System

Abstract

An object of a system according to an embodiment is to generate a specific and detailed persona and to grasp a highly accurate market survey and a reputation of a product.SOLUTION: A system according to an embodiment includes a generation section, a data analysis section, and a persona generation section. The generation unit generates a specific persona by analyzing the big AI using the generation information. The data analysis unit uses the persona generated by the generation unit to perform a reputation or market survey of the company's product. The persona generation unit generates a persona for a company to make a marketing strategy on the basis of the information obtained by the data analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it is difficult to obtain highly accurate information because the persona generation used for market research and understanding product reputation is not sufficiently specific and detailed.

[0005] The system according to the embodiment aims to generate specific and detailed personas and to conduct highly accurate market research and understand product reputations. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation unit, a data analysis unit, and a persona generation unit. The generation unit analyzes big data using a generation AI to generate specific personas. The data analysis unit uses the personas generated by the generation unit to conduct market research and evaluate the reputation of a company's products. The persona generation unit generates personas for companies to use in formulating marketing strategies based on information obtained by the data analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment generates specific and detailed personas, enabling highly accurate market research and understanding of product reputation. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A market research system according to an embodiment of the present invention uses a generative AI to analyze big data and generate specific personas that can be used by companies to conduct market research and gauge the reputation of their products. This allows the market research system to provide market research services to companies and obtain highly accurate information.

[0029] A market research system according to an embodiment includes a generation unit, a data analysis unit, and a persona generation unit. The generation unit analyzes big data using a generation AI to generate specific personas. For example, the generation AI uses a text generation AI such as GPT-3 or BERT to analyze various information contained in the big data and generate a profile of a person with specific attributes and behavioral patterns. The generation AI can also analyze big data such as social media data and purchase history data to generate specific personas. The data analysis unit uses the personas generated by the generation unit to conduct reputation and market research on the company's products. For example, the data analysis unit analyzes how the generated personas evaluate the company's products. The data analysis unit can also analyze what areas for improvement the generated personas point out. Furthermore, the data analysis unit can simulate how the generated personas will react to a new product before it is released to the market. The persona generation unit generates personas based on information obtained by the data analysis unit to help companies develop marketing strategies. For example, the persona generation unit creates a marketing strategy tailored to the target demographic based on the attributes and behavioral patterns of the generated persona. The persona generation unit can also improve products and develop new products based on evaluations and improvements of the generated persona. This allows the market research system according to the embodiment to provide market research services for companies and obtain highly accurate information. For example, companies can use the generated persona to accurately understand the reputation of their products and create effective marketing strategies. Companies can also use the generated persona to understand market needs and trends before launching new products. Companies can also use the generated persona to create a marketing strategy tailored to the target demographic.

[0030] The generation unit can analyze various information contained in big data and generate a persona with specific attributes and behavioral patterns. The generation unit can analyze, for example, demographic data and behavioral data contained in big data to generate a persona with specific attributes and behavioral patterns. For example, the generation unit can combine information such as age, gender, occupation, hobbies, and purchase history to generate a specific persona. The generation unit can also analyze data such as social media posts, search history, and survey results to generate a persona with specific attributes and behavioral patterns. Furthermore, the generation unit can add an emotional profile to the generated persona using an emotion estimation function to simulate emotional reactions. For example, the generation unit can simulate how the generated persona reacts emotionally to a specific advertisement or promotion. The generation unit can also analyze how the generated persona feels toward a specific product or service. This allows for the generation of more specific and detailed personas by analyzing big data.

[0031] The generation unit can incorporate real-time behavioral data and provide a dynamically updated persona. The generation unit, for example, incorporates real-time behavioral data into the persona to be generated. For example, the generation unit reflects the persona's purchase history and website browsing history in real time. The generation unit can also dynamically update the generated persona based on the real-time behavioral data. For example, if the persona's interests or concerns change, the persona's attributes and behavioral patterns are updated accordingly. Furthermore, the generation unit can incorporate real-time behavioral data and provide a dynamically updated persona, thereby generating a more realistic character profile. For example, the persona's behavioral patterns are changed depending on the season or events. In this way, by incorporating real-time behavioral data, a more realistic persona can be generated.

[0032] The generation unit can predict future behavior by including a future purchasing prediction based on the purchasing history. The generation unit, for example, includes a future purchasing prediction based on past purchasing history in the persona to be generated. For example, the generation unit analyzes past data to predict future purchasing trends. The generation unit can also predict the future behavior of the generated persona by combining the past purchasing history with the future purchasing prediction. For example, the generation unit simulates purchasing behavior during a specific season or event. Furthermore, the generation unit can predict future behavior by including a future purchasing prediction. For example, it predicts the purchasing behavior of a persona before a new product is released to the market. This makes it possible to optimize marketing strategies by predicting future behavior based on past data.

[0033] The generation unit can reflect the characteristics of different cultural spheres and regions, enabling market research from a global perspective. The generation unit, for example, reflects the characteristics of different cultural spheres and regions in the personas it generates. For example, the generation unit generates personas that take into account the cultures and customs of each region. The generation unit can also conduct market research from a global perspective using personas that reflect the characteristics of different cultural spheres and regions. For example, the generation unit analyzes consumer behavior in each region and develops a marketing strategy. Furthermore, the generation unit can enable market research from a global perspective by reflecting the characteristics of different cultural spheres and regions. For example, the generation unit designs advertising campaigns that are tailored to the characteristics of each region. In this way, market research from a global perspective is possible by reflecting the characteristics of different cultural spheres and regions.

[0034] The generation unit can reflect the brand image and corporate philosophy and generate personas based on the brand strategy. The generation unit, for example, reflects the company's brand image and corporate philosophy in the persona to be generated. For example, the generation unit generates personas that match the company's values ​​and mission. The generation unit can also generate personas based on the company's brand strategy and optimize the marketing strategy. For example, it can identify a target demographic that matches the brand image. Furthermore, the generation unit can generate personas based on the brand strategy by reflecting the company's brand image and corporate philosophy. For example, it can generate an image of a consumer with high brand loyalty. In this way, it is possible to generate personas based on the brand strategy by reflecting the company's brand image and corporate philosophy.

[0035] The data analysis unit can integrate different data sources to generate personas from a more multifaceted perspective. For example, the data analysis unit integrates different data sources when analyzing big data. For example, data from IoT devices can be combined with social media data for analysis. The data analysis unit can also integrate different data sources to generate personas from a more multifaceted perspective. For example, in addition to purchase history and search history, behavioral data from IoT devices can be reflected. Furthermore, the data analysis unit can generate more specific and detailed personas by integrating different data sources when analyzing big data. For example, a persona that reflects lifestyle habits can be generated based on data from smart home devices. This makes it possible to generate more specific and detailed personas by integrating different data sources.

[0036] The data analysis unit can take into account temporal fluctuations and reflect changes in consumer behavior due to seasons and events. The data analysis unit, for example, takes into account temporal fluctuations when analyzing big data. For example, it analyzes changes in consumer behavior due to seasons and events and reflects this in persona generation. The data analysis unit can also generate personas that take into account temporal fluctuations and reflect changes in consumer behavior due to seasons and events. For example, it can reflect purchasing behavior in response to events such as Christmas and Valentine's Day. Furthermore, by taking into account temporal fluctuations when analyzing big data, the data analysis unit can generate personas that are closer to reality. For example, it generates personas based on changes in consumer behavior by season. In this way, by taking into account temporal fluctuations, it is possible to generate personas that are closer to reality.

[0037] The data analysis department can compare data from different industries and fields to gain cross-industry insights. For example, the data analysis department compares the results of big data analysis with data from different industries and fields. For example, data from the fashion industry and the food industry can be compared to analyze similarities and differences in consumer behavior. The data analysis department can also compare data from different industries and fields to gain cross-industry insights. For example, data from the technology industry and healthcare industry can be combined to develop new marketing strategies. Furthermore, the data analysis department can gain cross-industry insights by comparing the results of big data analysis with data from different industries and fields. For example, trends in different industries can be analyzed to discover new business opportunities. This allows new marketing strategies to be developed by comparing data from different industries and fields.

[0038] The data analysis unit can use a visualization tool to visually display the results of big data analysis, making it easier to understand intuitively. The data analysis unit, for example, visually displays the results of big data analysis using a visualization tool. For example, it can show data trends using graphs and charts. The data analysis unit can also use a visualization tool to make the results of big data analysis easier to understand intuitively. For example, it can create an interactive dashboard to allow users to manipulate the data. Furthermore, the data analysis unit can also promote understanding of the data by visually displaying the results of big data analysis using a visualization tool. For example, it can plot data on a map to show consumer behavior by region. In this way, using a visualization tool can promote understanding of the data.

[0039] The data analysis unit can track product reputation over time based on the purchase history and behavioral patterns of the persona, and grasp trends. The data analysis unit, for example, tracks product reputation over time based on the purchase history and behavioral patterns of the generated persona. For example, it analyzes fluctuations in reputation over a specific period of time. The data analysis unit can also track the reputation of the generated persona over time based on the purchase history and behavioral patterns, and grasp trends. For example, it analyzes fluctuations in reputation due to seasons or events. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by tracking product reputation over time based on the purchase history and behavioral patterns of the generated persona. For example, it analyzes fluctuations in reputation during a specific campaign period. In this way, trends can be grasped by tracking product reputation over time.

[0040] The data analysis unit can analyze the social media comments of the persona and monitor reputation in real time. The data analysis unit, for example, analyzes the social media comments of the generated persona and monitors reputation in real time. For example, it analyzes reputation based on specific keywords or hashtags. The data analysis unit can also monitor the reputation of the generated persona in real time based on the social media comments. For example, it calculates the ratio of positive comments and negative comments. Furthermore, the data analysis unit can analyze the social media comments of the generated persona and monitor reputation in real time, thereby predicting the effectiveness of a marketing strategy. For example, it analyzes fluctuations in reputation during a specific campaign period. This makes it possible to monitor reputation in real time by analyzing social media comments.

[0041] The data analysis unit can compare the results of the persona's reputation analysis in different markets or regions to clarify the differences in reputation between regions. The data analysis unit, for example, compares the results of the generated persona's reputation analysis in different markets or regions. For example, it analyzes the differences in consumer behavior and reputation in each region. The data analysis unit can also compare the results of the reputation analysis in different markets or regions to clarify the differences in reputation between regions. For example, it can identify products or services that have a high reputation in a particular region. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by comparing the results of the generated persona's reputation analysis in different markets or regions. For example, it can design an advertising campaign based on the differences in reputation between regions. This makes it possible to optimize marketing strategies for each region by clarifying the differences in reputation between different markets or regions.

[0042] The data analysis department can compare the results of the persona's reputation analysis with competitors' products to clarify the strengths and weaknesses of the company's products. For example, the data analysis department compares the results of the generated persona's reputation analysis with competitors' products. For example, it analyzes differences in reputation for specific features or designs. The data analysis department can also compare the results of the generated persona's reputation analysis with competitors' products to clarify the strengths and weaknesses of the company's products. For example, it analyzes positive and negative reputations for competitors' products. Furthermore, the data analysis department can predict the effectiveness of marketing strategies by comparing the results of the generated persona's reputation analysis with competitors' products. For example, it can design an advertising campaign that emphasizes the strengths of the company's products. This makes it possible to clarify the strengths and weaknesses of the company's products by comparing them with competitors' products.

[0043] The data analysis unit can predict sales after the new product is launched based on the purchase predictions of the persona. The data analysis unit, for example, predicts sales after the new product is launched based on the purchase predictions of the generated persona. For example, it predicts future purchasing trends based on past data. The data analysis unit can also predict sales after the new product is launched based on the purchase predictions. For example, it predicts sales fluctuations during specific seasons or events. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by predicting sales after the new product is launched based on the purchase predictions of the generated persona. For example, it predicts sales fluctuations during a specific campaign period. In this way, it is possible to predict the effectiveness of a marketing strategy by predicting sales after the new product is launched.

[0044] The data analysis unit can simulate the effectiveness of a marketing campaign for a new product based on the behavioral patterns of the persona. The data analysis unit, for example, simulates the effectiveness of a marketing campaign for a new product based on the behavioral patterns of the generated persona. For example, it analyzes responses to specific advertisements and promotions. The data analysis unit can also simulate the effectiveness of a marketing campaign for a new product based on the behavioral patterns. For example, it can predict the effectiveness of an advertisement for a specific target demographic. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by simulating the effectiveness of a marketing campaign for a new product based on the behavioral patterns of the generated persona. For example, it analyzes responses during a specific campaign period. In this way, it is possible to predict the effectiveness of a marketing strategy by simulating the effectiveness of a marketing campaign for a new product.

[0045] The data analysis unit can use the personas to conduct market research in different market segments and understand the needs of each segment. The data analysis unit, for example, uses the generated personas to conduct market research in different market segments. For example, different personas can be generated for products aimed at younger people and products aimed at older people, and the needs of each can be understood. The data analysis unit can also conduct market research in different market segments and understand the needs of each segment. For example, consumer behavior in specific regions or cultural areas can be analyzed. Furthermore, the data analysis unit can use the generated personas to conduct market research in different market segments and predict the effectiveness of marketing strategies. For example, an advertising campaign can be designed based on the needs of each segment. In this way, the needs of each segment can be understood by conducting market research in different market segments.

[0046] The data analysis unit can use the personas to simulate market responses to products in different price ranges. For example, the data analysis unit uses the generated personas to simulate market responses to products in different price ranges. For example, different personas are generated for products in high price ranges and products in low price ranges, and the responses to each are analyzed. The data analysis unit can also simulate market responses to products in different price ranges. For example, purchasing willingness and reputation in a specific price range are analyzed. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by simulating market responses to products in different price ranges using the generated personas. For example, an advertising campaign is designed based on the responses for each price range. In this way, the effectiveness of a marketing strategy can be predicted by simulating market responses to products in different price ranges.

[0047] The generation unit can generate a persona that reflects life events and responds to changes in life. The generation unit, for example, reflects life events in the persona to be generated. For example, the generation unit generates a persona that takes into account important life events such as marriage, childbirth, or changing jobs. The generation unit can also generate a persona that reflects life events and create a marketing strategy that responds to changes in life. For example, a persona that reflects consumption behavior after marriage or needs after childbirth is generated. Furthermore, the generation unit can generate a persona that responds to changes in life by reflecting life events. For example, a persona that reflects changes in career path or lifestyle after changing jobs is generated. In this way, a persona that responds to changes in life can be generated by reflecting life events.

[0048] The generation unit can generate a health-conscious consumer profile by reflecting the health condition and fitness data. The generation unit, for example, reflects the health condition and fitness data in the persona to be generated. For example, the generation unit generates a health-conscious consumer profile and formulates a marketing strategy for health-related products. The generation unit can also generate a persona that reflects the health condition and fitness data to generate a health-conscious consumer profile. For example, a persona that reflects fitness app usage status and health food purchase history is generated. Furthermore, the generation unit can also generate a health-conscious consumer profile by reflecting the health condition and fitness data. For example, a persona that reflects health checkup results and exercise habits is generated. In this way, a health-conscious consumer profile can be generated by reflecting the health condition and fitness data.

[0049] The generation unit can reflect cultural and religious backgrounds to enable multicultural market research. The generation unit, for example, reflects different cultural and religious backgrounds in the personas it generates. For example, the generation unit generates personas that take into account the characteristics of each culture and religion. The generation unit can also conduct multicultural market research using personas that reflect different cultural and religious backgrounds. For example, the generation unit analyzes consumer behavior in each cultural region and develops a marketing strategy. Furthermore, the generation unit can enable multicultural market research by reflecting different cultural and religious backgrounds. For example, the generation unit designs advertising campaigns that are tailored to the characteristics of each culture and religion. This enables multicultural market research by reflecting different cultural and religious backgrounds.

[0050] The generation unit can reflect life stages and grasp needs for each life stage. The generation unit, for example, reflects life stages in the personas to be generated. For example, the generation unit generates personas according to life stages such as students, working adults, and retirees. The generation unit can also grasp needs for each life stage by using personas that reflect different life stages. For example, the generation unit analyzes the purchasing behavior of students and the consumption patterns of retirees. Furthermore, the generation unit can grasp needs for each life stage by reflecting different life stages in the personas to be generated. For example, the generation unit generates personas that reflect the career path of working adults and the lifestyle of retirees. In this way, needs for each life stage can be grasped by reflecting different life stages.

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

[0052] The generation unit can also reflect health status and fitness data in the persona to be generated. For example, the generation unit generates a health-conscious consumer profile based on fitness app usage status and health food purchase history. The generation unit can also generate a persona that reflects health checkup results and exercise habits. Furthermore, the generation unit can generate a health-conscious consumer profile by reflecting health status and fitness data, and can also develop a marketing strategy for health-related products. In this way, a health-conscious consumer profile can be generated by reflecting health status and fitness data.

[0053] The data analysis unit can also track product reputation over time based on the purchase history and behavioral patterns of the generated personas. For example, it can analyze fluctuations in reputation over a specific period of time. The data analysis unit can also analyze fluctuations in reputation due to seasons or events, and track the reputation of the generated personas over time. Furthermore, the data analysis unit can predict the effectiveness of marketing strategies by analyzing fluctuations in reputation during specific campaign periods. In this way, trends can be identified by tracking product reputation over time.

[0054] The generation unit can also reflect life events in the personas it generates. For example, the generation unit generates personas that take into account important life events such as marriage, childbirth, and job changes. The generation unit can also generate personas that reflect consumption behavior after marriage and needs after childbirth. Furthermore, the generation unit can create marketing strategies that respond to life changes by generating personas that reflect career paths and lifestyle changes after job changes. In this way, by reflecting life events, it is possible to generate personas that respond to life changes.

[0055] The data analysis unit can also analyze the social media comments made by the generated personas and monitor their reputation in real time. For example, it can analyze reputation based on specific keywords or hashtags. The data analysis unit can also calculate the ratio of positive and negative comments and monitor the reputation of the generated personas in real time. Furthermore, the data analysis unit can predict the effectiveness of marketing strategies by analyzing fluctuations in reputation during a specific campaign period. This makes it possible to monitor reputation in real time by analyzing social media comments.

[0056] The generation unit can also reflect different cultural and religious backgrounds in the personas it generates. For example, the generation unit generates personas that take into account the characteristics of each culture and religion. The generation unit can also conduct multicultural market research using personas that reflect different cultural and religious backgrounds. Furthermore, the generation unit can analyze consumer behavior in each cultural region and develop marketing strategies. This makes it possible to conduct multicultural market research by reflecting different cultural and religious backgrounds.

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

[0058] Step 1: The generation unit uses generation AI to analyze the big data and generate a specific persona. For example, the generation AI uses text generation AI such as GPT-3 or BERT to analyze the diverse information contained in the big data and generate a persona with specific attributes and behavioral patterns. The generation AI can also analyze big data such as social media data and purchase history data to generate specific personas. Step 2: The data analysis department uses the personas generated by the generation department to conduct market research and evaluate the reputation of the company's products. For example, the data analysis department analyzes how the generated personas evaluate the company's products. The data analysis department can also analyze what areas of improvement the generated personas point out. Furthermore, the data analysis department can simulate how the generated personas will react to a new product before it is released to the market. Step 3: The persona generation department uses the information obtained by the data analysis department to generate personas that companies can use to develop marketing strategies. For example, the persona generation department can create marketing strategies tailored to the target demographic based on the attributes and behavioral patterns of the generated personas. The persona generation department can also improve products or develop new products based on evaluations and areas for improvement of the generated personas.

[0059] (Example 2) A market research system according to an embodiment of the present invention uses a generative AI to analyze big data and generate specific personas that can be used by companies to conduct market research and gauge the reputation of their products. This allows the market research system to provide market research services to companies and obtain highly accurate information.

[0060] A market research system according to an embodiment includes a generation unit, a data analysis unit, and a persona generation unit. The generation unit analyzes big data using a generation AI to generate specific personas. For example, the generation AI uses a text generation AI such as GPT-3 or BERT to analyze various information contained in the big data and generate a profile of a person with specific attributes and behavioral patterns. The generation AI can also analyze big data such as social media data and purchase history data to generate specific personas. The data analysis unit uses the personas generated by the generation unit to conduct reputation and market research on the company's products. For example, the data analysis unit analyzes how the generated personas evaluate the company's products. The data analysis unit can also analyze what areas for improvement the generated personas point out. Furthermore, the data analysis unit can simulate how the generated personas will react to a new product before it is released to the market. The persona generation unit generates personas based on information obtained by the data analysis unit to help companies develop marketing strategies. For example, the persona generation unit creates a marketing strategy tailored to the target demographic based on the attributes and behavioral patterns of the generated persona. The persona generation unit can also improve products and develop new products based on evaluations and improvements of the generated persona. This allows the market research system according to the embodiment to provide market research services for companies and obtain highly accurate information. For example, companies can use the generated persona to accurately understand the reputation of their products and create effective marketing strategies. Companies can also use the generated persona to understand market needs and trends before launching new products. Companies can also use the generated persona to create a marketing strategy tailored to the target demographic.

[0061] The generation unit can analyze various information contained in big data and generate a persona with specific attributes and behavioral patterns. The generation unit can analyze, for example, demographic data and behavioral data contained in big data to generate a persona with specific attributes and behavioral patterns. For example, the generation unit can combine information such as age, gender, occupation, hobbies, and purchase history to generate a specific persona. The generation unit can also analyze data such as social media posts, search history, and survey results to generate a persona with specific attributes and behavioral patterns. Furthermore, the generation unit can add an emotional profile to the generated persona using an emotion estimation function to simulate emotional reactions. For example, the generation unit can simulate how the generated persona reacts emotionally to a specific advertisement or promotion. The generation unit can also analyze how the generated persona feels toward a specific product or service. This allows for the generation of more specific and detailed personas by analyzing big data.

[0062] The data analysis unit can add an emotional profile to the persona using the emotion estimation function and simulate emotional responses. The data analysis unit, for example, adds an emotional profile to the generated persona using the emotion estimation function. For example, the data analysis unit simulates what kind of emotional response the generated persona will have to a specific advertisement or promotion. The data analysis unit can also analyze what kind of emotion the generated persona will have toward a specific product or service. Furthermore, the data analysis unit can add an emotional profile to the generated persona and simulate emotional responses, thereby predicting the effectiveness of a marketing strategy. For example, the data analysis unit designs an advertising campaign targeting personas with strong emotional responses. In this way, the effectiveness of the marketing strategy can be predicted by simulating emotional responses.

[0063] The generation unit can incorporate real-time behavioral data and provide a dynamically updated persona. The generation unit, for example, incorporates real-time behavioral data into the persona to be generated. For example, the generation unit reflects the persona's purchase history and website browsing history in real time. The generation unit can also dynamically update the generated persona based on the real-time behavioral data. For example, if the persona's interests or concerns change, the persona's attributes and behavioral patterns are updated accordingly. Furthermore, the generation unit can incorporate real-time behavioral data and provide a dynamically updated persona, thereby generating a more realistic character profile. For example, the persona's behavioral patterns are changed depending on the season or events. In this way, by incorporating real-time behavioral data, a more realistic persona can be generated.

[0064] The generation unit can predict future behavior by including a future purchasing prediction based on the purchasing history. The generation unit, for example, includes a future purchasing prediction based on past purchasing history in the persona to be generated. For example, the generation unit analyzes past data to predict future purchasing trends. The generation unit can also predict the future behavior of the generated persona by combining the past purchasing history with the future purchasing prediction. For example, the generation unit simulates purchasing behavior during a specific season or event. Furthermore, the generation unit can predict future behavior by including a future purchasing prediction. For example, it predicts the purchasing behavior of a persona before a new product is released to the market. This makes it possible to optimize marketing strategies by predicting future behavior based on past data.

[0065] The generation unit can reflect the characteristics of different cultural spheres and regions, enabling market research from a global perspective. The generation unit, for example, reflects the characteristics of different cultural spheres and regions in the personas it generates. For example, the generation unit generates personas that take into account the cultures and customs of each region. The generation unit can also conduct market research from a global perspective using personas that reflect the characteristics of different cultural spheres and regions. For example, the generation unit analyzes consumer behavior in each region and develops a marketing strategy. Furthermore, the generation unit can enable market research from a global perspective by reflecting the characteristics of different cultural spheres and regions. For example, the generation unit designs advertising campaigns that are tailored to the characteristics of each region. In this way, market research from a global perspective is possible by reflecting the characteristics of different cultural spheres and regions.

[0066] The generation unit can reflect the brand image and corporate philosophy and generate personas based on the brand strategy. The generation unit, for example, reflects the company's brand image and corporate philosophy in the persona to be generated. For example, the generation unit generates personas that match the company's values ​​and mission. The generation unit can also generate personas based on the company's brand strategy and optimize the marketing strategy. For example, it can identify a target demographic that matches the brand image. Furthermore, the generation unit can generate personas based on the brand strategy by reflecting the company's brand image and corporate philosophy. For example, it can generate an image of a consumer with high brand loyalty. In this way, it is possible to generate personas based on the brand strategy by reflecting the company's brand image and corporate philosophy.

[0067] The data analysis unit can use the emotion estimation function to simulate how a persona will emotionally react to a specific advertisement or promotion. For example, the data analysis unit uses the emotion estimation function to simulate how a generated persona will emotionally react to a specific advertisement. For example, the data analysis unit analyzes emotional reactions to the content and design of the advertisement. The data analysis unit can also simulate how a generated persona will emotionally react to a specific promotion. For example, the data analysis unit analyzes emotional reactions to discount campaigns and special offers. Furthermore, the data analysis unit can use the emotion estimation function to simulate how a generated persona will emotionally react to a specific advertisement or promotion, thereby predicting the effectiveness of a marketing strategy. For example, an advertising campaign can be designed that targets personas with strong emotional reactions. In this way, the effectiveness of a marketing strategy can be predicted by simulating emotional reactions.

[0068] The data analysis unit can use the emotion estimation function to extract emotional trends in big data and reflect them in persona generation. For example, the data analysis unit uses the emotion estimation function to extract emotional trends in the data when analyzing big data. For example, it analyzes trends in positive and negative emotions from social media posts. The data analysis unit can also use the emotion estimation function to extract emotional trends in big data and reflect them in persona generation. For example, it can generate personas based on emotional reactions to specific products or services. Furthermore, the data analysis unit can use the emotion estimation function to extract emotional trends in the data when analyzing big data and reflect them in marketing strategies. For example, it can design advertising campaigns based on emotional trends. In this way, by reflecting emotional trends, it is possible to generate personas that are closer to reality.

[0069] The data analysis unit can integrate different data sources to generate personas from a more multifaceted perspective. For example, the data analysis unit integrates different data sources when analyzing big data. For example, data from IoT devices can be combined with social media data for analysis. The data analysis unit can also integrate different data sources to generate personas from a more multifaceted perspective. For example, in addition to purchase history and search history, behavioral data from IoT devices can be reflected. Furthermore, the data analysis unit can generate more specific and detailed personas by integrating different data sources when analyzing big data. For example, a persona that reflects lifestyle habits can be generated based on data from smart home devices. This makes it possible to generate more specific and detailed personas by integrating different data sources.

[0070] The data analysis unit can take into account temporal fluctuations and reflect changes in consumer behavior due to seasons and events. The data analysis unit, for example, takes into account temporal fluctuations when analyzing big data. For example, it analyzes changes in consumer behavior due to seasons and events and reflects this in persona generation. The data analysis unit can also generate personas that take into account temporal fluctuations and reflect changes in consumer behavior due to seasons and events. For example, it can reflect purchasing behavior in response to events such as Christmas and Valentine's Day. Furthermore, by taking into account temporal fluctuations when analyzing big data, the data analysis unit can generate personas that are closer to reality. For example, it generates personas based on changes in consumer behavior by season. In this way, by taking into account temporal fluctuations, it is possible to generate personas that are closer to reality.

[0071] The data analysis department can compare data from different industries and fields to gain cross-industry insights. For example, the data analysis department compares the results of big data analysis with data from different industries and fields. For example, data from the fashion industry and the food industry can be compared to analyze similarities and differences in consumer behavior. The data analysis department can also compare data from different industries and fields to gain cross-industry insights. For example, data from the technology industry and healthcare industry can be combined to develop new marketing strategies. Furthermore, the data analysis department can gain cross-industry insights by comparing the results of big data analysis with data from different industries and fields. For example, trends in different industries can be analyzed to discover new business opportunities. This allows new marketing strategies to be developed by comparing data from different industries and fields.

[0072] The data analysis unit can use a visualization tool to visually display the results of big data analysis, making it easier to understand intuitively. The data analysis unit, for example, visually displays the results of big data analysis using a visualization tool. For example, it can show data trends using graphs and charts. The data analysis unit can also use a visualization tool to make the results of big data analysis easier to understand intuitively. For example, it can create an interactive dashboard to allow users to manipulate the data. Furthermore, the data analysis unit can also promote understanding of the data by visually displaying the results of big data analysis using a visualization tool. For example, it can plot data on a map to show consumer behavior by region. In this way, using a visualization tool can promote understanding of the data.

[0073] The data analysis unit can use the emotion estimation function to analyze consumer emotional responses in big data and reflect them in marketing strategies. The data analysis unit, for example, uses the emotion estimation function to analyze consumer emotional responses in big data. For example, it extracts positive and negative emotions from social media posts. The data analysis unit can also analyze consumer emotional responses in big data and reflect them in marketing strategies. For example, it can identify products and services with strong emotional responses and design advertising campaigns. Furthermore, the data analysis unit can use the emotion estimation function to analyze consumer emotional responses in big data and reflect them in marketing strategies. For example, it can develop and promote new products based on emotional trends. In this way, it is possible to optimize marketing strategies by analyzing consumer emotional responses.

[0074] The data analysis unit can use the emotion estimation function to analyze how the persona emotionally reacts to the reputation of the company's products. For example, the data analysis unit uses the emotion estimation function of the generated persona to analyze the emotional reaction to the reputation of the company's products. For example, the data analysis unit calculates the ratio of positive and negative emotions. The data analysis unit can also use the emotion estimation function to analyze how the generated persona feels about the reputation of the company's products. For example, the data analysis unit analyzes the emotional reaction to a specific feature or design. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by analyzing the emotional reaction to the reputation of the company's products using the emotion estimation function of the generated persona. For example, an advertising campaign can be designed that targets personas with strong emotional reactions. In this way, the effectiveness of a marketing strategy can be predicted by analyzing the emotional reaction to the reputation of the company's products.

[0075] The data analysis unit can track product reputation over time based on the purchase history and behavioral patterns of the persona, and grasp trends. The data analysis unit, for example, tracks product reputation over time based on the purchase history and behavioral patterns of the generated persona. For example, it analyzes fluctuations in reputation over a specific period of time. The data analysis unit can also track the reputation of the generated persona over time based on the purchase history and behavioral patterns, and grasp trends. For example, it analyzes fluctuations in reputation due to seasons or events. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by tracking product reputation over time based on the purchase history and behavioral patterns of the generated persona. For example, it analyzes fluctuations in reputation during a specific campaign period. In this way, trends can be grasped by tracking product reputation over time.

[0076] The data analysis unit can analyze the social media comments of the persona and monitor reputation in real time. The data analysis unit, for example, analyzes the social media comments of the generated persona and monitors reputation in real time. For example, it analyzes reputation based on specific keywords or hashtags. The data analysis unit can also monitor the reputation of the generated persona in real time based on the social media comments. For example, it calculates the ratio of positive comments and negative comments. Furthermore, the data analysis unit can analyze the social media comments of the generated persona and monitor reputation in real time, thereby predicting the effectiveness of a marketing strategy. For example, it analyzes fluctuations in reputation during a specific campaign period. This makes it possible to monitor reputation in real time by analyzing social media comments.

[0077] The data analysis unit can compare the results of the persona's reputation analysis in different markets or regions to clarify the differences in reputation between regions. The data analysis unit, for example, compares the results of the generated persona's reputation analysis in different markets or regions. For example, it analyzes the differences in consumer behavior and reputation in each region. The data analysis unit can also compare the results of the reputation analysis in different markets or regions to clarify the differences in reputation between regions. For example, it can identify products or services that have a high reputation in a particular region. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by comparing the results of the generated persona's reputation analysis in different markets or regions. For example, it can design an advertising campaign based on the differences in reputation between regions. This makes it possible to optimize marketing strategies for each region by clarifying the differences in reputation between different markets or regions.

[0078] The data analysis department can compare the results of the persona's reputation analysis with competitors' products to clarify the strengths and weaknesses of the company's products. For example, the data analysis department compares the results of the generated persona's reputation analysis with competitors' products. For example, it analyzes differences in reputation for specific features or designs. The data analysis department can also compare the results of the generated persona's reputation analysis with competitors' products to clarify the strengths and weaknesses of the company's products. For example, it analyzes positive and negative reputations for competitors' products. Furthermore, the data analysis department can predict the effectiveness of marketing strategies by comparing the results of the generated persona's reputation analysis with competitors' products. For example, it can design an advertising campaign that emphasizes the strengths of the company's products. This makes it possible to clarify the strengths and weaknesses of the company's products by comparing them with competitors' products.

[0079] The data analysis unit can use the emotion estimation function to simulate how the persona will emotionally react to advertisements and promotions for the company's products. For example, the data analysis unit uses the emotion estimation function to simulate how the generated persona will emotionally react to advertisements for the company's products. For example, the data analysis unit analyzes emotional reactions to the content and design of the advertisements. The data analysis unit can also simulate how the generated persona will emotionally react to promotions for the company's products. For example, the data analysis unit analyzes emotional reactions to discount campaigns and special offers. Furthermore, the data analysis unit can use the emotion estimation function to simulate how the generated persona will emotionally react to advertisements and promotions for the company's products, thereby predicting the effectiveness of a marketing strategy. For example, an advertising campaign targeting personas with strong emotional reactions can be designed. In this way, the effectiveness of a marketing strategy can be predicted by simulating emotional reactions to advertisements and promotions for the company's products.

[0080] The data analysis unit can use the emotion estimation function to simulate what kind of emotional reactions a persona will have before a new product is launched to the market. For example, the data analysis unit uses the emotion estimation function of the generated persona to simulate emotional reactions before a new product is launched to the market. For example, the data analysis unit analyzes emotional reactions to the design and functions of the new product. The data analysis unit can also use the emotion estimation function to simulate what kind of emotions a generated persona will have before a new product is launched to the market. For example, the data analysis unit calculates the proportion of positive emotions and negative emotions. Furthermore, the data analysis unit can use the emotion estimation function of the generated persona to simulate emotional reactions before a new product is launched to predict the effectiveness of a marketing strategy. For example, an advertising campaign is designed that targets personas with strong emotional reactions. In this way, the effectiveness of a marketing strategy can be predicted by simulating emotional reactions before a new product is launched to the market.

[0081] The data analysis unit can predict sales after the new product is launched based on the purchase predictions of the persona. The data analysis unit, for example, predicts sales after the new product is launched based on the purchase predictions of the generated persona. For example, it predicts future purchasing trends based on past data. The data analysis unit can also predict sales after the new product is launched based on the purchase predictions. For example, it predicts sales fluctuations during specific seasons or events. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by predicting sales after the new product is launched based on the purchase predictions of the generated persona. For example, it predicts sales fluctuations during a specific campaign period. In this way, it is possible to predict the effectiveness of a marketing strategy by predicting sales after the new product is launched.

[0082] The data analysis unit can simulate the effectiveness of a marketing campaign for a new product based on the behavioral patterns of the persona. The data analysis unit, for example, simulates the effectiveness of a marketing campaign for a new product based on the behavioral patterns of the generated persona. For example, it analyzes responses to specific advertisements and promotions. The data analysis unit can also simulate the effectiveness of a marketing campaign for a new product based on the behavioral patterns. For example, it can predict the effectiveness of an advertisement for a specific target demographic. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by simulating the effectiveness of a marketing campaign for a new product based on the behavioral patterns of the generated persona. For example, it analyzes responses during a specific campaign period. In this way, it is possible to predict the effectiveness of a marketing strategy by simulating the effectiveness of a marketing campaign for a new product.

[0083] The data analysis unit can use the personas to conduct market research in different market segments and understand the needs of each segment. The data analysis unit, for example, uses the generated personas to conduct market research in different market segments. For example, different personas can be generated for products aimed at younger people and products aimed at older people, and the needs of each can be understood. The data analysis unit can also conduct market research in different market segments and understand the needs of each segment. For example, consumer behavior in specific regions or cultural areas can be analyzed. Furthermore, the data analysis unit can use the generated personas to conduct market research in different market segments and predict the effectiveness of marketing strategies. For example, an advertising campaign can be designed based on the needs of each segment. In this way, the needs of each segment can be understood by conducting market research in different market segments.

[0084] The data analysis unit can use the personas to simulate market responses to products in different price ranges. For example, the data analysis unit uses the generated personas to simulate market responses to products in different price ranges. For example, different personas are generated for products in high price ranges and products in low price ranges, and the responses to each are analyzed. The data analysis unit can also simulate market responses to products in different price ranges. For example, purchasing willingness and reputation in a specific price range are analyzed. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by simulating market responses to products in different price ranges using the generated personas. For example, an advertising campaign is designed based on the responses for each price range. In this way, the effectiveness of a marketing strategy can be predicted by simulating market responses to products in different price ranges.

[0085] The data analysis unit can use the emotion estimation function to simulate the emotional reactions that a persona will have to the design and functions of a new product. For example, the data analysis unit uses the emotion estimation function to simulate the emotional reactions that a generated persona will have to the design of a new product. For example, the emotional reactions to the color and shape of the design are analyzed. The data analysis unit can also simulate the emotional reactions that a generated persona will have to the functions of a new product. For example, the emotional reactions to specific functions and usability are analyzed. Furthermore, the data analysis unit can use the emotion estimation function to simulate the emotional reactions that a generated persona will have to the design and functions of a new product, thereby predicting the effectiveness of a marketing strategy. For example, an advertising campaign can be designed targeting personas with strong emotional reactions. In this way, the effectiveness of a marketing strategy can be predicted by simulating the emotional reactions to the design and functions of a new product.

[0086] The generation unit can use the emotion estimation function to add emotional diversity to the persona, thereby generating a more realistic character image. For example, the generation unit uses the emotion estimation function to add emotional diversity to the persona to be generated. For example, the generation unit generates multiple personas with different emotional states. The generation unit can also use the emotion estimation function to add emotional diversity to the generated persona, thereby generating a more realistic character image. For example, it can generate personas with positive emotions and negative emotions. Furthermore, the generation unit can use the emotion estimation function to add emotional diversity to the generated persona, thereby predicting the effectiveness of a marketing strategy. For example, an advertising campaign can be designed that targets personas with different emotional responses. In this way, adding emotional diversity can generate a more realistic character image.

[0087] The generation unit can generate a persona that reflects life events and responds to changes in life. The generation unit, for example, reflects life events in the persona to be generated. For example, the generation unit generates a persona that takes into account important life events such as marriage, childbirth, or changing jobs. The generation unit can also generate a persona that reflects life events and create a marketing strategy that responds to changes in life. For example, a persona that reflects consumption behavior after marriage or needs after childbirth is generated. Furthermore, the generation unit can generate a persona that responds to changes in life by reflecting life events. For example, a persona that reflects changes in career path or lifestyle after changing jobs is generated. In this way, a persona that responds to changes in life can be generated by reflecting life events.

[0088] The generation unit can generate a health-conscious consumer profile by reflecting the health condition and fitness data. The generation unit, for example, reflects the health condition and fitness data in the persona to be generated. For example, the generation unit generates a health-conscious consumer profile and formulates a marketing strategy for health-related products. The generation unit can also generate a persona that reflects the health condition and fitness data to generate a health-conscious consumer profile. For example, a persona that reflects fitness app usage status and health food purchase history is generated. Furthermore, the generation unit can also generate a health-conscious consumer profile by reflecting the health condition and fitness data. For example, a persona that reflects health checkup results and exercise habits is generated. In this way, a health-conscious consumer profile can be generated by reflecting the health condition and fitness data.

[0089] The generation unit can reflect cultural and religious backgrounds to enable multicultural market research. The generation unit, for example, reflects different cultural and religious backgrounds in the personas it generates. For example, the generation unit generates personas that take into account the characteristics of each culture and religion. The generation unit can also conduct multicultural market research using personas that reflect different cultural and religious backgrounds. For example, the generation unit analyzes consumer behavior in each cultural region and develops a marketing strategy. Furthermore, the generation unit can enable multicultural market research by reflecting different cultural and religious backgrounds. For example, the generation unit designs advertising campaigns that are tailored to the characteristics of each culture and religion. This enables multicultural market research by reflecting different cultural and religious backgrounds.

[0090] The generation unit can reflect life stages and grasp needs for each life stage. The generation unit, for example, reflects life stages in the personas to be generated. For example, the generation unit generates personas according to life stages such as students, working adults, and retirees. The generation unit can also grasp needs for each life stage by using personas that reflect different life stages. For example, the generation unit analyzes the purchasing behavior of students and the consumption patterns of retirees. Furthermore, the generation unit can grasp needs for each life stage by reflecting different life stages in the personas to be generated. For example, the generation unit generates personas that reflect the career path of working adults and the lifestyle of retirees. In this way, needs for each life stage can be grasped by reflecting different life stages.

[0091] The generation unit can use the emotion estimation function to simulate how the persona will emotionally react to specific social or environmental issues. For example, the generation unit can use the emotion estimation function to simulate how the generated persona will emotionally react to specific social issues. For example, the generation unit can analyze emotional reactions to environmental protection or social justice. The generation unit can also simulate how the generated persona will emotionally react to specific environmental issues. For example, the generation unit can analyze emotional reactions to climate change or recycling. Furthermore, the generation unit can use the emotion estimation function to simulate how the generated persona will emotionally react to specific social or environmental issues, thereby predicting the effectiveness of a marketing strategy. For example, the generation unit can design an advertising campaign targeting personas with strong emotional reactions. This allows the effectiveness of a marketing strategy to be predicted by simulating emotional reactions to social or environmental issues.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The generation unit can also reflect health status and fitness data in the persona to be generated. For example, the generation unit generates a health-conscious consumer profile based on fitness app usage status and health food purchase history. The generation unit can also generate a persona that reflects health checkup results and exercise habits. Furthermore, the generation unit can generate a health-conscious consumer profile by reflecting health status and fitness data, and can also develop a marketing strategy for health-related products. In this way, a health-conscious consumer profile can be generated by reflecting health status and fitness data.

[0094] The data analysis unit can also track product reputation over time based on the purchase history and behavioral patterns of the generated personas. For example, it can analyze fluctuations in reputation over a specific period of time. The data analysis unit can also analyze fluctuations in reputation due to seasons or events, and track the reputation of the generated personas over time. Furthermore, the data analysis unit can predict the effectiveness of marketing strategies by analyzing fluctuations in reputation during specific campaign periods. In this way, trends can be identified by tracking product reputation over time.

[0095] The generation unit can also reflect life events in the personas it generates. For example, the generation unit generates personas that take into account important life events such as marriage, childbirth, and job changes. The generation unit can also generate personas that reflect consumption behavior after marriage and needs after childbirth. Furthermore, the generation unit can create marketing strategies that respond to life changes by generating personas that reflect career paths and lifestyle changes after job changes. In this way, by reflecting life events, it is possible to generate personas that respond to life changes.

[0096] The data analysis unit can also analyze the social media comments made by the generated personas and monitor their reputation in real time. For example, it can analyze reputation based on specific keywords or hashtags. The data analysis unit can also calculate the ratio of positive and negative comments and monitor the reputation of the generated personas in real time. Furthermore, the data analysis unit can predict the effectiveness of marketing strategies by analyzing fluctuations in reputation during a specific campaign period. This makes it possible to monitor reputation in real time by analyzing social media comments.

[0097] The generation unit can also reflect different cultural and religious backgrounds in the personas it generates. For example, the generation unit generates personas that take into account the characteristics of each culture and religion. The generation unit can also conduct multicultural market research using personas that reflect different cultural and religious backgrounds. Furthermore, the generation unit can analyze consumer behavior in each cultural region and develop marketing strategies. This makes it possible to conduct multicultural market research by reflecting different cultural and religious backgrounds.

[0098] The data analysis unit can also use the emotion estimation function to simulate how the generated persona will emotionally react to a specific advertisement or promotion. For example, it analyzes emotional reactions to the content and design of an advertisement. The data analysis unit can also simulate how the generated persona will emotionally react to a specific promotion. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by designing an advertising campaign that targets personas with strong emotional reactions. In this way, the effectiveness of a marketing strategy can be predicted by simulating emotional reactions.

[0099] The generator can also use the emotion estimation function to add emotional diversity to the generated personas. For example, the generator can generate multiple personas with different emotional states. The generator can also generate personas with positive and negative emotions. Furthermore, the generator can predict the effectiveness of marketing strategies by designing advertising campaigns that target personas with different emotional responses. This allows for the generation of more realistic personas by adding emotional diversity.

[0100] The data analysis unit can also use the emotion estimation function to simulate the emotional reactions that the generated personas will have before a new product is launched. For example, it analyzes emotional reactions to the design and features of a new product. The data analysis unit can also calculate the proportion of positive and negative emotions to simulate the emotions that the generated personas will have before a new product is launched. Furthermore, the data analysis unit can predict the effectiveness of a marketing strategy by designing an advertising campaign that targets personas with strong emotional reactions. This makes it possible to predict the effectiveness of a marketing strategy by simulating emotional reactions before a new product is launched.

[0101] The data analysis unit can also use the emotion estimation function to analyze how the generated personas emotionally react to the reputation of the company's products. For example, it can calculate the percentage of positive and negative emotions. The data analysis unit can also analyze emotional reactions to specific features or designs. Furthermore, the data analysis unit can predict the effectiveness of marketing strategies by designing advertising campaigns that target personas with strong emotional reactions. This makes it possible to predict the effectiveness of marketing strategies by analyzing emotional reactions to the reputation of the company's products.

[0102] The data analysis unit can also use the emotion estimation function to analyze consumers' emotional responses in big data and reflect them in marketing strategies. For example, it can extract positive and negative emotions from social media posts. The data analysis unit can also identify products and services that evoke strong emotional responses and design advertising campaigns. Furthermore, the data analysis unit can predict the effectiveness of marketing strategies by developing and promoting new products based on emotional trends. This allows marketing strategies to be optimized by analyzing consumers' emotional responses.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The generation unit uses generation AI to analyze the big data and generate a specific persona. For example, the generation AI uses text generation AI such as GPT-3 or BERT to analyze the diverse information contained in the big data and generate a persona with specific attributes and behavioral patterns. The generation AI can also analyze big data such as social media data and purchase history data to generate specific personas. Step 2: The data analysis department uses the personas generated by the generation department to conduct market research and evaluate the reputation of the company's products. For example, the data analysis department analyzes how the generated personas evaluate the company's products. The data analysis department can also analyze what areas of improvement the generated personas point out. Furthermore, the data analysis department can simulate how the generated personas will react to a new product before it is released to the market. Step 3: The persona generation department uses the information obtained by the data analysis department to generate personas that companies can use to develop marketing strategies. For example, the persona generation department can create marketing strategies tailored to the target demographic based on the attributes and behavioral patterns of the generated personas. The persona generation department can also improve products or develop new products based on evaluations and areas for improvement of the generated personas.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0118] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0119] 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.

[0120] 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.

[0121] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] 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.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0134] 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.

[0135] 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.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] 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.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] 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.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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]

[0172] 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 generation part that uses generative AI to analyze big data and generate specific personas; a data analysis unit that uses the personas generated by the generation unit to conduct market research and reputation research on the company's products; and a persona generation unit for enabling a company to formulate a marketing strategy based on the information obtained by the data analysis unit. A system characterized by:

2. The generation unit Analyze the diverse information contained in the big data and generate a profile of a person with specific attributes and behavioral patterns.

2. The system of claim 1.

3. The data analysis unit Adding an emotional profile to the persona to simulate emotional responses 2. The system of claim 1.

4. The generation unit Incorporates real-time behavioral data to provide dynamically updated personas 2. The system of claim 1.

5. The generation unit Predict future behavior by including future purchase predictions based on purchase history 2. The system of claim 1.

Images