System

Abstract

An object of the system according to the embodiment is to formulate a marketing strategy based on customer data and to verify and optimize the effect thereof.SOLUTION: A system includes a data collection part, an analysis part, a strategy formulation part, a test execution part, and an optimization part. The data collection unit collects customer data. The analysis unit analyzes the customer data collected by the data collection unit. The strategy formulation unit formulates a marketing strategy based on the result analyzed by the analysis unit. The test execution unit executes the A / B test to verify the effect of the marketing strategy formulated by the strategy formulation unit. The optimization unit optimizes the marketing strategy based on the result obtained by the test execution 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 technologies do not adequately formulate marketing strategies based on customer data and verify their effectiveness, leaving room for improvement.

[0005] The system according to the embodiment aims to formulate a marketing strategy based on customer data and to verify and optimize its effectiveness. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, an analysis unit, a strategy formulation unit, a test implementation unit, and an optimization unit. The data collection unit collects customer data. The analysis unit analyzes the customer data collected by the data collection unit. The strategy formulation unit formulates a marketing strategy based on the results of the analysis by the analysis unit. The test implementation unit conducts A / B testing to verify the effectiveness of the marketing strategy formulated by the strategy formulation unit. The optimization unit optimizes the marketing strategy based on the results obtained by the test implementation unit. [Effects of the Invention]

[0007] The system according to the embodiment can formulate a marketing strategy based on customer data, and verify and optimize its effectiveness. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) A marketing system according to an embodiment of the present invention is a system that utilizes AI to collect and analyze customer data and formulate, implement, and optimize personalized marketing strategies, thereby enabling the marketing system to understand customer behavior patterns and provide optimal marketing strategies.

[0029] A marketing system according to an embodiment includes a data collection unit, an analysis unit, a strategy formulation unit, a test implementation unit, and an optimization unit. The data collection unit collects customer data, such as website access logs, purchase histories, and email open rates. The data collection unit can also collect data such as customer behavioral histories and click rates. The analysis unit analyzes the customer data collected by the data collection unit. For example, a generation AI analyzes customer behavior patterns and finds patterns such as customers who frequently visit specific product pages or customers who open emails at specific times of the day. The generation AI can use a text generation AI (e.g., LLM) or a multimodal generation AI to analyze customer data in detail. The strategy formulation unit formulates a marketing strategy based on the results of the analysis by the analysis unit. For example, the generation AI provides promotional information related to a specific product to customers who are highly interested in a specific service. The generation AI also predicts which products are likely to be purchased next based on past purchase history and provides information about the product. The test implementation unit conducts A / B tests to verify the effectiveness of the marketing strategy formulated by the strategy formulation unit. For example, the generation AI tests different wordings of promotional messages for the same service to see which strategy obtains a higher click-through rate. The generation AI analyzes the test results and determines which strategy is most effective. The optimization unit optimizes the marketing strategy based on the results obtained by the test implementation unit. For example, the generation AI analyzes the test results, extracts effective elements, and reflects them in the strategy. In this way, the marketing system according to the embodiment can collect and analyze customer data and formulate, implement, and optimize personalized marketing strategies.

[0030] The data collection unit tracks customers' social media activities and analyzes them with generative AI to understand their online behavior patterns. For example, the data collection unit collects customers' Twitter and Facebook posts and analyzes them with generative AI. For example, it identifies what topics customers are interested in. The data collection unit also collects customers' Instagram posts and analyzes them with generative AI. For example, it analyzes what images and videos customers post and identifies their areas of interest. Furthermore, the data collection unit can track customers' LinkedIn activity and analyze it with generative AI. For example, it identifies what industries and job types customers are interested in. This allows the company to understand customers' online behavior patterns and develop more effective marketing strategies.

[0031] The data collection unit can collect customer purchase history, return history, and customer support inquiries, and then comprehensively analyze them using generation AI. For example, the data collection unit collects customer purchase history and return history and analyzes them using generation AI. For example, it can identify what types of products are likely to be returned. The data collection unit also collects customer support inquiries and analyzes them using generation AI. For example, it can identify what problems customers are having and consider countermeasures. Furthermore, the data collection unit can comprehensively collect customer purchase history, return history, and customer support inquiries, and analyze them using generation AI. For example, it can comprehensively analyze what products customers are satisfied with and what products they are dissatisfied with. This allows for the comprehensive analysis of customer purchase history, return history, and customer support inquiries to be used to develop more effective marketing strategies.

[0032] The data collection unit collects customer location data and analyzes it with the generation AI, thereby identifying regional behavioral patterns. For example, the data collection unit collects location data from customers' smartphones and analyzes it with the generation AI. For example, it identifies purchasing behavior in a specific region. The data collection unit also collects customers' GPS data and analyzes it with the generation AI. For example, it identifies the types of places customers frequently visit. Furthermore, the data collection unit can also collect customers' Wi-Fi location information and analyze it with the generation AI. For example, it identifies the types of stores and facilities customers visit. This allows it to identify regional behavioral patterns and develop marketing strategies tailored to each region.

[0033] The data collection unit collects biometric data from customers' wearable devices and analyzes it with generation AI, allowing the company to develop marketing strategies based on their health status and lifestyle habits. For example, the data collection unit collects heart rate data from customers' smartwatches and analyzes it with generation AI. For example, the data collection unit identifies the customer's stress level. The data collection unit also collects step count data from customers' fitness trackers and analyzes it with generation AI. For example, the data collection unit identifies the customer's exercise habits. Furthermore, the data collection unit can collect sleep data from customers' wearable devices and analyze it with generation AI. For example, the data collection unit identifies the customer's sleep patterns and evaluates their health status. This allows the company to develop marketing strategies based on their health status and lifestyle habits.

[0034] The strategy formulation department can combine a customer's past purchase history with current behavioral data to use generation AI to predict future purchases and develop marketing strategies based on that. For example, the strategy formulation department can combine a customer's past purchase history with current website browsing data to use generation AI to predict future purchases. For example, it can identify the products that are likely to be purchased next. The strategy formulation department can also combine a customer's past purchase history with current click data to use generation AI to predict future purchases. For example, it can identify the links that are likely to be clicked next. Furthermore, the strategy formulation department can combine a customer's past purchase history with current email open data to use generation AI to predict future purchases. For example, it can identify the email that is likely to be opened next. This makes it possible to develop marketing strategies based on future purchase predictions.

[0035] The strategy formulation department can predict customer life events and provide personalized promotions accordingly. For example, the strategy formulation department analyzes customer social media posts to predict life events such as marriage and childbirth. For example, it promotes wedding-related products to customers who are planning to get married. The strategy formulation department can also analyze customer purchase histories to predict life events such as moving. For example, it promotes moving-related products to customers who are planning to move. Furthermore, the strategy formulation department can analyze customer survey results to predict life events. For example, it promotes baby products to customers who are planning to give birth. This makes it possible to provide personalized promotions according to customer life events.

[0036] The strategy formulation department can use generative AI to automatically generate content based on customers' hobbies and interests, and incorporate it into a personalized marketing strategy. For example, the strategy formulation department analyzes customers' social media posts to identify their hobbies and interests. For example, it automatically generates travel-related content for customers who like to travel. The strategy formulation department also analyzes customer survey results to identify their hobbies and interests. For example, it automatically generates music-related content for customers who like music. Furthermore, the strategy formulation department can analyze customers' purchasing history to identify their hobbies and interests. For example, it automatically generates sports-related content for customers who frequently purchase sports equipment. This makes it possible to automatically generate content based on customers' hobbies and interests, and incorporate it into a personalized marketing strategy.

[0037] The strategy formulation department can compare a customer's purchase history with data from other customers and formulate a common marketing strategy for customer groups with similar behavioral patterns. For example, the strategy formulation department analyzes customer purchase histories to identify customer groups with similar behavioral patterns. For example, a common promotion is run for customer groups that frequently purchase the same products. The strategy formulation department can also analyze customer behavioral data to identify customer groups with similar behavioral patterns. For example, a common promotion is run for customer groups that frequently visit the same website. Furthermore, the strategy formulation department can analyze customer survey results to identify customer groups with similar behavioral patterns. For example, a common promotion is run for customer groups with the same interests. This makes it possible to formulate a common marketing strategy for customer groups with similar behavioral patterns.

[0038] The test implementation department can improve the accuracy of test results by collecting real-time behavioral data of customers during the test period and analyzing it with generation AI. For example, the test implementation department can collect customer website browsing data in real time during the test period and analyze it with generation AI. For example, it can identify which pages are viewed the most. The test implementation department can also collect customer click data in real time during the test period and analyze it with generation AI. For example, it can identify which links are clicked the most. Furthermore, the test implementation department can collect customer email opening data in real time during the test period and analyze it with generation AI. For example, it can identify which emails are opened the most. In this way, by collecting and analyzing real-time behavioral data of customers during the test period, it can improve the accuracy of test results.

[0039] The test implementation department can apply the results of the A / B test to other marketing channels and analyze them comprehensively using generative AI. For example, the test implementation department can apply the results of the A / B test to email marketing and analyze them using generative AI. For example, it can identify the most effective email wording. The test implementation department can also apply the results of the A / B test to social media marketing and analyze them using generative AI. For example, it can identify the most effective social media post. The test implementation department can also apply the results of the A / B test to online advertising and analyze them using generative AI. For example, it can identify the most effective advertising wording. In this way, the results of the A / B test can be applied to other marketing channels and analyzed comprehensively, allowing for the development of a more effective marketing strategy.

[0040] The test implementation department can conduct A / B tests simultaneously in different regions and cultural areas and compare and analyze the results using generative AI. For example, the test implementation department can conduct A / B tests simultaneously in different regions and compare and analyze the results using generative AI. For example, it can identify differences in responses between urban and rural areas. The test implementation department can also conduct A / B tests simultaneously in different cultural areas and compare and analyze the results using generative AI. For example, it can identify differences in responses between Asia and Europe. Furthermore, the test implementation department can conduct A / B tests simultaneously in different age groups and compare and analyze the results using generative AI. For example, it can identify differences in responses between younger and older groups. This allows A / B tests to be conducted simultaneously in different regions and cultural areas and the results to be compared and analyzed, making it possible to develop marketing strategies tailored to each region and culture.

[0041] The optimization unit can automatically generate a new marketing strategy using a generative AI based on the results of an A / B test and continuously optimize it. The optimization unit, for example, develops a system that automatically generates a new marketing strategy using a generative AI based on the results of an A / B test. For example, it generates a strategy that combines the most effective elements. The optimization unit also automatically generates a new marketing strategy using a generative AI based on the results of an A / B test and continuously optimizes it. For example, it regularly evaluates the test results and updates the strategy. Furthermore, the optimization unit can automatically generate a new marketing strategy using a generative AI based on the results of an A / B test and continuously optimize it. For example, it uses a feedback loop to improve the strategy. This allows the generative AI to automatically generate a new marketing strategy based on the results of an A / B test and continuously optimize it.

[0042] The optimization department can apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the optimization department can apply the strategy improvement process to customer support and perform comprehensive optimization using generative AI. For example, to improve the quality of customer service. The optimization department can also apply the strategy improvement process to product development and perform comprehensive optimization using generative AI. For example, to plan new products or improve existing products. Furthermore, the optimization department can also apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the marketing strategy improvement process can be applied to sales activities to improve sales efficiency. This allows the strategy improvement process to be applied to other business areas and performed comprehensive optimization.

[0043] The optimization unit can combine different marketing strategies, simulate their effects using a generation AI, and identify the optimal combination. For example, the optimization unit builds a system that combines different marketing strategies and simulates their effects using a generation AI. For example, it evaluates the effects of combining multiple promotions. The optimization unit also combines different marketing strategies, simulates their effects using a generation AI, and identifies the optimal combination. For example, it evaluates the effects of combining online advertising and email marketing. The optimization unit can also combine different marketing strategies, simulate their effects using a generation AI, and identify the optimal combination. For example, it evaluates the effects of combining a social media promotion and an offline event. This makes it possible to combine different marketing strategies, simulate their effects, and identify the optimal combination.

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

[0045] The data collection unit can collect not only customer purchase history but also product reviews and ratings viewed by customers, and analyze them with the generation AI. For example, it can identify products that customers have given high and low ratings and formulate a marketing strategy based on those ratings. The data collection unit can also analyze the content of reviews posted by customers and extract specific keywords and phrases. For example, it can promote products that customers have rated as "good quality" by emphasizing their quality. Furthermore, the data collection unit can collect the history of customers' viewing of other customers' reviews and analyze it with the generation AI. For example, it can identify trends in the reviews that customers frequently view and suggest related products based on those trends. This makes it possible to formulate a marketing strategy based on customer reviews and ratings.

[0046] The data collection unit can track not only the customer's social media activity but also the activity of the online communities and forums in which the customer participates, and analyze this with Generative AI. For example, it can identify topics that the customer frequently posts about in a particular forum and promote products related to those topics. The data collection unit can also collect the history of online events and webinars that the customer participates in and analyze this with Generative AI. For example, it can suggest related products based on the theme of the event the customer attended. Furthermore, the data collection unit can track the activity of influencers and brands that the customer follows and analyze this with Generative AI. For example, it can promote products recommended by influencers that the customer follows. This allows the company to develop marketing strategies based on the activity of the customer's online communities and forums.

[0047] The data collection unit can collect not only customer purchase and return histories, but also the history of subscription services used by customers, and analyze this with generation AI. For example, it can identify the contents of subscription services that customers regularly use and promote products related to those services. The data collection unit can also collect the reasons why customers canceled subscription services and analyze this with generation AI. For example, it can identify areas for improvement based on the reasons for cancellation and suggest resubscription. Furthermore, the data collection unit can collect the history of new subscription services started by customers and analyze this with generation AI. For example, it can suggest products related to the newly started service. This makes it possible to develop marketing strategies based on the customer's subscription service history.

[0048] The data collection unit can collect not only customer location data but also data on the means of transportation used by the customer, which can be analyzed by the generation AI. For example, it can identify the means of transportation frequently used by the customer and promote products and services related to that means of transportation. The data collection unit can also collect customers' commute routes and travel routes and analyze them with the generation AI. For example, it can suggest stores and services along specific commute routes. Furthermore, the data collection unit can collect the history of the means of transportation used by the customer and analyze them with the generation AI. For example, it can suggest related products and services based on the means of transportation frequently used by the customer. This makes it possible to develop marketing strategies based on the customer's means of transportation.

[0049] The data collection unit can collect not only biometric data from customers' wearable devices but also data from fitness apps used by customers, and analyze it with the generation AI. For example, it can collect exercise data recorded by customers in fitness apps and identify exercise habits based on that data. The data collection unit can also collect goals set by customers in fitness apps and their progress, and analyze it with the generation AI. For example, it can suggest related products and services based on the goals set by customers. Furthermore, the data collection unit can collect data on challenges and communities that customers participate in in fitness apps, and analyze it with the generation AI. For example, it can suggest related products based on the challenges that customers participate in. This makes it possible to develop marketing strategies based on the data from customers' fitness apps.

[0050] The Strategy Planning Department can combine not only a customer's past purchase history with current behavioral data, but also their lifestyle data to use generative AI to predict future purchases. For example, it can collect survey results about a customer's lifestyle and use that data to identify the next product they are likely to purchase. The Strategy Planning Department can also analyze social media posts about a customer's lifestyle and use that data to predict future purchases. For example, it can suggest related products based on the lifestyle content posted by the customer. Furthermore, the Strategy Planning Department can analyze a customer's lifestyle-related purchase history and use that data to predict future purchases. For example, if a customer has a health-conscious lifestyle, it can suggest health-related products. This allows it to predict future purchases based on customer lifestyle data and formulate marketing strategies.

[0051] The strategy planning department can not only compare a customer's purchase history with other customers' data, but also collect customer behavioral data in real time and analyze it with generative AI. For example, it can collect the product pages customers are currently viewing and the links they are clicking in real time, and develop a common marketing strategy based on that data. The strategy planning department can also identify the behavioral patterns of customer groups by collecting real-time customer behavioral data and analyzing it with generative AI. For example, it can run a common promotion for a group of customers who view a specific page at the same time. Furthermore, the strategy planning department can identify the interests and preferences of customer groups by collecting real-time customer behavioral data and analyzing it with generative AI. For example, it can run a common promotion for a group of customers who frequently view products in the same category. This makes it possible to develop a common marketing strategy based on real-time behavioral data.

[0052] The test implementation department not only collects real-time behavioral data of customers during the test period, but also collects customer feedback in real time and analyzes it with the generation AI. For example, it collects feedback provided by customers in real time during the test period and analyzes the test results based on that data. The test implementation department can also improve the accuracy of the test results by collecting feedback provided by customers during the test period and analyzing it with the generation AI. For example, it can identify how customers respond to a particular promotion. The test implementation department can also improve the accuracy of the test results by collecting feedback provided by customers during the test period and analyzing it with the generation AI. For example, it can identify how customers respond to a particular promotion. In this way, it is possible to improve the accuracy of the test results by collecting and analyzing real-time behavioral data and feedback of customers during the test period.

[0053] The test implementation department can apply the results of the A / B test to other marketing channels and analyze them comprehensively using generative AI. For example, the results of the A / B test can be applied to email marketing and analyzed using generative AI. For example, the most effective email wording can be identified. The test implementation department can also apply the results of the A / B test to social media marketing and analyze them using generative AI. For example, the most effective social media post can be identified. The test implementation department can also apply the results of the A / B test to online advertising and analyze them using generative AI. For example, the most effective advertising wording can be identified. In this way, the results of the A / B test can be applied to other marketing channels and analyzed comprehensively, allowing for the development of a more effective marketing strategy.

[0054] The test implementation department can conduct A / B tests simultaneously in different regions and cultural areas and compare and analyze the results using generative AI. For example, A / B tests can be conducted simultaneously in different regions and the results can be compared and analyzed using generative AI. For example, differences in responses between urban and rural areas can be identified. The test implementation department can also conduct A / B tests simultaneously in different cultural areas and the results can be compared and analyzed using generative AI. For example, differences in responses between Asia and Europe can be identified. Furthermore, the test implementation department can conduct A / B tests simultaneously in different age groups and the results can be compared and analyzed using generative AI. For example, differences in responses between younger and older groups can be identified. This allows A / B tests to be conducted simultaneously in different regions and cultural areas and the results compared and analyzed, making it possible to develop marketing strategies tailored to each region and culture.

[0055] The optimization unit can use generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests. For example, a system can be developed that uses generative AI to automatically generate new marketing strategies based on the results of A / B tests. For example, a strategy that combines the most effective elements can be generated. The optimization unit can also use generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests. For example, the optimization unit can periodically evaluate test results and update the strategy. The optimization unit can also use generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests. For example, a feedback loop can be used to improve the strategy. This allows generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests.

[0056] The optimization department can apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the strategy improvement process can be applied to customer support and comprehensively optimized using generative AI. For example, to improve the quality of customer service. The optimization department can also apply the strategy improvement process to product development and comprehensively optimize using generative AI. For example, to plan new products or improve existing products. The optimization department can also apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the marketing strategy improvement process can be applied to sales activities to improve sales efficiency. This allows the strategy improvement process to be applied to other business areas and comprehensively optimized.

[0057] The optimization unit can combine different marketing strategies, simulate their effects using generative AI, and identify the optimal combination. For example, a system can be built that combines different marketing strategies and simulates their effects using generative AI. For example, the effectiveness of combining multiple promotions can be evaluated. The optimization unit can also combine different marketing strategies, simulate their effects using generative AI, and identify the optimal combination. For example, the effectiveness of combining online advertising and email marketing can be evaluated. The optimization unit can also combine different marketing strategies, simulate their effects using generative AI, and identify the optimal combination. For example, the effectiveness of combining social media promotions and offline events can be evaluated. This makes it possible to combine different marketing strategies, simulate their effects, and identify the optimal combination.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The data collection department collects customer data, such as website access logs, purchase history, email open rates, customer behavior history, and click rates. Step 2: The analysis department analyzes the customer data collected by the data collection department. For example, it uses generative AI to analyze customer behavior patterns and finds patterns such as customers who frequently visit specific product pages or open emails at specific times of the day. Step 3: The Strategy Planning Department formulates a marketing strategy based on the results of the analysis by the Analysis Department. For example, generative AI can be used to provide promotional information related to a particular product to customers who are highly interested in that service. It can also predict the next product that customers are likely to purchase based on their past purchase history and provide information about that product. Step 4: The Testing Department conducts A / B testing to verify the effectiveness of the marketing strategy developed by the Strategy Department. For example, they use generative AI to test different promotional messages for the same service to see which gets a higher click-through rate. Step 5: The optimization department optimizes the marketing strategy based on the results obtained by the test implementation department. For example, they use generative AI to analyze the test results, extract effective elements, and incorporate them into the strategy.

[0060] (Example 2) A marketing system according to an embodiment of the present invention is a system that utilizes AI to collect and analyze customer data and formulate, implement, and optimize personalized marketing strategies, thereby enabling the marketing system to understand customer behavior patterns and provide optimal marketing strategies.

[0061] A marketing system according to an embodiment includes a data collection unit, an analysis unit, a strategy formulation unit, a test implementation unit, and an optimization unit. The data collection unit collects customer data, such as website access logs, purchase histories, and email open rates. The data collection unit can also collect data such as customer behavioral histories and click rates. The analysis unit analyzes the customer data collected by the data collection unit. For example, a generation AI analyzes customer behavior patterns and finds patterns such as customers who frequently visit specific product pages or customers who open emails at specific times of the day. The generation AI can use a text generation AI (e.g., LLM) or a multimodal generation AI to analyze customer data in detail. The strategy formulation unit formulates a marketing strategy based on the results of the analysis by the analysis unit. For example, the generation AI provides promotional information related to a specific product to customers who are highly interested in a specific service. The generation AI also predicts which products are likely to be purchased next based on past purchase history and provides information about the product. The test implementation unit conducts A / B tests to verify the effectiveness of the marketing strategy formulated by the strategy formulation unit. For example, the generation AI tests different wordings of promotional messages for the same service to see which strategy obtains a higher click-through rate. The generation AI analyzes the test results and determines which strategy is most effective. The optimization unit optimizes the marketing strategy based on the results obtained by the test implementation unit. For example, the generation AI analyzes the test results, extracts effective elements, and reflects them in the strategy. In this way, the marketing system according to the embodiment can collect and analyze customer data and formulate, implement, and optimize personalized marketing strategies.

[0062] The data collection unit collects customer voice data or chat logs and performs sentiment analysis using a generation AI to understand customer emotional patterns. For example, the data collection unit collects voice data from customers' inquiries to customer support and performs sentiment analysis using a generation AI. For example, if a customer is dissatisfied, the data collection unit identifies their emotions and considers countermeasures. The data collection unit also collects chat logs and performs sentiment analysis using a generation AI. For example, it analyzes the emotions expressed by customers in chats to understand their emotional patterns. Furthermore, the data collection unit can collect customer voice data in real time and perform sentiment analysis using a generation AI. For example, it can analyze the emotions of customers while they are talking on the phone in real time and provide immediate countermeasures. This allows for understanding customer emotional patterns and allows for the development of more effective marketing strategies.

[0063] The data collection unit tracks customers' social media activities and analyzes them with generative AI to understand their online behavior patterns. For example, the data collection unit collects customers' Twitter and Facebook posts and analyzes them with generative AI. For example, it identifies what topics customers are interested in. The data collection unit also collects customers' Instagram posts and analyzes them with generative AI. For example, it analyzes what images and videos customers post and identifies their areas of interest. Furthermore, the data collection unit can track customers' LinkedIn activity and analyze it with generative AI. For example, it identifies what industries and job types customers are interested in. This allows the company to understand customers' online behavior patterns and develop more effective marketing strategies.

[0064] The data collection unit can collect customer purchase history, return history, and customer support inquiries, and then comprehensively analyze them using generation AI. For example, the data collection unit collects customer purchase history and return history and analyzes them using generation AI. For example, it can identify what types of products are likely to be returned. The data collection unit also collects customer support inquiries and analyzes them using generation AI. For example, it can identify what problems customers are having and consider countermeasures. Furthermore, the data collection unit can comprehensively collect customer purchase history, return history, and customer support inquiries, and analyze them using generation AI. For example, it can comprehensively analyze what products customers are satisfied with and what products they are dissatisfied with. This allows for the comprehensive analysis of customer purchase history, return history, and customer support inquiries to be used to develop more effective marketing strategies.

[0065] The data collection unit collects customer location data and analyzes it with the generation AI, thereby identifying regional behavioral patterns. For example, the data collection unit collects location data from customers' smartphones and analyzes it with the generation AI. For example, it identifies purchasing behavior in a specific region. The data collection unit also collects customers' GPS data and analyzes it with the generation AI. For example, it identifies the types of places customers frequently visit. Furthermore, the data collection unit can also collect customers' Wi-Fi location information and analyze it with the generation AI. For example, it identifies the types of stores and facilities customers visit. This allows it to identify regional behavioral patterns and develop marketing strategies tailored to each region.

[0066] The data collection unit collects biometric data from customers' wearable devices and analyzes it with generation AI, allowing the company to develop marketing strategies based on their health status and lifestyle habits. For example, the data collection unit collects heart rate data from customers' smartwatches and analyzes it with generation AI. For example, the data collection unit identifies the customer's stress level. The data collection unit also collects step count data from customers' fitness trackers and analyzes it with generation AI. For example, the data collection unit identifies the customer's exercise habits. Furthermore, the data collection unit can collect sleep data from customers' wearable devices and analyze it with generation AI. For example, the data collection unit identifies the customer's sleep patterns and evaluates their health status. This allows the company to develop marketing strategies based on their health status and lifestyle habits.

[0067] The strategy formulation department can combine a customer's past purchase history with current behavioral data to use generation AI to predict future purchases and develop marketing strategies based on that. For example, the strategy formulation department can combine a customer's past purchase history with current website browsing data to use generation AI to predict future purchases. For example, it can identify the products that are likely to be purchased next. The strategy formulation department can also combine a customer's past purchase history with current click data to use generation AI to predict future purchases. For example, it can identify the links that are likely to be clicked next. Furthermore, the strategy formulation department can combine a customer's past purchase history with current email open data to use generation AI to predict future purchases. For example, it can identify the email that is likely to be opened next. This makes it possible to develop marketing strategies based on future purchase predictions.

[0068] The strategy formulation department can predict customer life events and provide personalized promotions accordingly. For example, the strategy formulation department analyzes customer social media posts to predict life events such as marriage and childbirth. For example, it promotes wedding-related products to customers who are planning to get married. The strategy formulation department can also analyze customer purchase histories to predict life events such as moving. For example, it promotes moving-related products to customers who are planning to move. Furthermore, the strategy formulation department can analyze customer survey results to predict life events. For example, it promotes baby products to customers who are planning to give birth. This makes it possible to provide personalized promotions according to customer life events.

[0069] The strategy formulation unit can use the emotion estimation function to generate marketing messages according to the emotional state of the customer and deliver them at the optimal timing. For example, the strategy formulation unit analyzes the emotional state of the customer in real time and delivers marketing messages when the customer is feeling positive. For example, it sends promotional information when the customer is happy. The strategy formulation unit also analyzes the emotional state of the customer and delivers encouraging messages when the customer is feeling negative. For example, it provides special offers when the customer is feeling down. Furthermore, the strategy formulation unit can analyze the emotional state of the customer and provide information when the customer is feeling neutral. For example, it provides information about new products when the customer is not showing any particular emotion. This makes it possible to deliver marketing messages according to the emotional state of the customer at the optimal timing.

[0070] The strategy formulation department can use generative AI to automatically generate content based on customers' hobbies and interests, and incorporate it into a personalized marketing strategy. For example, the strategy formulation department analyzes customers' social media posts to identify their hobbies and interests. For example, it automatically generates travel-related content for customers who like to travel. The strategy formulation department also analyzes customer survey results to identify their hobbies and interests. For example, it automatically generates music-related content for customers who like music. Furthermore, the strategy formulation department can analyze customers' purchasing history to identify their hobbies and interests. For example, it automatically generates sports-related content for customers who frequently purchase sports equipment. This makes it possible to automatically generate content based on customers' hobbies and interests, and incorporate it into a personalized marketing strategy.

[0071] The strategy formulation department can compare a customer's purchase history with data from other customers and formulate a common marketing strategy for customer groups with similar behavioral patterns. For example, the strategy formulation department analyzes customer purchase histories to identify customer groups with similar behavioral patterns. For example, a common promotion is run for customer groups that frequently purchase the same products. The strategy formulation department can also analyze customer behavioral data to identify customer groups with similar behavioral patterns. For example, a common promotion is run for customer groups that frequently visit the same website. Furthermore, the strategy formulation department can analyze customer survey results to identify customer groups with similar behavioral patterns. For example, a common promotion is run for customer groups with the same interests. This makes it possible to formulate a common marketing strategy for customer groups with similar behavioral patterns.

[0072] The strategy formulation unit can use the emotion estimation function to analyze the emotions customers have toward a specific product and carry out promotions based on those emotions. For example, the strategy formulation unit analyzes the emotions customers have when viewing a specific product page and promotes products for which they have positive emotions. For example, it provides special offers for products that customers are excited about. The strategy formulation unit can also analyze customer reviews and feedback to identify emotions toward a specific product. For example, it can promote products for which customers are satisfied. Furthermore, the strategy formulation unit can analyze customers' social media posts to identify emotions toward a specific product. For example, it can promote products for which customers have positive emotions. This makes it possible to carry out promotions based on the emotions customers have toward a specific product.

[0073] The test implementation department can improve the accuracy of test results by collecting real-time behavioral data of customers during the test period and analyzing it with generation AI. For example, the test implementation department can collect customer website browsing data in real time during the test period and analyze it with generation AI. For example, it can identify which pages are viewed the most. The test implementation department can also collect customer click data in real time during the test period and analyze it with generation AI. For example, it can identify which links are clicked the most. Furthermore, the test implementation department can collect customer email opening data in real time during the test period and analyze it with generation AI. For example, it can identify which emails are opened the most. In this way, by collecting and analyzing real-time behavioral data of customers during the test period, it can improve the accuracy of test results.

[0074] The test implementation unit uses the emotion estimation function to collect customers' emotional responses during the A / B test and analyze them with generative AI, thereby identifying the optimal strategy based on emotions. For example, the test implementation unit analyzes customers' facial expressions during the A / B test to collect emotional responses. For example, it identifies customer responses that show positive emotions. The test implementation unit also analyzes customers' voices during the A / B test to collect emotional responses. For example, it identifies responses when customers are excited. Furthermore, the test implementation unit can collect customers' biometric data during the A / B test to analyze their emotional responses. For example, it calculates an emotion score based on heart rate fluctuations. In this way, by collecting and analyzing customers' emotional responses during the A / B test, it is possible to identify the optimal strategy based on emotions.

[0075] The test implementation department can apply the results of the A / B test to other marketing channels and analyze them comprehensively using generative AI. For example, the test implementation department can apply the results of the A / B test to email marketing and analyze them using generative AI. For example, it can identify the most effective email wording. The test implementation department can also apply the results of the A / B test to social media marketing and analyze them using generative AI. For example, it can identify the most effective social media post. The test implementation department can also apply the results of the A / B test to online advertising and analyze them using generative AI. For example, it can identify the most effective advertising wording. In this way, the results of the A / B test can be applied to other marketing channels and analyzed comprehensively, allowing for the development of a more effective marketing strategy.

[0076] The test implementation department can conduct A / B tests simultaneously in different regions and cultural areas and compare and analyze the results using generative AI. For example, the test implementation department can conduct A / B tests simultaneously in different regions and compare and analyze the results using generative AI. For example, it can identify differences in responses between urban and rural areas. The test implementation department can also conduct A / B tests simultaneously in different cultural areas and compare and analyze the results using generative AI. For example, it can identify differences in responses between Asia and Europe. Furthermore, the test implementation department can conduct A / B tests simultaneously in different age groups and compare and analyze the results using generative AI. For example, it can identify differences in responses between younger and older groups. This allows A / B tests to be conducted simultaneously in different regions and cultural areas and the results to be compared and analyzed, making it possible to develop marketing strategies tailored to each region and culture.

[0077] The test implementation department can use the emotion estimation function to monitor customers' emotional responses in real time based on the results of A / B tests and instantly adjust strategies. For example, the test implementation department builds a system that monitors customers' emotional responses in real time based on the results of A / B tests. For example, it analyzes customers' facial expressions and voices to calculate an emotion score. The test implementation department also monitors customers' emotional responses in real time based on the results of A / B tests and instantly adjusts strategies. For example, it provides special offers to customers who show positive emotions. Furthermore, the test implementation department can monitor customers' emotional responses in real time based on the results of A / B tests and instantly adjust strategies. For example, it sends encouraging messages to customers who show negative emotions. In this way, by monitoring customers' emotional responses in real time based on the results of A / B tests and instantly adjusting strategies, a more effective marketing strategy can be developed.

[0078] The optimization unit can automatically generate a new marketing strategy using a generative AI based on the results of an A / B test and continuously optimize it. The optimization unit, for example, develops a system that automatically generates a new marketing strategy using a generative AI based on the results of an A / B test. For example, it generates a strategy that combines the most effective elements. The optimization unit also automatically generates a new marketing strategy using a generative AI based on the results of an A / B test and continuously optimizes it. For example, it regularly evaluates the test results and updates the strategy. Furthermore, the optimization unit can automatically generate a new marketing strategy using a generative AI based on the results of an A / B test and continuously optimize it. For example, it uses a feedback loop to improve the strategy. This allows the generative AI to automatically generate a new marketing strategy based on the results of an A / B test and continuously optimize it.

[0079] The optimization unit can use the emotion estimation function to improve the strategy based on the customer's emotional response and strengthen elements that elicit positive emotions. The optimization unit, for example, uses the emotion estimation function to build a system that improves the strategy based on the customer's emotional response. For example, it strengthens elements that elicit positive emotions. The optimization unit can also use the emotion estimation function to improve the strategy based on the customer's emotional response and strengthen elements that elicit positive emotions. For example, it can strengthen specific messages or promotional methods. The optimization unit can also use the emotion estimation function to improve the strategy based on the customer's emotional response and strengthen elements that elicit positive emotions. For example, it can increase the frequency or improve the content. This makes it possible to improve the strategy based on the customer's emotional response and strengthen elements that elicit positive emotions.

[0080] The optimization department can apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the optimization department can apply the strategy improvement process to customer support and perform comprehensive optimization using generative AI. For example, to improve the quality of customer service. The optimization department can also apply the strategy improvement process to product development and perform comprehensive optimization using generative AI. For example, to plan new products or improve existing products. Furthermore, the optimization department can also apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the marketing strategy improvement process can be applied to sales activities to improve sales efficiency. This allows the strategy improvement process to be applied to other business areas and performed comprehensive optimization.

[0081] The optimization unit can combine different marketing strategies, simulate their effects using a generation AI, and identify the optimal combination. For example, the optimization unit builds a system that combines different marketing strategies and simulates their effects using a generation AI. For example, it evaluates the effects of combining multiple promotions. The optimization unit also combines different marketing strategies, simulates their effects using a generation AI, and identifies the optimal combination. For example, it evaluates the effects of combining online advertising and email marketing. The optimization unit can also combine different marketing strategies, simulate their effects using a generation AI, and identify the optimal combination. For example, it evaluates the effects of combining a social media promotion and an offline event. This makes it possible to combine different marketing strategies, simulate their effects, and identify the optimal combination.

[0082] The optimization unit can use the emotion estimation function to monitor customers' emotional responses in real time during the strategy improvement process and make immediate adjustments. For example, the optimization unit uses the emotion estimation function to build a system that monitors customers' emotional responses in real time during the strategy improvement process. For example, the optimization unit analyzes customers' facial expressions and voices to calculate an emotion score. The optimization unit also uses the emotion estimation function to monitor customers' emotional responses in real time during the strategy improvement process and make immediate adjustments. For example, it provides special offers to customers who show positive emotions. Furthermore, the optimization unit can also use the emotion estimation function to monitor customers' emotional responses in real time during the strategy improvement process and make immediate adjustments. For example, it sends encouraging messages to customers who show negative emotions. In this way, by monitoring customers' emotional responses in real time during the strategy improvement process and making immediate adjustments, a more effective marketing strategy can be formulated.

[0083] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0084] The data collection unit can collect not only customer purchase history but also product reviews and ratings viewed by customers, and analyze them with the generation AI. For example, it can identify products that customers have given high and low ratings and formulate a marketing strategy based on those ratings. The data collection unit can also analyze the content of reviews posted by customers and extract specific keywords and phrases. For example, it can promote products that customers have rated as "good quality" by emphasizing their quality. Furthermore, the data collection unit can collect the history of customers' viewing of other customers' reviews and analyze it with the generation AI. For example, it can identify trends in the reviews that customers frequently view and suggest related products based on those trends. This makes it possible to formulate a marketing strategy based on customer reviews and ratings.

[0085] The data collection department can use the customer sentiment estimation function to analyze the sentiment that customers have toward a particular brand and formulate a marketing strategy based on that sentiment. For example, if a customer has positive sentiment toward a particular brand, that brand's products can be promoted preferentially. If a customer has negative sentiment toward a particular brand, that brand's products can be avoided or special offers can be provided to alleviate the negative sentiment. Furthermore, if a customer has neutral sentiment toward a particular brand, content can be generated to provide information about that brand's products and attract their interest. This makes it possible to formulate a marketing strategy based on the sentiment that customers have toward a particular brand.

[0086] The data collection unit can track not only the customer's social media activity but also the activity of the online communities and forums in which the customer participates, and analyze this with Generative AI. For example, it can identify topics that the customer frequently posts about in a particular forum and promote products related to those topics. The data collection unit can also collect the history of online events and webinars that the customer participates in and analyze this with Generative AI. For example, it can suggest related products based on the theme of the event the customer attended. Furthermore, the data collection unit can track the activity of influencers and brands that the customer follows and analyze this with Generative AI. For example, it can promote products recommended by influencers that the customer follows. This allows the company to develop marketing strategies based on the activity of the customer's online communities and forums.

[0087] The data collection unit can collect not only customer purchase and return histories, but also the history of subscription services used by customers, and analyze this with generation AI. For example, it can identify the contents of subscription services that customers regularly use and promote products related to those services. The data collection unit can also collect the reasons why customers canceled subscription services and analyze this with generation AI. For example, it can identify areas for improvement based on the reasons for cancellation and suggest resubscription. Furthermore, the data collection unit can collect the history of new subscription services started by customers and analyze this with generation AI. For example, it can suggest products related to the newly started service. This makes it possible to develop marketing strategies based on the customer's subscription service history.

[0088] The data collection unit can collect not only customer location data but also data on the means of transportation used by the customer, which can be analyzed by the generation AI. For example, it can identify the means of transportation frequently used by the customer and promote products and services related to that means of transportation. The data collection unit can also collect customers' commute routes and travel routes and analyze them with the generation AI. For example, it can suggest stores and services along specific commute routes. Furthermore, the data collection unit can collect the history of the means of transportation used by the customer and analyze them with the generation AI. For example, it can suggest related products and services based on the means of transportation frequently used by the customer. This makes it possible to develop marketing strategies based on the customer's means of transportation.

[0089] The data collection unit can collect not only biometric data from customers' wearable devices but also data from fitness apps used by customers, and analyze it with the generation AI. For example, it can collect exercise data recorded by customers in fitness apps and identify exercise habits based on that data. The data collection unit can also collect goals set by customers in fitness apps and their progress, and analyze it with the generation AI. For example, it can suggest related products and services based on the goals set by customers. Furthermore, the data collection unit can collect data on challenges and communities that customers participate in in fitness apps, and analyze it with the generation AI. For example, it can suggest related products based on the challenges that customers participate in. This makes it possible to develop marketing strategies based on the data from customers' fitness apps.

[0090] The Strategy Planning Department can combine not only a customer's past purchase history with current behavioral data, but also their lifestyle data to use generative AI to predict future purchases. For example, it can collect survey results about a customer's lifestyle and use that data to identify the next product they are likely to purchase. The Strategy Planning Department can also analyze social media posts about a customer's lifestyle and use that data to predict future purchases. For example, it can suggest related products based on the lifestyle content posted by the customer. Furthermore, the Strategy Planning Department can analyze a customer's lifestyle-related purchase history and use that data to predict future purchases. For example, if a customer has a health-conscious lifestyle, it can suggest health-related products. This allows it to predict future purchases based on customer lifestyle data and formulate marketing strategies.

[0091] The strategy planning department can not only predict a customer's life events, but also use the customer's emotion estimation function to analyze the customer's emotional response to the life events and provide promotions based on those emotions. For example, if a customer is planning to get married and is feeling positive, wedding-related products can be promoted. If a customer is planning to move and is feeling stressed, moving-related products can be offered as a special offer. Furthermore, if a customer is expecting a baby and is excited, baby products can be promoted. This makes it possible to provide personalized promotions based on the customer's emotional response to life events.

[0092] The strategy formulation department uses the emotion estimation function to not only generate marketing messages that correspond to the customer's emotional state, but also to suggest products that correspond to the customer's emotional state. For example, if a customer has positive emotions, it will suggest products that will further enhance those emotions. If a customer has negative emotions, it will suggest products that will alleviate those emotions. Furthermore, if a customer has neutral emotions, it will suggest products that will enhance those emotions. This makes it possible to propose products that correspond to the customer's emotional state and formulate more effective marketing strategies.

[0093] The Strategy Planning Department not only uses AI to automatically generate content based on customers' hobbies and interests, but also uses the customer's emotion estimation function to analyze their emotional responses to hobbies and interests and provide content based on those emotions. For example, if a customer has positive feelings about travel, travel-related content can be provided. If a customer is excited about music, music-related content can be provided. Furthermore, if a customer is passionate about sports, sports-related content can be provided. This makes it possible to provide content based on customers' emotional responses to their hobbies and interests and incorporate it into personalized marketing strategies.

[0094] The strategy planning department can not only compare a customer's purchase history with other customers' data, but also collect customer behavioral data in real time and analyze it with generative AI. For example, it can collect the product pages customers are currently viewing and the links they are clicking in real time, and develop a common marketing strategy based on that data. The strategy planning department can also identify the behavioral patterns of customer groups by collecting real-time customer behavioral data and analyzing it with generative AI. For example, it can run a common promotion for a group of customers who view a specific page at the same time. Furthermore, the strategy planning department can identify the interests and preferences of customer groups by collecting real-time customer behavioral data and analyzing it with generative AI. For example, it can run a common promotion for a group of customers who frequently view products in the same category. This makes it possible to develop a common marketing strategy based on real-time behavioral data.

[0095] The strategy planning department can use the emotion estimation function to not only analyze the emotions customers have toward a particular product, but also the emotions they have toward a particular brand, and then conduct promotions based on those emotions. For example, if a customer has positive emotions toward a particular brand, the department will prioritize promoting that brand's products. If a customer has negative emotions toward a particular brand, the department will either avoid that brand's products or provide them with special offers to alleviate their negative emotions. Furthermore, if a customer has neutral emotions toward a particular brand, the department will provide them with information about that brand's products and generate content to attract their interest. This makes it possible to conduct promotions based on the emotions customers have toward a particular brand.

[0096] The test implementation department not only collects real-time behavioral data of customers during the test period, but also collects customer feedback in real time and analyzes it with the generation AI. For example, it collects feedback provided by customers in real time during the test period and analyzes the test results based on that data. The test implementation department can also improve the accuracy of the test results by collecting feedback provided by customers during the test period and analyzing it with the generation AI. For example, it can identify how customers respond to a particular promotion. The test implementation department can also improve the accuracy of the test results by collecting feedback provided by customers during the test period and analyzing it with the generation AI. For example, it can identify how customers respond to a particular promotion. In this way, it is possible to improve the accuracy of the test results by collecting and analyzing real-time behavioral data and feedback of customers during the test period.

[0097] The test implementation unit uses the emotion estimation function to collect customers' emotional responses during A / B testing and analyze them with generative AI, thereby identifying the optimal strategy based on emotions. For example, the test implementation unit analyzes customers' facial expressions during A / B testing to collect emotional responses. For example, it identifies customer responses that show positive emotions. The test implementation unit also analyzes customers' voices during A / B testing to collect emotional responses. For example, it identifies responses when customers are excited. Furthermore, the test implementation unit can collect customers' biometric data during A / B testing to analyze their emotional responses. For example, it calculates an emotion score based on heart rate fluctuations. In this way, the test implementation unit can collect and analyze customers' emotional responses during A / B testing to identify the optimal strategy based on emotions.

[0098] The test implementation department can apply the results of the A / B test to other marketing channels and analyze them comprehensively using generative AI. For example, the results of the A / B test can be applied to email marketing and analyzed using generative AI. For example, the most effective email wording can be identified. The test implementation department can also apply the results of the A / B test to social media marketing and analyze them using generative AI. For example, the most effective social media post can be identified. The test implementation department can also apply the results of the A / B test to online advertising and analyze them using generative AI. For example, the most effective advertising wording can be identified. In this way, the results of the A / B test can be applied to other marketing channels and analyzed comprehensively, allowing for the development of a more effective marketing strategy.

[0099] The test implementation department can conduct A / B tests simultaneously in different regions and cultural areas and compare and analyze the results using generative AI. For example, A / B tests can be conducted simultaneously in different regions and the results can be compared and analyzed using generative AI. For example, differences in responses between urban and rural areas can be identified. The test implementation department can also conduct A / B tests simultaneously in different cultural areas and the results can be compared and analyzed using generative AI. For example, differences in responses between Asia and Europe can be identified. Furthermore, the test implementation department can conduct A / B tests simultaneously in different age groups and the results can be compared and analyzed using generative AI. For example, differences in responses between younger and older groups can be identified. This allows A / B tests to be conducted simultaneously in different regions and cultural areas and the results compared and analyzed, making it possible to develop marketing strategies tailored to each region and culture.

[0100] The test implementation department can use the emotion estimation function to monitor customers' emotional responses in real time based on the results of A / B tests and instantly adjust strategies. For example, a system can be built to monitor customers' emotional responses in real time based on the results of A / B tests. For example, the system can analyze customers' facial expressions and voices to calculate an emotion score. The test implementation department can also monitor customers' emotional responses in real time based on the results of A / B tests and instantly adjust strategies. For example, it can provide special offers to customers who show positive emotions. The test implementation department can also monitor customers' emotional responses in real time based on the results of A / B tests and instantly adjust strategies. For example, it can send encouraging messages to customers who show negative emotions. This allows for the development of more effective marketing strategies by monitoring customers' emotional responses in real time based on the results of A / B tests and instantly adjusting strategies.

[0101] The optimization unit can use generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests. For example, a system can be developed that uses generative AI to automatically generate new marketing strategies based on the results of A / B tests. For example, a strategy that combines the most effective elements can be generated. The optimization unit can also use generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests. For example, the optimization unit can periodically evaluate test results and update the strategy. The optimization unit can also use generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests. For example, a feedback loop can be used to improve the strategy. This allows generative AI to automatically generate and continuously optimize new marketing strategies based on the results of A / B tests.

[0102] The optimization unit can use the emotion estimation function to improve the strategy based on the customer's emotional response and strengthen elements that elicit positive emotions. For example, the emotion estimation function can be used to build a system that improves the strategy based on the customer's emotional response. For example, elements that elicit positive emotions can be strengthened. The optimization unit can also use the emotion estimation function to improve the strategy based on the customer's emotional response and strengthen elements that elicit positive emotions. For example, specific messages or promotional methods can be strengthened. The optimization unit can also use the emotion estimation function to improve the strategy based on the customer's emotional response and strengthen elements that elicit positive emotions. For example, by increasing frequency or improving content. In this way, the strategy can be improved based on the customer's emotional response and strengthen elements that elicit positive emotions.

[0103] The optimization department can apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the strategy improvement process can be applied to customer support and comprehensively optimized using generative AI. For example, to improve the quality of customer service. The optimization department can also apply the strategy improvement process to product development and comprehensively optimize using generative AI. For example, to plan new products or improve existing products. The optimization department can also apply the strategy improvement process to other business areas and perform comprehensive optimization using generative AI. For example, the marketing strategy improvement process can be applied to sales activities to improve sales efficiency. This allows the strategy improvement process to be applied to other business areas and comprehensively optimized.

[0104] The optimization unit can combine different marketing strategies, simulate their effects using generative AI, and identify the optimal combination. For example, a system can be built that combines different marketing strategies and simulates their effects using generative AI. For example, the effectiveness of combining multiple promotions can be evaluated. The optimization unit can also combine different marketing strategies, simulate their effects using generative AI, and identify the optimal combination. For example, the effectiveness of combining online advertising and email marketing can be evaluated. The optimization unit can also combine different marketing strategies, simulate their effects using generative AI, and identify the optimal combination. For example, the effectiveness of combining social media promotions and offline events can be evaluated. This makes it possible to combine different marketing strategies, simulate their effects, and identify the optimal combination.

[0105] The optimization unit can use the emotion estimation function to monitor customers' emotional responses in real time during the strategy improvement process and make immediate adjustments. For example, the emotion estimation function can be used to build a system that monitors customers' emotional responses in real time during the strategy improvement process. For example, the emotion estimation function can be used to analyze customers' facial expressions and voices and calculate an emotion score. The optimization unit can also use the emotion estimation function to monitor customers' emotional responses in real time during the strategy improvement process and make immediate adjustments. For example, a special offer can be provided to customers who show positive emotions. The optimization unit can also use the emotion estimation function to monitor customers' emotional responses in real time during the strategy improvement process and make immediate adjustments. For example, an encouraging message can be sent to customers who show negative emotions. In this way, a more effective marketing strategy can be developed by monitoring customers' emotional responses in real time during the strategy improvement process and making immediate adjustments.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The data collection department collects customer data, such as website access logs, purchase history, email open rates, customer behavior history, and click rates. Step 2: The analysis department analyzes the customer data collected by the data collection department. For example, it uses generative AI to analyze customer behavior patterns and finds patterns such as customers who frequently visit specific product pages or open emails at specific times of the day. Step 3: The Strategy Planning Department formulates a marketing strategy based on the results of the analysis by the Analysis Department. For example, generative AI can be used to provide promotional information related to a particular product to customers who are highly interested in that service. It can also predict the next product that customers are likely to purchase based on their past purchase history and provide information about that product. Step 4: The Testing Department conducts A / B testing to verify the effectiveness of the marketing strategy developed by the Strategy Department. For example, they use generative AI to test different promotional messages for the same service to see which gets a higher click-through rate. Step 5: The optimization department optimizes the marketing strategy based on the results obtained by the test implementation department. For example, they use generative AI to analyze the test results, extract effective elements, and incorporate them into the strategy.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0121] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0137] 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.

[0138] 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.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0152] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0153] 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.

[0154] 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.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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."

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a data collection unit that collects customer data; an analysis unit that analyzes the customer data collected by the data collection unit; a strategy formulation unit that formulates a marketing strategy based on the results of the analysis by the analysis unit; a test implementation department that conducts A / B tests to verify the effectiveness of the marketing strategy formulated by the strategy formulation department; an optimization unit that optimizes a marketing strategy based on the results obtained by the test implementation unit; A system characterized by:

2. The data collection unit Collect customer voice data or chat logs and use generative AI to perform sentiment analysis to understand customer emotional patterns 2. The system of claim 1.

3. The data collection unit The system described in claim 1 is characterized in that it collects customer location data and analyzes it using generation AI to identify behavioral patterns by region.

4. The strategy formulation department 2. The system according to claim 1, wherein an emotion estimation function is used to generate a marketing message according to the emotional state of the customer and deliver the message at an optimal timing.

5. The test implementation unit The system described in claim 1 uses an emotion estimation function to collect customer emotional responses during A / B testing and analyzes them with generative AI to identify the optimal strategy based on emotions.

6. The optimization unit The system described in claim 1, characterized in that a generative AI automatically generates new marketing strategies based on the results of A / B testing and continuously optimizes them.

7. The strategy formulation department 2. The system according to claim 1, wherein an emotion estimation function is used to analyze the emotions that customers have toward a particular product, and a promotion is carried out based on the emotions.

8. The optimization unit 10. The system of claim 1, wherein an emotion estimation function is used to monitor customer emotional responses in real time during the strategy improvement process and make immediate adjustments.

Images