System

Abstract

An object of the system according to the embodiment is to generate a performance based on an interest of a viewer and to effectively sell a product.SOLUTION: The system according to the embodiment includes an interest analysis unit, a performance generation unit, a product display unit, and a purchase unit. The interest analysis unit analyzes an interest of the viewer. The performance generation unit generates a performance based on the information analyzed by the interest analysis unit. The product display unit displays a product during the performance generated by the performance generation unit. The purchase part purchases the commodity displayed by the commodity display part.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 techniques have not adequately addressed effectively selling products while providing performances based on audience interest, and there is room for improvement.

[0005] The system according to the embodiment aims to generate a performance based on the interests of viewers and to sell products effectively. [Means for solving the problem]

[0006] The system according to the embodiment includes an interest analysis unit, a performance generation unit, a product display unit, and a purchase unit. The interest analysis unit analyzes the interests of viewers. The performance generation unit generates a performance based on information analyzed by the interest analysis unit. The product display unit displays products during the performance generated by the performance generation unit. The purchase unit purchases the products displayed by the product display unit. [Effects of the Invention]

[0007] The system according to the embodiment can generate a performance based on the interests of viewers and sell products effectively. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A live commerce system according to an embodiment of the present invention analyzes viewer interests, generates performances, displays products, and facilitates purchases. This live commerce system includes an interest analysis unit that analyzes viewer interests, a performance generation unit that generates performances based on information analyzed by the interest analysis unit, a product display unit that displays products during the performances generated by the performance generation unit, and a purchase unit that purchases the products displayed by the product display unit. For example, if a viewer prefers a particular genre of music, the AI ​​generates a performance tailored to that genre. This allows viewers to enjoy entertainment tailored to their preferences. Next, the product display unit that displays products during the live event displays products that the viewer is interested in on the screen, and viewers can proceed with the purchase process by clicking on them. For example, costumes worn or items used by virtual idols may be sold. This allows viewers to easily purchase their favorite products while enjoying the live event. Furthermore, AI-generated idols have an activity unit that operates 24 hours a day, allowing viewers to watch live events at their convenience. For example, virtual idols can perform even during times when traditional idols are not active, such as late at night or early in the morning. This increases flexibility and convenience for viewers. This allows the live commerce system to generate performances based on the viewer's interests and display and purchase products. For example, if a viewer likes a particular genre of music, the AI ​​generates a performance that matches that genre. This allows viewers to enjoy entertainment tailored to their preferences. Next, a product display unit that displays products during the live event displays products that the viewer is interested in on the screen, and viewers can proceed with the purchase by clicking on them. For example, costumes worn or items used by virtual idols may be sold. This allows viewers to easily purchase their favorite products while enjoying the live event.Furthermore, AI idols have a 24-hour activity team, allowing viewers to watch live events at their convenience. For example, virtual idols can perform even at times when traditional idols are not available, such as late at night or early in the morning. This increases flexibility and convenience for viewers. This allows the live commerce system to generate performances based on viewers' interests, and display and purchase products.

[0029] The live commerce system according to the embodiment includes an interest analysis unit, a performance generation unit, a product display unit, and a purchase unit. The interest analysis unit analyzes viewer interests. Viewer interests include, but are not limited to, viewing history, search history, and social media activity. The interest analysis unit identifies viewer interests based on, for example, viewing history. The interest analysis unit can also identify viewer interests based on search history. The interest analysis unit can also identify viewer interests based on social media activity. For example, the interest analysis unit analyzes viewing history to identify genres preferred by the viewer. The interest analysis unit analyzes search history to identify topics in which the viewer is interested. The interest analysis unit analyzes social media activity to identify interests based on accounts followed by the viewer and posts "liked." The performance generation unit generates a performance based on the information analyzed by the interest analysis unit. Performances include, but are not limited to, videos, music, live streaming, and the like. For example, the performance generation unit generates music in a genre preferred by the viewer. The performance generation unit can also generate videos based on topics in which the viewer is interested. The performance generation unit can also generate a live stream that incorporates the style of the account that the viewer follows. For example, the performance generation unit generates music in a genre that the viewer likes. Generates videos based on topics that the viewer is interested in. Generates a live stream that incorporates the style of the account that the viewer follows. The product display unit displays products during the performance generated by the performance generation unit. Products include, but are not limited to, physical products, digital content, services, etc. For example, the product display unit displays outfits worn by the virtual idol. The product display unit can also display items used by the virtual idol. The product display unit can also display services introduced by the virtual idol. For example, the product display unit displays outfits worn by the virtual idol. The product display unit displays items used by the virtual idol.The service introduced by the virtual idol is displayed. The purchasing unit purchases the product displayed by the product display unit. For example, the purchase procedure may be progressed by clicking, but is not limited to such an example. For example, the viewer may purchase the product by clicking on the purchasing unit. The viewer may also purchase the product by tapping on the purchasing unit. The viewer may also purchase the product by using a voice command on the purchasing unit. For example, the viewer may purchase the product by clicking on the purchasing unit. The viewer may purchase the product by tapping on the purchasing unit. The viewer may purchase the product by using a voice command on the purchasing unit. In this way, the live commerce system according to the embodiment can generate a performance based on the viewer's interests and display and purchase products.

[0030] The live commerce system further includes an activity unit that allows AI-generated idols to be active at all times. The activity unit allows AI-generated idols to be active 24 hours a day. For example, virtual idols can perform even during times when traditional idols are not active, such as late at night or early in the morning. This allows viewers to watch live events according to their own convenience. For example, the activity unit can perform late at night. The activity unit can also perform early in the morning. The activity unit can also perform according to the viewer's convenience. For example, the activity unit can perform late at night. The activity unit can also perform early in the morning. The activity unit can also perform according to the viewer's convenience. This allows AI-generated idols to be active 24 hours a day, increasing flexibility and convenience for viewers. Some or all of the above-described processing in the activity unit may be performed using AI, or may be performed without AI. For example, the activity unit can input a schedule for performances to suit the viewer's convenience into AI, which can then generate an optimal schedule.

[0031] The interest analysis unit can analyze the viewer's past viewing history and optimize the interest analysis algorithm. For example, the interest analysis unit uses AI to generate a new performance based on performances in a genre the viewer has previously viewed. The interest analysis unit can also analyze the time periods in which the viewer has previously viewed content and generate a performance tailored to that time period. The interest analysis unit can also analyze the characteristics of idols the viewer has previously viewed content and generate a performance with similar characteristics. For example, the interest analysis unit generates a new performance based on performances in a genre the viewer has previously viewed content. It analyzes the time periods in which the viewer has previously viewed content and generates a performance tailored to that time period. It analyzes the characteristics of idols the viewer has previously viewed content and generates a performance with similar characteristics. This optimizes the interest analysis algorithm based on the viewer's past viewing history. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or without AI. For example, the interest analysis unit can input the viewer's past viewing history data into the generation AI and cause the generation AI to optimize the interest analysis algorithm.

[0032] The interest analysis unit can analyze the viewer's social media activity and reflect changes in interests in real time. For example, the interest analysis unit generates related performances using AI based on posts that the viewer has "liked" on social media. The interest analysis unit can also analyze interests using AI based on the activity of accounts that the viewer follows on social media. The interest analysis unit can also analyze changes in interests using AI based on content that the viewer has shared on social media. For example, the interest analysis unit generates related performances based on posts that the viewer has "liked" on social media. It analyzes interests based on the activity of accounts that the viewer follows on social media. It analyzes changes in interests based on content that the viewer has shared on social media. In this way, changes in interests are reflected in real time based on the viewer's social media activity. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input the viewer's social media activity data into the generation AI and cause the generation AI to perform analysis to reflect changes in interests in real time.

[0033] The interest analysis unit can analyze regional interest trends based on the viewer's geographical location information. For example, the interest analysis unit uses AI to generate a performance based on popular genres in the viewer's region. The interest analysis unit can also use AI to generate a related performance based on event information in the viewer's region. The interest analysis unit can also use AI to generate a performance taking into account the cultural background of the viewer's region. For example, the interest analysis unit generates a performance based on popular genres in the viewer's region. It generates a related performance based on event information in the viewer's region. It generates a performance taking into account the cultural background of the viewer's region. In this way, regional interest trends are analyzed based on the viewer's geographical location information. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input the viewer's geographical location information data into the generation AI and cause the generation AI to perform an analysis to analyze regional interest trends.

[0034] The interest analysis unit can analyze the purchase history of the viewer and improve the accuracy of the interest analysis. For example, the interest analysis unit generates related performances using AI based on the genre of products the viewer has purchased in the past. The interest analysis unit can also analyze interests using AI based on the price range of products the viewer has purchased in the past. The interest analysis unit can also analyze interests using AI based on the brands of products the viewer has purchased in the past. For example, the interest analysis unit generates related performances based on the genre of products the viewer has purchased in the past. The interest is analyzed based on the price range of products the viewer has purchased in the past. The interest is analyzed based on the brands of products the viewer has purchased in the past. This improves the accuracy of the interest analysis based on the viewer's purchase history. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input the viewer's purchase history data into the generation AI and cause the generation AI to perform an analysis to improve the accuracy of the interest analysis.

[0035] The interest analysis unit can perform interest analysis based on attribute information such as the viewer's age and gender. For example, the interest analysis unit uses AI to generate a performance tailored to the viewer's age group. The interest analysis unit can also use AI to generate a performance tailored to the viewer's gender. The interest analysis unit can also analyze interests based on the viewer's attribute information and generate an optimal performance. For example, the interest analysis unit generates a performance tailored to the viewer's age group. Generates a performance tailored to the viewer's gender. Analyzes interests based on the viewer's attribute information and generates an optimal performance. In this way, interest analysis is performed based on the viewer's attribute information. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input viewer attribute information data into the generation AI and cause the generation AI to perform analysis to perform interest analysis.

[0036] The interest analysis unit can continuously improve the interest analysis algorithm by reflecting viewer feedback. For example, the interest analysis unit uses AI to adjust the interest analysis algorithm based on feedback provided by the viewer. The interest analysis unit can also improve the accuracy of the interest analysis based on viewer ratings. The interest analysis unit can also analyze viewer comments and improve the interest analysis algorithm by AI. For example, the interest analysis unit adjusts the interest analysis algorithm based on feedback provided by the viewer. Improves the accuracy of the interest analysis based on viewer ratings. Improves the interest analysis algorithm by analyzing viewer comments. This allows the interest analysis algorithm to be continuously improved based on viewer feedback. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input viewer feedback data into the generation AI and cause the generation AI to perform analysis to continuously improve the interest analysis algorithm.

[0037] The performance generation unit can customize the content of the performance by referring to the viewer's past viewing history. For example, the performance generation unit uses AI to generate a new performance based on performances of a genre that the viewer has previously viewed. The performance generation unit can also analyze the time period during which the viewer previously viewed and generate a performance that matches that time period. The performance generation unit can also analyze the characteristics of idols that the viewer has previously viewed and generate a performance with similar characteristics. For example, the performance generation unit generates a new performance based on performances of a genre that the viewer has previously viewed. It analyzes the time period during which the viewer previously viewed and generates a performance that matches that time period. It analyzes the characteristics of idols that the viewer has previously viewed and generates a performance with similar characteristics. In this way, the content of the performance is customized based on the viewer's past viewing history. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or without AI. For example, the performance generation unit can input the viewer's past viewing history data into the generation AI and have the generation AI perform an analysis to customize the content of the performance.

[0038] The performance generation unit can generate performances of different genres based on the viewer interest analysis results. For example, the performance generation unit uses AI to generate a performance in a genre in which the viewer is interested. The performance generation unit can also use AI to generate a performance that incorporates the style of an artist in which the viewer is interested. The performance generation unit can also use AI to generate a performance based on a theme in which the viewer is interested. For example, the performance generation unit generates a performance in a genre in which the viewer is interested. A performance that incorporates the style of an artist in which the viewer is interested. A performance based on a theme in which the viewer is interested. In this way, performances of different genres are generated based on the viewer interest analysis results. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or may be performed without using AI. For example, the performance generation unit can input viewer interest analysis result data into the generation AI and cause the generation AI to perform an analysis to generate a performance of a different genre.

[0039] The performance generation unit can reflect viewer feedback and continuously improve the content of the performance. For example, the performance generation unit uses AI to adjust the content of the performance based on feedback provided by viewers. The performance generation unit can also improve the accuracy of the performance based on viewer ratings. The performance generation unit can also analyze viewer comments and use AI to improve the content of the performance. For example, the performance generation unit adjusts the content of the performance based on feedback provided by viewers. Improves the accuracy of the performance based on viewer ratings. Analyzes viewer comments and improves the content of the performance. In this way, the content of the performance is continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the performance generation unit may be performed using AI, for example, or may be performed without using AI. For example, the performance generation unit can input viewer feedback data into the generation AI and cause the generation AI to perform analysis to continuously improve the content of the performance.

[0040] The performance generation unit can generate a different performance for each region by taking into account the viewer's geographical location information. For example, the performance generation unit uses AI to generate a performance based on a popular genre in the viewer's region. The performance generation unit can also use AI to generate a related performance based on event information in the viewer's region. The performance generation unit can also use AI to generate a performance by taking into account the cultural background of the viewer's region. For example, the performance generation unit generates a performance based on a popular genre in the viewer's region. A related performance is generated based on event information in the viewer's region. A performance is generated by taking into account the cultural background of the viewer's region. In this way, a different performance is generated for each region based on the viewer's geographical location information. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or without AI. For example, the performance generation unit can input viewer's geographical location information data into the generation AI and cause the generation AI to perform analysis to generate a different performance for each region.

[0041] The performance generation unit can generate a performance taking into account attribute information such as the viewer's age and gender. For example, the performance generation unit uses AI to generate a performance tailored to the viewer's age group. The performance generation unit can also use AI to generate a performance tailored to the viewer's gender. The performance generation unit can also analyze the viewer's interests based on the viewer's attribute information and generate an optimal performance. For example, the performance generation unit generates a performance tailored to the viewer's age group. Generates a performance tailored to the viewer's gender. Analyzes the viewer's interests based on the viewer's attribute information and generates an optimal performance. In this way, a performance is generated based on the viewer's attribute information. Some or all of the above-mentioned processing in the performance generation unit may be performed using AI, for example, or may be performed without using AI. For example, the performance generation unit can input viewer attribute information data into the generation AI and have the generation AI perform analysis to generate a performance.

[0042] The performance generation unit can analyze the viewer's social media activity and generate a performance based on a trend. For example, the performance generation unit uses AI to generate a related performance based on posts that the viewer has "liked" on social media. The performance generation unit can also use AI to analyze interests based on the activity of accounts that the viewer follows on social media. The performance generation unit can also use AI to analyze changes in interests based on content that the viewer has shared on social media. For example, the performance generation unit generates a related performance based on posts that the viewer has "liked" on social media. The performance generation unit analyzes interests based on the activity of accounts that the viewer follows on social media. The performance generation unit analyzes changes in interests based on content that the viewer has shared on social media. In this way, a performance based on a trend is generated based on the viewer's social media activity. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or without AI. For example, the performance generation unit can input the viewer's social media activity data into the generation AI and cause the generation AI to perform an analysis to generate a performance based on a trend.

[0043] The product display unit can prioritize displaying highly relevant products by referring to the viewer's past purchasing history. For example, the product display unit displays products related by AI based on the genre of products purchased by the viewer in the past. The product display unit can also display products related by AI based on the price range of products purchased by the viewer in the past. The product display unit can also display products related by AI based on the brand of products purchased by the viewer in the past. For example, the product display unit displays related products based on the genre of products purchased by the viewer in the past. Displays related products based on the price range of products purchased by the viewer in the past. Displays related products based on the brand of products purchased by the viewer in the past. In this way, highly relevant products are displayed preferentially based on the viewer's past purchasing history. Some or all of the above-described processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input the viewer's past purchasing history data into the generation AI and cause the generation AI to perform analysis to preferentially display highly relevant products.

[0044] The product display unit can customize the content of the product display based on the viewer interest analysis results. For example, the product display unit uses AI to display products in a genre in which the viewer is interested. The product display unit can also use AI to display products of brands in which the viewer is interested. The product display unit can also use AI to display products in a price range in which the viewer is interested. For example, the product display unit displays products in a genre in which the viewer is interested. Displays products of brands in which the viewer is interested. Displays products in a price range in which the viewer is interested. This customizes the content of the product display based on the viewer interest analysis results. Some or all of the above-mentioned processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input viewer interest analysis result data into a generation AI and cause the generation AI to perform an analysis to customize the content of the product display.

[0045] The product display unit can reflect viewer feedback and continuously improve the product display algorithm. For example, the product display unit can have AI adjust the product display algorithm based on feedback provided by viewers. The product display unit can also improve the accuracy of product display based on viewer ratings. The product display unit can also analyze viewer comments and have AI improve the product display algorithm. For example, the product display unit can adjust the product display algorithm based on feedback provided by viewers. Improve the accuracy of product display based on viewer ratings. Improve the product display algorithm by analyzing viewer comments. This allows the product display algorithm to be continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the product display unit can be performed using AI, for example, or without AI. For example, the product display unit can input viewer feedback data into the generation AI and cause the generation AI to perform analysis to continuously improve the product display algorithm.

[0046] The product display unit can display different products for each region, taking into account the viewer's geographical location information. For example, the product display unit uses AI to display products based on popular products in the viewer's region. The product display unit can also use AI to display related products based on event information in the viewer's region. The product display unit can also use AI to display products while taking into account the cultural background of the viewer's region. For example, the product display unit displays products based on popular products in the viewer's region. It displays related products based on event information in the viewer's region. It displays products while taking into account the cultural background of the viewer's region. In this way, different products are displayed for each region based on the viewer's geographical location information. Some or all of the above-described processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input the viewer's geographical location information data into the generation AI and cause the generation AI to perform analysis to display different products for each region.

[0047] The product display unit can display products taking into consideration attribute information such as the viewer's age and gender. For example, the product display unit uses AI to display products tailored to the viewer's age group. The product display unit can also use AI to display products tailored to the viewer's gender. The product display unit can also analyze the viewer's interests based on the viewer's attribute information and display the most suitable products. For example, the product display unit displays products tailored to the viewer's age group. Displays products tailored to the viewer's gender. Analyzes the viewer's interests based on the viewer's attribute information and displays the most suitable products. In this way, products are displayed based on the viewer's attribute information. Some or all of the above-mentioned processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input viewer attribute information data into the generation AI and have the generation AI perform analysis to display products.

[0048] The product display unit can analyze the viewer's social media activity and display products based on trends. For example, the product display unit uses AI to display related products based on posts that the viewer has "liked" on social media. The product display unit can also use AI to analyze interests based on the activity of accounts that the viewer follows on social media. The product display unit can also use AI to analyze changes in interests based on content that the viewer has shared on social media. For example, the product display unit displays related products based on posts that the viewer has "liked" on social media. The product display unit analyzes interests based on the activity of accounts that the viewer follows on social media. The product display unit analyzes changes in interests based on content that the viewer has shared on social media. This allows products based on trends based on the viewer's social media activity to be displayed. Some or all of the above-described processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input the viewer's social media activity data into a generation AI and cause the generation AI to perform an analysis to display products based on trends.

[0049] The purchasing unit can simplify the purchasing procedure by referring to the viewer's past purchasing history. For example, the purchasing unit uses AI to automatically fill in input fields based on information about products the viewer has purchased in the past. The purchasing unit can also use AI to suggest the optimal payment method based on payment methods the viewer has used in the past. The purchasing unit can also use AI to suggest the optimal delivery option based on the viewer's past purchasing history. For example, the purchasing unit automatically fills in input fields based on information about products the viewer has purchased in the past. It suggests the optimal payment method based on payment methods the viewer has used in the past. It suggests the optimal delivery option based on the viewer's past purchasing history. This simplifies the purchasing procedure based on the viewer's past purchasing history. Some or all of the above-mentioned processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input the viewer's past purchasing history data into a generation AI and have the generation AI perform an analysis to simplify the purchasing procedure.

[0050] The purchasing unit can customize the contents of the purchasing procedure based on the viewer's interest analysis results. For example, the purchasing unit uses AI to customize the purchasing procedure based on information about products in which the viewer is interested. The purchasing unit can also use AI to customize the purchasing procedure based on information about brands in which the viewer is interested. The purchasing unit can also use AI to customize the purchasing procedure based on information about price ranges in which the viewer is interested. For example, the purchasing unit customizes the purchasing procedure based on information about products in which the viewer is interested. The purchasing procedure is customized based on information about brands in which the viewer is interested. The purchasing procedure is customized based on information about price ranges in which the viewer is interested. In this way, the contents of the purchasing procedure are customized based on the viewer's interest analysis results. Some or all of the above-described processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input viewer interest analysis result data into a generation AI and have the generation AI perform an analysis to customize the contents of the purchasing procedure.

[0051] The purchasing unit can reflect viewer feedback and continuously improve the purchasing checkout algorithm. For example, the purchasing unit uses AI to adjust the purchasing checkout algorithm based on feedback provided by viewers. The purchasing unit can also improve the accuracy of the purchasing checkout algorithm based on viewer ratings. The purchasing unit can also analyze viewer comments and use AI to improve the purchasing checkout algorithm. For example, the purchasing unit adjusts the purchasing checkout algorithm based on feedback provided by viewers. Improves the accuracy of the purchasing checkout based on viewer ratings. Analyzes viewer comments and improves the purchasing checkout algorithm. In this way, the purchasing checkout algorithm is continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input viewer feedback data into the generation AI and have the generation AI perform analysis to continuously improve the purchasing checkout algorithm.

[0052] The purchasing unit can provide a different purchasing procedure for each region by taking into account the viewer's geographic location information. For example, the purchasing unit uses AI to provide the optimal purchasing procedure based on delivery options for the viewer's region. The purchasing unit can also provide the optimal purchasing procedure by taking into account taxes and fees for the viewer's region. The purchasing unit can also provide the optimal payment method based on the currency for the viewer's region. For example, the purchasing unit provides the optimal purchasing procedure based on delivery options for the viewer's region. The purchasing unit provides the optimal purchasing procedure by taking into account taxes and fees for the viewer's region. The optimal payment method is provided based on the currency for the viewer's region. In this way, a different purchasing procedure is provided for each region based on the viewer's geographic location information. Some or all of the above-described processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input the viewer's geographic location information data into the generation AI and cause the generation AI to perform analysis to provide a different purchasing procedure for each region.

[0053] The purchasing unit can provide a purchasing procedure taking into account attribute information such as the viewer's age and gender. For example, the purchasing unit uses AI to provide a purchasing procedure tailored to the viewer's age group. The purchasing unit can also use AI to provide a purchasing procedure tailored to the viewer's gender. The purchasing unit can also use AI to provide an optimal purchasing procedure based on the viewer's attribute information. For example, the purchasing unit provides a purchasing procedure tailored to the viewer's age group. Provides a purchasing procedure tailored to the viewer's gender. Provides an optimal purchasing procedure based on the viewer's attribute information. In this way, a purchasing procedure is provided based on the viewer's attribute information. Some or all of the above-mentioned processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input viewer attribute information data into a generation AI and have the generation AI perform analysis to provide a purchasing procedure.

[0054] The purchasing unit can analyze the viewer's social media activity and provide a purchasing checkout based on trends. For example, the purchasing unit uses AI to provide a relevant purchasing checkout based on posts that the viewer has "liked" on social media. The purchasing unit can also use AI to analyze interests based on the activity of accounts that the viewer follows on social media. The purchasing unit can also use AI to analyze changes in interests based on content that the viewer has shared on social media. For example, the purchasing unit can provide a relevant purchasing checkout based on posts that the viewer has "liked" on social media. The purchasing unit can analyze interests based on the activity of accounts that the viewer follows on social media. The purchasing unit can analyze changes in interests based on content that the viewer has shared on social media. This provides a purchasing checkout based on trends based on the viewer's social media activity. Some or all of the above-described processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input the viewer's social media activity data into the generation AI and cause the generation AI to perform an analysis to provide a purchasing checkout based on trends.

[0055] The activity unit can select the optimal activity time by referring to the viewer's past viewing history. For example, the activity unit uses AI to select the optimal activity time based on the time period in which the viewer previously viewed programs. The activity unit can also use AI to select the optimal activity time based on the performance of a genre in which the viewer previously viewed programs. The activity unit can also use AI to select the optimal activity time based on the characteristics of idols the viewer previously viewed programs. For example, the activity unit selects the optimal activity time based on the time period in which the viewer previously viewed programs. The activity unit selects the optimal activity time based on the performance of a genre in which the viewer previously viewed programs. The activity unit selects the optimal activity time based on the characteristics of idols the viewer previously viewed programs. In this way, the optimal activity time is selected based on the viewer's past viewing history. Some or all of the above-described processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input the viewer's past viewing history data into the generation AI and have the generation AI perform an analysis to select the optimal activity time.

[0056] The activity unit can customize the activity content based on the viewer interest analysis results. For example, the activity unit uses AI to generate a performance in a genre that the viewer is interested in. The activity unit can also use AI to generate a performance that incorporates the style of an artist that the viewer is interested in. The activity unit can also use AI to generate a performance based on a theme that the viewer is interested in. For example, the activity unit generates a performance in a genre that the viewer is interested in. Generates a performance that incorporates the style of an artist that the viewer is interested in. Generates a performance based on a theme that the viewer is interested in. In this way, the activity content is customized based on the viewer interest analysis results. Some or all of the above-mentioned processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input viewer interest analysis result data into a generation AI and have the generation AI perform an analysis to customize the activity content.

[0057] The activity department can continuously improve the activity schedule by reflecting viewer feedback. For example, the activity department can have AI adjust the activity schedule based on feedback provided by viewers. The activity department can also have AI improve the accuracy of the activity schedule based on viewer ratings. The activity department can also analyze viewer comments and have AI improve the activity schedule. For example, the activity department can adjust the activity schedule based on feedback provided by viewers. Improve the accuracy of the activity schedule based on viewer ratings. Analyze viewer comments and improve the activity schedule. In this way, the activity schedule is continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the activity department can be performed, for example, using AI or without using AI. For example, the activity department can input viewer feedback data into the generation AI and have the generation AI perform analysis to continuously improve the activity schedule.

[0058] The activity department can provide different activities for each region by taking into account the viewer's geographical location information. For example, the activity department uses AI to generate a performance based on popular genres in the viewer's region. The activity department can also use AI to generate a relevant performance based on event information in the viewer's region. The activity department can also use AI to generate a performance by taking into account the cultural background of the viewer's region. For example, the activity department generates a performance based on popular genres in the viewer's region. A relevant performance is generated based on event information in the viewer's region. A performance is generated by taking into account the cultural background of the viewer's region. In this way, different activities are provided for each region based on the viewer's geographical location information. Some or all of the above-described processing in the activity department may be performed using AI, for example, or may be performed without using AI. For example, the activity department can input viewer's geographical location information data into the generation AI and have the generation AI perform an analysis to provide different activities for each region.

[0059] The activity unit can provide activities taking into account attribute information such as the viewer's age and gender. For example, the activity unit uses AI to generate performances tailored to the viewer's age group. The activity unit can also use AI to generate performances tailored to the viewer's gender. The activity unit can also analyze the viewer's interests based on the viewer's attribute information and generate an optimal performance. For example, the activity unit generates a performance tailored to the viewer's age group. A performance tailored to the viewer's gender is generated. The interests are analyzed based on the viewer's attribute information and an optimal performance is generated. In this way, activities are provided based on the viewer's attribute information. Some or all of the above-described processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input viewer attribute information data into a generation AI and have the generation AI perform an analysis to provide activities.

[0060] The activity unit can analyze viewers' social media activities and provide trend-based activities. For example, the activity unit uses AI to generate relevant performances based on posts that viewers have "liked" on social media. The activity unit can also use AI to analyze interests based on the activity of accounts that viewers follow on social media. The activity unit can also use AI to analyze interest fluctuations based on content that viewers have shared on social media. For example, the activity unit generates relevant performances based on posts that viewers have "liked" on social media. The activity unit analyzes interests based on the activity of accounts that viewers follow on social media. The activity unit analyzes interest fluctuations based on content that viewers have shared on social media. In this way, trend-based activities are provided based on the viewers' social media activities. Some or all of the above-described processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input viewers' social media activity data into a generation AI and cause the generation AI to perform an analysis to provide trend-based activities.

[0061] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0062] The live commerce system analyzes viewers' purchasing history and can suggest new products based on the genre, price range, and brand of products they have previously purchased. For example, it can display related new products based on the genre of products the viewer has previously purchased. It can also suggest products that fit the viewer's budget based on the price range of products the viewer has previously purchased. It can also display new products from the same brand based on the brand of products the viewer has previously purchased. This makes it possible to make more personalized product suggestions based on the viewer's purchasing history.

[0063] The live commerce system analyzes the viewer's geographic location information and can suggest products based on popular products and event information for each region. For example, related products can be displayed based on popular products in the viewer's region. Products related to events can also be suggested based on event information for the viewer's region. Furthermore, regionally specific products can be displayed taking into account the cultural background of the viewer's region. This makes it possible to suggest optimal products for each region based on the viewer's geographic location information.

[0064] The live commerce system analyzes viewers' social media activity and can suggest products based on the posts they have liked and the accounts they follow. For example, it can display related products based on the posts they have liked. It can also suggest products that viewers may be interested in based on the activity of the accounts they follow. It can also analyze changes in interests based on the content shared by viewers and make product suggestions in real time. This makes it possible to make more personalized product suggestions based on the viewer's social media activity.

[0065] The live commerce system can analyze the viewer's attribute information, such as age and gender, and suggest products according to those attributes. For example, it can display products tailored to the viewer's age group. It can also suggest products tailored to the viewer's gender. Furthermore, it can analyze the viewer's interests based on their attribute information and suggest the most suitable products. This makes it possible to suggest more personalized products based on the viewer's attribute information.

[0066] The live commerce system can reflect viewer feedback and continuously improve the product recommendation algorithm. For example, the product recommendation algorithm can be adjusted based on the feedback provided by viewers. The accuracy of product recommendations can also be improved based on viewer ratings. Furthermore, the product recommendation algorithm can be improved by analyzing viewer comments. In this way, the product recommendation algorithm can be continuously improved based on viewer feedback.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The interest analysis unit analyzes the viewer's interests. The viewer's interests include viewing history, search history, social media activity, etc. For example, the viewer's interests are identified based on the viewing history, the viewer's interests are identified based on the search history, and the viewer's interests are identified based on the social media activity. Step 2: The performance generation unit generates a performance based on the information analyzed by the interest analysis unit. The performance may include videos, music, live streaming, etc. For example, it may generate music in the genres the viewer likes, generate videos based on topics the viewer is interested in, or generate live streaming in the style of accounts the viewer follows. Step 3: The product display unit displays products during the performance generated by the performance generation unit. Products include physical goods, digital content, services, etc. For example, the product display unit displays the outfit worn by the virtual idol, the items used by the virtual idol, and the services introduced by the virtual idol. Step 4: The purchasing unit purchases the product displayed by the product display unit. The purchase may be performed by clicking, tapping, using a voice command, etc. For example, the viewer may purchase the product by clicking, tapping, or using a voice command.

[0069] (Example 2) A live commerce system according to an embodiment of the present invention analyzes viewer interests, generates performances, displays products, and facilitates purchases. This live commerce system includes an interest analysis unit that analyzes viewer interests, a performance generation unit that generates performances based on information analyzed by the interest analysis unit, a product display unit that displays products during the performances generated by the performance generation unit, and a purchase unit that purchases the products displayed by the product display unit. For example, if a viewer prefers a particular genre of music, the AI ​​generates a performance tailored to that genre. This allows viewers to enjoy entertainment tailored to their preferences. Next, the product display unit that displays products during the live event displays products that the viewer is interested in on the screen, and viewers can proceed with the purchase process by clicking on them. For example, costumes worn or items used by virtual idols may be sold. This allows viewers to easily purchase their favorite products while enjoying the live event. Furthermore, AI-generated idols have an activity unit that operates 24 hours a day, allowing viewers to watch live events at their convenience. For example, virtual idols can perform even during times when traditional idols are not active, such as late at night or early in the morning. This increases flexibility and convenience for viewers. This allows the live commerce system to generate performances based on the viewer's interests and display and purchase products. For example, if a viewer likes a particular genre of music, the AI ​​generates a performance that matches that genre. This allows viewers to enjoy entertainment tailored to their preferences. Next, a product display unit that displays products during the live event displays products that the viewer is interested in on the screen, and viewers can proceed with the purchase by clicking on them. For example, costumes worn or items used by virtual idols may be sold. This allows viewers to easily purchase their favorite products while enjoying the live event.Furthermore, AI idols have a 24-hour activity team, allowing viewers to watch live events at their convenience. For example, virtual idols can perform even at times when traditional idols are not available, such as late at night or early in the morning. This increases flexibility and convenience for viewers. This allows the live commerce system to generate performances based on viewers' interests, and display and purchase products.

[0070] The live commerce system according to the embodiment includes an interest analysis unit, a performance generation unit, a product display unit, and a purchase unit. The interest analysis unit analyzes viewer interests. Viewer interests include, but are not limited to, viewing history, search history, and social media activity. The interest analysis unit identifies viewer interests based on, for example, viewing history. The interest analysis unit can also identify viewer interests based on search history. The interest analysis unit can also identify viewer interests based on social media activity. For example, the interest analysis unit analyzes viewing history to identify genres preferred by the viewer. The interest analysis unit analyzes search history to identify topics in which the viewer is interested. The interest analysis unit analyzes social media activity to identify interests based on accounts followed by the viewer and posts "liked." The performance generation unit generates a performance based on the information analyzed by the interest analysis unit. Performances include, but are not limited to, videos, music, live streaming, and the like. For example, the performance generation unit generates music in a genre preferred by the viewer. The performance generation unit can also generate videos based on topics in which the viewer is interested. The performance generation unit can also generate a live stream that incorporates the style of the account that the viewer follows. For example, the performance generation unit generates music in a genre that the viewer likes. Generates videos based on topics that the viewer is interested in. Generates a live stream that incorporates the style of the account that the viewer follows. The product display unit displays products during the performance generated by the performance generation unit. Products include, but are not limited to, physical products, digital content, services, etc. For example, the product display unit displays outfits worn by the virtual idol. The product display unit can also display items used by the virtual idol. The product display unit can also display services introduced by the virtual idol. For example, the product display unit displays outfits worn by the virtual idol. The product display unit displays items used by the virtual idol.The service introduced by the virtual idol is displayed. The purchasing unit purchases the product displayed by the product display unit. For example, the purchase procedure may be progressed by clicking, but is not limited to such an example. For example, the viewer may purchase the product by clicking on the purchasing unit. The viewer may also purchase the product by tapping on the purchasing unit. The viewer may also purchase the product by using a voice command on the purchasing unit. For example, the viewer may purchase the product by clicking on the purchasing unit. The viewer may purchase the product by tapping on the purchasing unit. The viewer may purchase the product by using a voice command on the purchasing unit. In this way, the live commerce system according to the embodiment can generate a performance based on the viewer's interests and display and purchase products.

[0071] The live commerce system further includes an activity unit that allows AI-generated idols to be active at all times. The activity unit allows AI-generated idols to be active 24 hours a day. For example, virtual idols can perform even during times when traditional idols are not active, such as late at night or early in the morning. This allows viewers to watch live events according to their own convenience. For example, the activity unit can perform late at night. The activity unit can also perform early in the morning. The activity unit can also perform according to the viewer's convenience. For example, the activity unit can perform late at night. The activity unit can also perform early in the morning. The activity unit can also perform according to the viewer's convenience. This allows AI-generated idols to be active 24 hours a day, increasing flexibility and convenience for viewers. Some or all of the above-described processing in the activity unit may be performed using AI, or may be performed without AI. For example, the activity unit can input a schedule for performances to suit the viewer's convenience into AI, which can then generate an optimal schedule.

[0072] The interest analysis unit can estimate the viewer's emotions and improve the accuracy of interest analysis based on the estimated viewer's emotions. For example, if the viewer is excited, the AI ​​in the interest analysis unit can detect the viewer's emotions and generate an energetic performance. Furthermore, if the viewer is relaxed, the AI ​​in the interest analysis unit can detect the viewer's emotions and generate a calm performance. Furthermore, if the viewer is sad, the AI ​​in the interest analysis unit can detect the viewer's emotions and generate a comforting performance. For example, if the viewer is excited, the interest analysis unit can generate an energetic performance. If the viewer is relaxed, the AI ​​can generate a calm performance. If the viewer is sad, the AI ​​can generate a comforting performance. This improves the accuracy of interest analysis based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the interest analysis unit can be performed, for example, using AI or without AI. For example, the interest analysis unit can input viewer emotional data into the generation AI and have the generation AI perform analysis to improve the accuracy of interest analysis.

[0073] The interest analysis unit can analyze the viewer's past viewing history and optimize the interest analysis algorithm. For example, the interest analysis unit uses AI to generate a new performance based on performances in a genre the viewer has previously viewed. The interest analysis unit can also analyze the time periods in which the viewer has previously viewed content and generate a performance tailored to that time period. The interest analysis unit can also analyze the characteristics of idols the viewer has previously viewed content and generate a performance with similar characteristics. For example, the interest analysis unit generates a new performance based on performances in a genre the viewer has previously viewed content. It analyzes the time periods in which the viewer has previously viewed content and generates a performance tailored to that time period. It analyzes the characteristics of idols the viewer has previously viewed content and generates a performance with similar characteristics. This optimizes the interest analysis algorithm based on the viewer's past viewing history. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or without AI. For example, the interest analysis unit can input the viewer's past viewing history data into the generation AI and cause the generation AI to optimize the interest analysis algorithm.

[0074] The interest analysis unit can analyze the viewer's social media activity and reflect changes in interests in real time. For example, the interest analysis unit generates related performances using AI based on posts that the viewer has "liked" on social media. The interest analysis unit can also analyze interests using AI based on the activity of accounts that the viewer follows on social media. The interest analysis unit can also analyze changes in interests using AI based on content that the viewer has shared on social media. For example, the interest analysis unit generates related performances based on posts that the viewer has "liked" on social media. It analyzes interests based on the activity of accounts that the viewer follows on social media. It analyzes changes in interests based on content that the viewer has shared on social media. In this way, changes in interests are reflected in real time based on the viewer's social media activity. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input the viewer's social media activity data into the generation AI and cause the generation AI to perform analysis to reflect changes in interests in real time.

[0075] The interest analysis unit can analyze regional interest trends based on the viewer's geographical location information. For example, the interest analysis unit uses AI to generate a performance based on popular genres in the viewer's region. The interest analysis unit can also use AI to generate a related performance based on event information in the viewer's region. The interest analysis unit can also use AI to generate a performance taking into account the cultural background of the viewer's region. For example, the interest analysis unit generates a performance based on popular genres in the viewer's region. It generates a related performance based on event information in the viewer's region. It generates a performance taking into account the cultural background of the viewer's region. In this way, regional interest trends are analyzed based on the viewer's geographical location information. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input the viewer's geographical location information data into the generation AI and cause the generation AI to perform an analysis to analyze regional interest trends.

[0076] The interest analysis unit can estimate the viewer's emotions and adjust the order in which the results of the interest analysis are displayed based on the estimated viewer's emotions. For example, if the viewer is excited, the interest analysis unit can cause the AI ​​to prioritize displaying energetic performances. Furthermore, if the viewer is relaxed, the interest analysis unit can cause the AI ​​to prioritize displaying calm performances. Furthermore, if the viewer is sad, the interest analysis unit can cause the AI ​​to prioritize displaying comforting performances. For example, if the viewer is excited, the interest analysis unit can prioritize displaying energetic performances. If the viewer is relaxed, the interest analysis unit can prioritize displaying calm performances. If the viewer is sad, the interest analysis unit can prioritize displaying comforting performances. In this way, the order in which the results of the interest analysis are displayed is adjusted based on the viewer's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the interest analysis unit can be performed using, for example, an AI, or without an AI. For example, the interest analysis unit can input viewer emotional data into the generation AI and cause the generation AI to perform an analysis to adjust the order in which the results of the interest analysis are displayed.

[0077] The interest analysis unit can analyze the purchase history of the viewer and improve the accuracy of the interest analysis. For example, the interest analysis unit generates related performances using AI based on the genre of products the viewer has purchased in the past. The interest analysis unit can also analyze interests using AI based on the price range of products the viewer has purchased in the past. The interest analysis unit can also analyze interests using AI based on the brands of products the viewer has purchased in the past. For example, the interest analysis unit generates related performances based on the genre of products the viewer has purchased in the past. The interest is analyzed based on the price range of products the viewer has purchased in the past. The interest is analyzed based on the brands of products the viewer has purchased in the past. This improves the accuracy of the interest analysis based on the viewer's purchase history. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input the viewer's purchase history data into the generation AI and cause the generation AI to perform an analysis to improve the accuracy of the interest analysis.

[0078] The interest analysis unit can perform interest analysis based on attribute information such as the viewer's age and gender. For example, the interest analysis unit uses AI to generate a performance tailored to the viewer's age group. The interest analysis unit can also use AI to generate a performance tailored to the viewer's gender. The interest analysis unit can also analyze interests based on the viewer's attribute information and generate an optimal performance. For example, the interest analysis unit generates a performance tailored to the viewer's age group. Generates a performance tailored to the viewer's gender. Analyzes interests based on the viewer's attribute information and generates an optimal performance. In this way, interest analysis is performed based on the viewer's attribute information. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input viewer attribute information data into the generation AI and cause the generation AI to perform analysis to perform interest analysis.

[0079] The interest analysis unit can continuously improve the interest analysis algorithm by reflecting viewer feedback. For example, the interest analysis unit uses AI to adjust the interest analysis algorithm based on feedback provided by the viewer. The interest analysis unit can also improve the accuracy of the interest analysis based on viewer ratings. The interest analysis unit can also analyze viewer comments and improve the interest analysis algorithm by AI. For example, the interest analysis unit adjusts the interest analysis algorithm based on feedback provided by the viewer. Improves the accuracy of the interest analysis based on viewer ratings. Improves the interest analysis algorithm by analyzing viewer comments. This allows the interest analysis algorithm to be continuously improved based on viewer feedback. Some or all of the above-described processing in the interest analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the interest analysis unit can input viewer feedback data into the generation AI and cause the generation AI to perform analysis to continuously improve the interest analysis algorithm.

[0080] The performance generation unit can estimate the viewer's emotions and adjust the content of the performance based on the estimated viewer's emotions. For example, if the viewer is excited, the AI ​​can generate an energetic performance. Furthermore, if the viewer is relaxed, the AI ​​can generate a calm performance. Furthermore, if the viewer is sad, the AI ​​can generate a comforting performance. For example, if the viewer is excited, the performance generation unit can generate an energetic performance. If the viewer is relaxed, the AI ​​can generate a calm performance. If the viewer is sad, the AI ​​can generate a comforting performance. In this way, the content of the performance is adjusted based on the viewer's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the performance generation unit can be performed using, for example, an AI, or without an AI. For example, the performance generation unit can input viewer emotion data into the generation AI and have the generation AI perform an analysis to adjust the content of the performance.

[0081] The performance generation unit can customize the content of the performance by referring to the viewer's past viewing history. For example, the performance generation unit uses AI to generate a new performance based on performances of a genre that the viewer has previously viewed. The performance generation unit can also analyze the time period during which the viewer previously viewed and generate a performance that matches that time period. The performance generation unit can also analyze the characteristics of idols that the viewer has previously viewed and generate a performance with similar characteristics. For example, the performance generation unit generates a new performance based on performances of a genre that the viewer has previously viewed. It analyzes the time period during which the viewer previously viewed and generates a performance that matches that time period. It analyzes the characteristics of idols that the viewer has previously viewed and generates a performance with similar characteristics. In this way, the content of the performance is customized based on the viewer's past viewing history. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or without AI. For example, the performance generation unit can input the viewer's past viewing history data into the generation AI and have the generation AI perform an analysis to customize the content of the performance.

[0082] The performance generation unit can generate performances of different genres based on the viewer interest analysis results. For example, the performance generation unit uses AI to generate a performance in a genre in which the viewer is interested. The performance generation unit can also use AI to generate a performance that incorporates the style of an artist in which the viewer is interested. The performance generation unit can also use AI to generate a performance based on a theme in which the viewer is interested. For example, the performance generation unit generates a performance in a genre in which the viewer is interested. A performance that incorporates the style of an artist in which the viewer is interested. A performance based on a theme in which the viewer is interested. In this way, performances of different genres are generated based on the viewer interest analysis results. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or may be performed without using AI. For example, the performance generation unit can input viewer interest analysis result data into the generation AI and cause the generation AI to perform an analysis to generate a performance of a different genre.

[0083] The performance generation unit can reflect viewer feedback and continuously improve the content of the performance. For example, the performance generation unit uses AI to adjust the content of the performance based on feedback provided by viewers. The performance generation unit can also improve the accuracy of the performance based on viewer ratings. The performance generation unit can also analyze viewer comments and use AI to improve the content of the performance. For example, the performance generation unit adjusts the content of the performance based on feedback provided by viewers. Improves the accuracy of the performance based on viewer ratings. Analyzes viewer comments and improves the content of the performance. In this way, the content of the performance is continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the performance generation unit may be performed using AI, for example, or may be performed without using AI. For example, the performance generation unit can input viewer feedback data into the generation AI and cause the generation AI to perform analysis to continuously improve the content of the performance.

[0084] The performance generation unit can estimate the viewer's emotions and adjust the length of the performance based on the estimated viewer's emotions. For example, if the viewer is excited, the AI ​​generates a short and energetic performance. Furthermore, if the viewer is relaxed, the AI ​​can generate a long and calm performance. Furthermore, if the viewer is sad, the AI ​​can generate a short and comforting performance. For example, if the viewer is excited, the performance generation unit generates a short and energetic performance. If the viewer is relaxed, the AI ​​generates a long and calm performance. If the viewer is sad, the AI ​​generates a short and comforting performance. Thus, the length of the performance is adjusted based on the viewer's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the performance generation unit can be performed using, for example, an AI, or without an AI. For example, the performance generation unit can input viewer emotional data into the generation AI and have the generation AI perform an analysis to adjust the length of the performance.

[0085] The performance generation unit can generate a different performance for each region by taking into account the viewer's geographical location information. For example, the performance generation unit uses AI to generate a performance based on a popular genre in the viewer's region. The performance generation unit can also use AI to generate a related performance based on event information in the viewer's region. The performance generation unit can also use AI to generate a performance by taking into account the cultural background of the viewer's region. For example, the performance generation unit generates a performance based on a popular genre in the viewer's region. A related performance is generated based on event information in the viewer's region. A performance is generated by taking into account the cultural background of the viewer's region. In this way, a different performance is generated for each region based on the viewer's geographical location information. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or without AI. For example, the performance generation unit can input viewer's geographical location information data into the generation AI and cause the generation AI to perform analysis to generate a different performance for each region.

[0086] The performance generation unit can generate a performance taking into account attribute information such as the viewer's age and gender. For example, the performance generation unit uses AI to generate a performance tailored to the viewer's age group. The performance generation unit can also use AI to generate a performance tailored to the viewer's gender. The performance generation unit can also analyze the viewer's interests based on the viewer's attribute information and generate an optimal performance. For example, the performance generation unit generates a performance tailored to the viewer's age group. Generates a performance tailored to the viewer's gender. Analyzes the viewer's interests based on the viewer's attribute information and generates an optimal performance. In this way, a performance is generated based on the viewer's attribute information. Some or all of the above-mentioned processing in the performance generation unit may be performed using AI, for example, or may be performed without using AI. For example, the performance generation unit can input viewer attribute information data into the generation AI and have the generation AI perform analysis to generate a performance.

[0087] The performance generation unit can analyze the viewer's social media activity and generate a performance based on a trend. For example, the performance generation unit uses AI to generate a related performance based on posts that the viewer has "liked" on social media. The performance generation unit can also use AI to analyze interests based on the activity of accounts that the viewer follows on social media. The performance generation unit can also use AI to analyze changes in interests based on content that the viewer has shared on social media. For example, the performance generation unit generates a related performance based on posts that the viewer has "liked" on social media. The performance generation unit analyzes interests based on the activity of accounts that the viewer follows on social media. The performance generation unit analyzes changes in interests based on content that the viewer has shared on social media. In this way, a performance based on a trend is generated based on the viewer's social media activity. Some or all of the above-described processing in the performance generation unit may be performed using AI, for example, or without AI. For example, the performance generation unit can input the viewer's social media activity data into the generation AI and cause the generation AI to perform an analysis to generate a performance based on a trend.

[0088] The product display unit can estimate the viewer's emotions and adjust the timing of product display based on the estimated viewer's emotions. For example, if the viewer is excited, the product display unit displays products during an energetic performance by the AI. Furthermore, if the viewer is relaxed, the product display unit can also display products during a calm performance by the AI. Furthermore, if the viewer is sad, the product display unit can also display products during a comforting performance by the AI. For example, if the viewer is excited, the product display unit displays products during an energetic performance. If the viewer is relaxed, the product display unit displays products during a calm performance. If the viewer is sad, the product display unit displays products during a comforting performance. In this way, the timing of product display is adjusted based on the viewer's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the product display unit may be performed using, for example, an AI, or without an AI. For example, the product display unit can input viewer emotional data into the generation AI and have the generation AI perform analysis to adjust the timing of product display.

[0089] The product display unit can prioritize displaying highly relevant products by referring to the viewer's past purchasing history. For example, the product display unit displays products related by AI based on the genre of products purchased by the viewer in the past. The product display unit can also display products related by AI based on the price range of products purchased by the viewer in the past. The product display unit can also display products related by AI based on the brand of products purchased by the viewer in the past. For example, the product display unit displays related products based on the genre of products purchased by the viewer in the past. Displays related products based on the price range of products purchased by the viewer in the past. Displays related products based on the brand of products purchased by the viewer in the past. In this way, highly relevant products are displayed preferentially based on the viewer's past purchasing history. Some or all of the above-described processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input the viewer's past purchasing history data into the generation AI and cause the generation AI to perform analysis to preferentially display highly relevant products.

[0090] The product display unit can customize the content of the product display based on the viewer interest analysis results. For example, the product display unit uses AI to display products in a genre in which the viewer is interested. The product display unit can also use AI to display products of brands in which the viewer is interested. The product display unit can also use AI to display products in a price range in which the viewer is interested. For example, the product display unit displays products in a genre in which the viewer is interested. Displays products of brands in which the viewer is interested. Displays products in a price range in which the viewer is interested. This customizes the content of the product display based on the viewer interest analysis results. Some or all of the above-mentioned processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input viewer interest analysis result data into a generation AI and cause the generation AI to perform an analysis to customize the content of the product display.

[0091] The product display unit can reflect viewer feedback and continuously improve the product display algorithm. For example, the product display unit can have AI adjust the product display algorithm based on feedback provided by viewers. The product display unit can also improve the accuracy of product display based on viewer ratings. The product display unit can also analyze viewer comments and have AI improve the product display algorithm. For example, the product display unit can adjust the product display algorithm based on feedback provided by viewers. Improve the accuracy of product display based on viewer ratings. Improve the product display algorithm by analyzing viewer comments. This allows the product display algorithm to be continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the product display unit can be performed using AI, for example, or without AI. For example, the product display unit can input viewer feedback data into the generation AI and cause the generation AI to perform analysis to continuously improve the product display algorithm.

[0092] The product display unit can estimate the viewer's emotions and adjust the order of product display based on the estimated viewer's emotions. For example, if the viewer is excited, the product display unit can prioritize displaying products during an energetic performance by the AI. Furthermore, if the viewer is relaxed, the product display unit can also prioritize displaying products during a calm performance by the AI. Furthermore, if the viewer is sad, the product display unit can prioritize displaying products during a comforting performance by the AI. For example, if the viewer is excited, the product display unit can prioritize displaying products during an energetic performance. If the viewer is relaxed, the product display unit can prioritize displaying products during a calm performance. If the viewer is sad, the product display unit can prioritize displaying products during a comforting performance. In this way, the order of product display is adjusted based on the viewer's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the product display unit can be performed using, for example, an AI, or without an AI. For example, the product display unit can input viewer emotional data into the generation AI and have the generation AI perform analysis to adjust the order of product display.

[0093] The product display unit can display different products for each region, taking into account the viewer's geographical location information. For example, the product display unit uses AI to display products based on popular products in the viewer's region. The product display unit can also use AI to display related products based on event information in the viewer's region. The product display unit can also use AI to display products while taking into account the cultural background of the viewer's region. For example, the product display unit displays products based on popular products in the viewer's region. It displays related products based on event information in the viewer's region. It displays products while taking into account the cultural background of the viewer's region. In this way, different products are displayed for each region based on the viewer's geographical location information. Some or all of the above-described processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input the viewer's geographical location information data into the generation AI and cause the generation AI to perform analysis to display different products for each region.

[0094] The product display unit can display products taking into consideration attribute information such as the viewer's age and gender. For example, the product display unit uses AI to display products tailored to the viewer's age group. The product display unit can also use AI to display products tailored to the viewer's gender. The product display unit can also analyze the viewer's interests based on the viewer's attribute information and display the most suitable products. For example, the product display unit displays products tailored to the viewer's age group. Displays products tailored to the viewer's gender. Analyzes the viewer's interests based on the viewer's attribute information and displays the most suitable products. In this way, products are displayed based on the viewer's attribute information. Some or all of the above-mentioned processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input viewer attribute information data into the generation AI and have the generation AI perform analysis to display products.

[0095] The product display unit can analyze the viewer's social media activity and display products based on trends. For example, the product display unit uses AI to display related products based on posts that the viewer has "liked" on social media. The product display unit can also use AI to analyze interests based on the activity of accounts that the viewer follows on social media. The product display unit can also use AI to analyze changes in interests based on content that the viewer has shared on social media. For example, the product display unit displays related products based on posts that the viewer has "liked" on social media. The product display unit analyzes interests based on the activity of accounts that the viewer follows on social media. The product display unit analyzes changes in interests based on content that the viewer has shared on social media. This allows products based on trends based on the viewer's social media activity to be displayed. Some or all of the above-described processing in the product display unit may be performed using AI, for example, or may be performed without using AI. For example, the product display unit can input the viewer's social media activity data into a generation AI and cause the generation AI to perform an analysis to display products based on trends.

[0096] The purchasing unit can estimate the viewer's emotions and adjust the flow of the purchasing checkout based on the estimated viewer's emotions. For example, if the viewer is excited, the AI ​​can provide a quick purchasing checkout. Also, if the viewer is relaxed, the AI ​​can provide a purchasing checkout with detailed instructions. Also, if the viewer is sad, the AI ​​can provide a purchasing checkout with a comforting message. For example, if the viewer is excited, the purchasing unit can provide a quick purchasing checkout. If the viewer is relaxed, the AI ​​can provide a purchasing checkout with detailed instructions. If the viewer is sad, the AI ​​can provide a purchasing checkout with a comforting message. In this way, the flow of the purchasing checkout is adjusted based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the purchasing unit can be performed, for example, using AI or without AI. For example, the purchasing department can input viewer emotional data into the generation AI and have the generation AI perform analysis to adjust the flow of the purchase process.

[0097] The purchasing unit can simplify the purchasing procedure by referring to the viewer's past purchasing history. For example, the purchasing unit uses AI to automatically fill in input fields based on information about products the viewer has purchased in the past. The purchasing unit can also use AI to suggest the optimal payment method based on payment methods the viewer has used in the past. The purchasing unit can also use AI to suggest the optimal delivery option based on the viewer's past purchasing history. For example, the purchasing unit automatically fills in input fields based on information about products the viewer has purchased in the past. It suggests the optimal payment method based on payment methods the viewer has used in the past. It suggests the optimal delivery option based on the viewer's past purchasing history. This simplifies the purchasing procedure based on the viewer's past purchasing history. Some or all of the above-mentioned processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input the viewer's past purchasing history data into a generation AI and have the generation AI perform an analysis to simplify the purchasing procedure.

[0098] The purchasing unit can customize the contents of the purchasing procedure based on the viewer's interest analysis results. For example, the purchasing unit uses AI to customize the purchasing procedure based on information about products in which the viewer is interested. The purchasing unit can also use AI to customize the purchasing procedure based on information about brands in which the viewer is interested. The purchasing unit can also use AI to customize the purchasing procedure based on information about price ranges in which the viewer is interested. For example, the purchasing unit customizes the purchasing procedure based on information about products in which the viewer is interested. The purchasing procedure is customized based on information about brands in which the viewer is interested. The purchasing procedure is customized based on information about price ranges in which the viewer is interested. In this way, the contents of the purchasing procedure are customized based on the viewer's interest analysis results. Some or all of the above-described processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input viewer interest analysis result data into a generation AI and have the generation AI perform an analysis to customize the contents of the purchasing procedure.

[0099] The purchasing unit can reflect viewer feedback and continuously improve the purchasing checkout algorithm. For example, the purchasing unit uses AI to adjust the purchasing checkout algorithm based on feedback provided by viewers. The purchasing unit can also improve the accuracy of the purchasing checkout algorithm based on viewer ratings. The purchasing unit can also analyze viewer comments and use AI to improve the purchasing checkout algorithm. For example, the purchasing unit adjusts the purchasing checkout algorithm based on feedback provided by viewers. Improves the accuracy of the purchasing checkout based on viewer ratings. Analyzes viewer comments and improves the purchasing checkout algorithm. In this way, the purchasing checkout algorithm is continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input viewer feedback data into the generation AI and have the generation AI perform analysis to continuously improve the purchasing checkout algorithm.

[0100] The purchasing unit can estimate the viewer's emotions and prioritize the purchase process based on the estimated viewer's emotions. For example, if the viewer is excited, the AI ​​prioritizes a quick purchase process. Furthermore, if the viewer is relaxed, the AI ​​can prioritize a purchase process that includes detailed explanations. Furthermore, if the viewer is sad, the AI ​​can prioritize a purchase process that includes a comforting message. For example, if the viewer is excited, the purchasing unit prioritizes a quick purchase process. If the viewer is relaxed, the AI ​​prioritizes a purchase process that includes detailed explanations. If the viewer is sad, the AI ​​prioritizes a purchase process that includes a comforting message. Thus, the purchase process is prioritized based on the viewer's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the purchasing unit may be performed using, for example, AI, or without AI. For example, the purchasing department can input viewer emotional data into the generation AI and have the generation AI perform an analysis to determine priorities for the purchase process.

[0101] The purchasing unit can provide a different purchasing procedure for each region by taking into account the viewer's geographic location information. For example, the purchasing unit uses AI to provide the optimal purchasing procedure based on delivery options for the viewer's region. The purchasing unit can also provide the optimal purchasing procedure by taking into account taxes and fees for the viewer's region. The purchasing unit can also provide the optimal payment method based on the currency for the viewer's region. For example, the purchasing unit provides the optimal purchasing procedure based on delivery options for the viewer's region. The purchasing unit provides the optimal purchasing procedure by taking into account taxes and fees for the viewer's region. The optimal payment method is provided based on the currency for the viewer's region. In this way, a different purchasing procedure is provided for each region based on the viewer's geographic location information. Some or all of the above-described processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input the viewer's geographic location information data into the generation AI and cause the generation AI to perform analysis to provide a different purchasing procedure for each region.

[0102] The purchasing unit can provide a purchasing procedure taking into account attribute information such as the viewer's age and gender. For example, the purchasing unit uses AI to provide a purchasing procedure tailored to the viewer's age group. The purchasing unit can also use AI to provide a purchasing procedure tailored to the viewer's gender. The purchasing unit can also use AI to provide an optimal purchasing procedure based on the viewer's attribute information. For example, the purchasing unit provides a purchasing procedure tailored to the viewer's age group. Provides a purchasing procedure tailored to the viewer's gender. Provides an optimal purchasing procedure based on the viewer's attribute information. In this way, a purchasing procedure is provided based on the viewer's attribute information. Some or all of the above-mentioned processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input viewer attribute information data into a generation AI and have the generation AI perform analysis to provide a purchasing procedure.

[0103] The purchasing unit can analyze the viewer's social media activity and provide a purchasing checkout based on trends. For example, the purchasing unit uses AI to provide a relevant purchasing checkout based on posts that the viewer has "liked" on social media. The purchasing unit can also use AI to analyze interests based on the activity of accounts that the viewer follows on social media. The purchasing unit can also use AI to analyze changes in interests based on content that the viewer has shared on social media. For example, the purchasing unit can provide a relevant purchasing checkout based on posts that the viewer has "liked" on social media. The purchasing unit can analyze interests based on the activity of accounts that the viewer follows on social media. The purchasing unit can analyze changes in interests based on content that the viewer has shared on social media. This provides a purchasing checkout based on trends based on the viewer's social media activity. Some or all of the above-described processing in the purchasing unit may be performed using AI, for example, or may be performed without using AI. For example, the purchasing unit can input the viewer's social media activity data into the generation AI and cause the generation AI to perform an analysis to provide a purchasing checkout based on trends.

[0104] The activity unit can estimate the viewer's emotions and adjust the activity schedule based on the estimated viewer's emotions. For example, if the viewer is excited, the AI ​​can schedule an energetic performance preferentially. Furthermore, if the viewer is relaxed, the AI ​​can schedule a calm performance preferentially. Furthermore, if the viewer is sad, the activity unit can schedule a comforting performance preferentially. For example, if the viewer is excited, the activity unit can schedule an energetic performance preferentially. If the viewer is relaxed, the activity unit can schedule a calm performance preferentially. If the viewer is sad, the activity unit can schedule a comforting performance preferentially. Thus, the activity schedule is adjusted based on the viewer's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the activity unit can be performed using, for example, an AI, or without an AI. For example, the activity department can input viewer emotional data into the generation AI and have the generation AI perform analysis to adjust the activity schedule.

[0105] The activity unit can select the optimal activity time by referring to the viewer's past viewing history. For example, the activity unit uses AI to select the optimal activity time based on the time period in which the viewer previously viewed programs. The activity unit can also use AI to select the optimal activity time based on the performance of a genre in which the viewer previously viewed programs. The activity unit can also use AI to select the optimal activity time based on the characteristics of idols the viewer previously viewed programs. For example, the activity unit selects the optimal activity time based on the time period in which the viewer previously viewed programs. The activity unit selects the optimal activity time based on the performance of a genre in which the viewer previously viewed programs. The activity unit selects the optimal activity time based on the characteristics of idols the viewer previously viewed programs. In this way, the optimal activity time is selected based on the viewer's past viewing history. Some or all of the above-described processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input the viewer's past viewing history data into the generation AI and have the generation AI perform an analysis to select the optimal activity time.

[0106] The activity unit can customize the activity content based on the viewer interest analysis results. For example, the activity unit uses AI to generate a performance in a genre that the viewer is interested in. The activity unit can also use AI to generate a performance that incorporates the style of an artist that the viewer is interested in. The activity unit can also use AI to generate a performance based on a theme that the viewer is interested in. For example, the activity unit generates a performance in a genre that the viewer is interested in. Generates a performance that incorporates the style of an artist that the viewer is interested in. Generates a performance based on a theme that the viewer is interested in. In this way, the activity content is customized based on the viewer interest analysis results. Some or all of the above-mentioned processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input viewer interest analysis result data into a generation AI and have the generation AI perform an analysis to customize the activity content.

[0107] The activity department can continuously improve the activity schedule by reflecting viewer feedback. For example, the activity department can have AI adjust the activity schedule based on feedback provided by viewers. The activity department can also have AI improve the accuracy of the activity schedule based on viewer ratings. The activity department can also analyze viewer comments and have AI improve the activity schedule. For example, the activity department can adjust the activity schedule based on feedback provided by viewers. Improve the accuracy of the activity schedule based on viewer ratings. Analyze viewer comments and improve the activity schedule. In this way, the activity schedule is continuously improved based on viewer feedback. Some or all of the above-mentioned processing in the activity department can be performed, for example, using AI or without using AI. For example, the activity department can input viewer feedback data into the generation AI and have the generation AI perform analysis to continuously improve the activity schedule.

[0108] The activity unit can estimate the viewer's emotions and prioritize activities based on the estimated viewer's emotions. For example, if the viewer is excited, the AI ​​can schedule an energetic performance preferentially. Furthermore, if the viewer is relaxed, the activity unit can schedule a calm performance preferentially. Furthermore, if the viewer is sad, the activity unit can schedule a comforting performance preferentially. For example, if the viewer is excited, the activity unit can schedule an energetic performance preferentially. If the viewer is relaxed, the activity unit can schedule a calm performance preferentially. If the viewer is sad, the activity unit can schedule a comforting performance preferentially. Thus, the prioritization of activities is determined based on the viewer's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the activity unit may be performed using, for example, an AI, or without an AI. For example, the activity department can input viewer emotional data into the generation AI and have the generation AI perform analysis to determine activity priorities.

[0109] The activity department can provide different activities for each region by taking into account the viewer's geographical location information. For example, the activity department uses AI to generate a performance based on popular genres in the viewer's region. The activity department can also use AI to generate a relevant performance based on event information in the viewer's region. The activity department can also use AI to generate a performance by taking into account the cultural background of the viewer's region. For example, the activity department generates a performance based on popular genres in the viewer's region. A relevant performance is generated based on event information in the viewer's region. A performance is generated by taking into account the cultural background of the viewer's region. In this way, different activities are provided for each region based on the viewer's geographical location information. Some or all of the above-described processing in the activity department may be performed using AI, for example, or may be performed without using AI. For example, the activity department can input viewer's geographical location information data into the generation AI and have the generation AI perform an analysis to provide different activities for each region.

[0110] The activity unit can provide activities taking into account attribute information such as the viewer's age and gender. For example, the activity unit uses AI to generate performances tailored to the viewer's age group. The activity unit can also use AI to generate performances tailored to the viewer's gender. The activity unit can also analyze the viewer's interests based on the viewer's attribute information and generate an optimal performance. For example, the activity unit generates a performance tailored to the viewer's age group. A performance tailored to the viewer's gender is generated. The interests are analyzed based on the viewer's attribute information and an optimal performance is generated. In this way, activities are provided based on the viewer's attribute information. Some or all of the above-described processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input viewer attribute information data into a generation AI and have the generation AI perform an analysis to provide activities.

[0111] The activity unit can analyze viewers' social media activities and provide trend-based activities. For example, the activity unit uses AI to generate relevant performances based on posts that viewers have "liked" on social media. The activity unit can also use AI to analyze interests based on the activity of accounts that viewers follow on social media. The activity unit can also use AI to analyze interest fluctuations based on content that viewers have shared on social media. For example, the activity unit generates relevant performances based on posts that viewers have "liked" on social media. The activity unit analyzes interests based on the activity of accounts that viewers follow on social media. The activity unit analyzes interest fluctuations based on content that viewers have shared on social media. In this way, trend-based activities are provided based on the viewers' social media activities. Some or all of the above-described processing in the activity unit may be performed using AI, for example, or may be performed without using AI. For example, the activity unit can input viewers' social media activity data into a generation AI and cause the generation AI to perform an analysis to provide trend-based activities. === Hard Collateral 1-1 === Each of the multiple elements including the interest analysis unit, performance generation unit, product display unit, purchase unit, and activity unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the interest analysis unit can analyze the interests of viewers using the control unit 46A of the smart device 14. The performance generation unit generates a performance based on the interests of viewers using the specific processing unit 290 of the data processing device 12. The product display unit displays products using the display 40A of the smart device 14. The purchase unit purchases products using the touch panel 38A of the smart device 14. The activity unit manages the idol's activities 24 hours a day using AI using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the interest analysis unit, performance generation unit, product display unit, purchase unit, and activity unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the interest analysis unit can analyze the viewer's interest using the control unit 46A of the smart glasses 214. The performance generation unit generates a performance based on the viewer's interest using the specific processing unit 290 of the data processing device 12. The product display unit displays products using the display of the smart glasses 214. The purchase unit purchases products using the touch panel of the smart glasses 214. The activity unit manages the idol's activities 24 hours a day using AI using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the interest analysis unit, performance generation unit, product display unit, purchasing unit, and activity unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the interest analysis unit can analyze the interests of viewers using the control unit 46A of the headset type terminal 314. The performance generation unit generates a performance based on the interests of viewers using the specific processing unit 290 of the data processing device 12. The product display unit displays products using the display 343 of the headset type terminal 314. The purchasing unit purchases products using the touch panel of the headset type terminal 314. The activity unit manages the idol's activities around the clock using AI using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the interest analysis unit, performance generation unit, product display unit, purchase unit, and activity unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the interest analysis unit can analyze the interests of viewers using the control unit 46A of the robot 414. The performance generation unit generates a performance based on the interests of viewers using the specific processing unit 290 of the data processing device 12. The product display unit displays products using the display of the robot 414. The purchase unit purchases products using the touch panel of the robot 414. The activity unit manages the idol's activities around the clock using AI using the specific processing unit 290 of the data processing device 12.

[0112] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0113] The live commerce system analyzes viewers' purchasing history and can suggest new products based on the genre, price range, and brand of products they have previously purchased. For example, it can display related new products based on the genre of products the viewer has previously purchased. It can also suggest products that fit the viewer's budget based on the price range of products the viewer has previously purchased. It can also display new products from the same brand based on the brand of products the viewer has previously purchased. This makes it possible to make more personalized product suggestions based on the viewer's purchasing history.

[0114] The live commerce system analyzes the viewer's geographic location information and can suggest products based on popular products and event information for each region. For example, related products can be displayed based on popular products in the viewer's region. Products related to events can also be suggested based on event information for the viewer's region. Furthermore, regionally specific products can be displayed taking into account the cultural background of the viewer's region. This makes it possible to suggest optimal products for each region based on the viewer's geographic location information.

[0115] The live commerce system analyzes viewers' social media activity and can suggest products based on the posts they have liked and the accounts they follow. For example, it can display related products based on the posts they have liked. It can also suggest products that viewers may be interested in based on the activity of the accounts they follow. It can also analyze changes in interests based on the content shared by viewers and make product suggestions in real time. This makes it possible to make more personalized product suggestions based on the viewer's social media activity.

[0116] The live commerce system can analyze the viewer's attribute information, such as age and gender, and suggest products according to those attributes. For example, it can display products tailored to the viewer's age group. It can also suggest products tailored to the viewer's gender. Furthermore, it can analyze the viewer's interests based on their attribute information and suggest the most suitable products. This makes it possible to suggest more personalized products based on the viewer's attribute information.

[0117] The live commerce system can reflect viewer feedback and continuously improve the product recommendation algorithm. For example, the product recommendation algorithm can be adjusted based on the feedback provided by viewers. The accuracy of product recommendations can also be improved based on viewer ratings. Furthermore, the product recommendation algorithm can be improved by analyzing viewer comments. In this way, the product recommendation algorithm can be continuously improved based on viewer feedback.

[0118] The live commerce system can estimate the viewer's emotions and adjust the product recommendations based on the estimated viewer's emotions. For example, if the viewer is excited, energetic products can be recommended. If the viewer is relaxed, calming products can be recommended. Furthermore, if the viewer is sad, comforting products can be recommended. This allows for more appropriate product recommendations based on the viewer's emotions.

[0119] The live commerce system can estimate the viewer's emotions and adjust the timing of product suggestions based on the estimated viewer's emotions. For example, if the viewer is excited, products can be suggested during an energetic performance. If the viewer is relaxed, products can be suggested during a calm performance. Furthermore, if the viewer is sad, products can be suggested during a comforting performance. In this way, the timing of product suggestions can be adjusted based on the viewer's emotions.

[0120] The live commerce system can estimate the viewer's emotions and adjust the order of product suggestions based on the estimated viewer's emotions. For example, if the viewer is excited, energetic products can be prioritized. If the viewer is relaxed, calming products can be prioritized. Furthermore, if the viewer is sad, comforting products can be prioritized. In this way, the order of product suggestions can be adjusted based on the viewer's emotions.

[0121] The live commerce system can estimate the viewer's emotions and adjust the flow of the purchase checkout based on the estimated viewer's emotions. For example, if the viewer is excited, a quick purchase checkout can be provided. If the viewer is relaxed, a purchase checkout with detailed explanations can be provided. Furthermore, if the viewer is sad, a purchase checkout with a comforting message can be provided. In this way, the flow of the purchase checkout can be adjusted based on the viewer's emotions.

[0122] The live commerce system can estimate the viewer's emotions and prioritize purchase checkouts based on the estimated viewer's emotions. For example, if the viewer is excited, a quick purchase checkout can be prioritized. If the viewer is relaxed, a purchase checkout that includes detailed explanations can be prioritized. Furthermore, if the viewer is sad, a purchase checkout that includes a comforting message can be prioritized. In this way, the purchase checkout can be prioritized based on the viewer's emotions.

[0123] The processing flow of the second embodiment will be briefly explained below.

[0124] Step 1: The interest analysis unit analyzes the viewer's interests. The viewer's interests include viewing history, search history, social media activity, etc. For example, the viewer's interests are identified based on the viewing history, the viewer's interests are identified based on the search history, and the viewer's interests are identified based on the social media activity. Step 2: The performance generation unit generates a performance based on the information analyzed by the interest analysis unit. The performance may include videos, music, live streaming, etc. For example, it may generate music in the genres the viewer likes, generate videos based on topics the viewer is interested in, or generate live streaming in the style of accounts the viewer follows. Step 3: The product display unit displays products during the performance generated by the performance generation unit. Products include physical goods, digital content, services, etc. For example, the product display unit displays the outfit worn by the virtual idol, the items used by the virtual idol, and the services introduced by the virtual idol. Step 4: The purchasing unit purchases the product displayed by the product display unit. The purchase may be performed by clicking, tapping, using a voice command, etc. For example, the viewer may purchase the product by clicking, tapping, or using a voice command.

[0125] 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.

[0126] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] 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.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0139] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0155] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0172] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] [Explanation of symbols]

[0197] 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. an interest analysis unit that analyzes the interests of viewers; a performance generation unit that generates a performance based on the information analyzed by the interest analysis unit; a product display unit that displays products during the performance generated by the performance generation unit; a purchasing unit for purchasing the product displayed by the product display unit. A system characterized by:

2. It will also have an activity department where AI idols can be constantly active.

2. The system of claim 1.

3. The interest analysis unit Estimate viewer emotions and improve the accuracy of interest analysis based on the estimated viewer emotions 2. The system of claim 1.

4. The interest analysis unit Analyze viewers' past viewing history and optimize interest analysis algorithms 2. The system of claim 1.

5. The interest analysis unit Analyze your audience's social media activity and reflect changes in their interests in real time 2. The system of claim 1.

6. The interest analysis unit Analyze regional interest trends based on viewers' geographic location 2. The system of claim 1.

7. The interest analysis unit Estimate viewer sentiment and adjust the order in which interest analysis results are displayed based on the estimated viewer sentiment.

2. The system of claim 1.

8. The interest analysis unit Analyze viewers' purchasing history and improve the accuracy of interest analysis 2. The system of claim 1.

9. The interest analysis unit Analyze viewers' interests based on demographic information such as age and gender 2. The system of claim 1.

Images