing strategies in response to changes in emotions. The system of claim 1 .

Images