system

Abstract

The system according to this embodiment aims to enable viewers to easily purchase products featured on television programs. [Solution] The system according to the embodiment comprises an image analysis unit, a product identification unit, a recommendation unit, an eye-tracking unit, and a purchase acceptance unit. The image analysis unit analyzes an image. The product identification unit identifies a product based on the image analyzed by the image analysis unit. The recommendation unit recommends the product identified by the product identification unit to the viewer. The eye-tracking unit tracks the viewer's gaze. The purchase acceptance unit accepts purchases from the viewer to buy the product.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional technologies do not sufficiently provide a means for viewers to easily purchase products introduced on TV programs, and there is room for improvement.

[0005] The system according to the embodiment aims to enable viewers to easily purchase products introduced on TV programs.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an image analysis unit, a product identification unit, a recommendation unit, an eye-tracking unit, and a purchase acceptance unit. The image analysis unit analyzes an image. The product identification unit identifies a product based on the image analyzed by the image analysis unit. The recommendation unit recommends the product identified by the product identification unit to the viewer. The eye-tracking unit tracks the viewer's gaze. The purchase acceptance unit accepts purchases from the viewer for the purchase of a product. [Effects of the Invention]

[0007] The system according to this embodiment can make it easy for viewers to purchase products featured on television programs. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The product purchase system according to an embodiment of the present invention is a system that allows users to directly purchase products shown on a television program screen with an "OK!". This product purchase system uses generative AI to recognize products shown on the television program screen and recommends them to the viewer. Using an eye-tracking device that tracks the viewer's gaze, when the viewer looks at a product they are interested in, information about that product is displayed, and the viewer can purchase it directly through an "OK!". Furthermore, when a viewer purchases a product, they are provided with a $99 eye-tracking device. This device is used to track the viewer's gaze and identify products they are interested in. The viewer can use this device to purchase products directly from the television program screen. This mechanism allows viewers to easily purchase products they are interested in while watching television programs, improving advertising effectiveness. In addition, television program production teams can obtain product information from videos in the same way as before, so there is no increase in production effort. For example, the generative AI analyzes images to recognize products shown on the television program screen. Next, the generative AI makes recommendations to the viewer based on the products it has identified. These recommendations are made using an eye-tracking device that tracks the viewer's gaze. When a viewer looks at a product they are interested in, information about that product is displayed, and the viewer can purchase it directly through "OK!". Furthermore, when a viewer makes a purchase, they are provided with a $99 eye-tracking device. This device is used to track the viewer's gaze and identify the product they are interested in. Viewers can use this device to purchase products directly from the TV program screen. This system allows viewers to easily purchase products they are interested in while watching TV, improving advertising effectiveness. Also, TV program producers can obtain product information in videos in the same way as before, so there is no increase in production effort. In short, the product purchase system allows viewers to purchase products directly from the TV program screen.

[0029] The product purchase system according to this embodiment comprises an image analysis unit, a product identification unit, a recommendation unit, an eye-tracking unit, and a purchase acceptance unit. The image analysis unit analyzes images to recognize products displayed on a television program screen. For example, the image analysis unit uses a generation AI to recognize products displayed on a television program screen. The generation AI uses a deep learning algorithm to detect objects in an image and identify products. For example, the generation AI can recognize products by extracting features from an image and comparing them with a database. The generation AI can also analyze text information in an image to identify product names and brand names. The product identification unit identifies products based on the images analyzed by the image analysis unit. For example, the product identification unit uses a generation AI to identify products based on features in an image. The generation AI can identify products by comparing them with a database. The product identification unit can also analyze text information in an image to identify product names and brand names. The recommendation unit recommends products identified by the product identification unit to viewers. For example, the recommendation unit uses generative AI to recommend products based on the viewer's interests and preferences. The generative AI can analyze the viewer's eye-tracking data and past purchase history to recommend the most suitable products. The recommendation unit can also track the viewer's gaze and identify products they are interested in. The eye-tracking unit tracks the viewer's gaze and identifies products they are interested in. For example, the eye-tracking unit uses an eye-tracking device to track the viewer's gaze. The eye-tracking device acquires the viewer's eye-tracking data in real time and can identify products the viewer is interested in. The eye-tracking unit can also analyze the viewer's eye-tracking data to identify the viewer's interests and preferences. The purchase acceptance unit receives information from the viewer to purchase a product. For example, the purchase acceptance unit accepts information from the viewer when they say "OK!". The purchase acceptance unit can analyze the viewer's voice data to confirm their intention to purchase. The purchase acceptance unit can also analyze the viewer's eye-tracking data to identify products the viewer is interested in. As a result, the product purchase system according to this embodiment allows viewers to purchase products directly from the television program screen.

[0030] The image analysis unit can recognize products displayed on a television program screen. For example, the image analysis unit uses a generative AI to recognize products displayed on the television program screen. The generative AI uses a deep learning algorithm to detect objects in the image and identify products. For example, the generative AI can recognize products by extracting features from the image and comparing them with a database. The generative AI can also analyze text information in the image to identify product names and brand names. This allows for accurate recognition of products displayed on the television program screen. Some or all of the above-described processes in the image analysis unit are performed using the generative AI. For example, to recognize products displayed on a television program screen, the image analysis unit inputs image data into the generative AI, which then identifies the products.

[0031] The product identification unit can identify products based on images analyzed by the image analysis unit. For example, the product identification unit uses a generation AI to identify products based on features in the image. The generation AI can identify products by comparing them with a database. The product identification unit can also analyze text information in the image to identify product names and brand names. This allows for accurate product identification based on the analyzed image. Some or all of the above-described processes in the product identification unit are performed using the generation AI. For example, the product identification unit inputs image data analyzed by the image analysis unit into the generation AI, which then identifies the product.

[0032] The recommendation unit can recommend products identified by the product identification unit to viewers. The recommendation unit, for example, uses a generative AI to recommend products based on the viewer's interests and preferences. The generative AI can analyze the viewer's eye-tracking data and past purchase history to recommend the most suitable products. The recommendation unit can also track the viewer's gaze and identify products they are interested in. This allows for the effective recommendation of identified products to viewers. Some or all of the above-described processes in the recommendation unit are performed using the generative AI. For example, the recommendation unit inputs product data identified by the product identification unit into the generative AI, which then recommends the most suitable products to the viewer.

[0033] The eye-tracking unit can track the viewer's gaze and identify products that the viewer is interested in. For example, the eye-tracking unit uses an eye-tracking device to track the viewer's gaze. The eye-tracking device acquires the viewer's gaze data in real time and can identify products that the viewer is interested in. The eye-tracking unit can also analyze the viewer's gaze data to identify the viewer's interests and preferences. This allows for the accurate identification of products that the viewer is interested in. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's gaze data into the AI, which then identifies products that the viewer is interested in.

[0034] The purchase reception unit can receive information from viewers to purchase products. For example, the purchase reception unit can receive information to purchase a product when a viewer says "OK!". The purchase reception unit can analyze the viewer's voice data to confirm their intention to purchase. The purchase reception unit can also analyze the viewer's eye-tracking data to identify products that the viewer is interested in. This makes it easy for viewers to purchase products. Some or all of the above processes in the purchase reception unit are performed using AI. For example, the purchase reception unit inputs the viewer's voice data into the AI, and the AI ​​confirms the intention to purchase.

[0035] The image analysis unit can apply different image analysis algorithms depending on the genre of the program. For example, in a drama program, the generating AI applies an image analysis algorithm that focuses on the characters' costumes and props. In a cooking program, the generating AI applies an image analysis algorithm that focuses on ingredients and cooking utensils. In a sports program, the generating AI applies an image analysis algorithm that focuses on sports equipment and the athletes' gear. This enables optimal image analysis according to the genre of the program. Some or all of the above processing in the image analysis unit is performed using the generating AI. For example, the image analysis unit inputs program genre information into the generating AI, and the generating AI applies the most suitable image analysis algorithm.

[0036] The image analysis unit can improve the accuracy of its analysis by referring to past analysis data during image analysis. For example, the image analysis unit can refer to data of the same product that has been analyzed in the past, and the generating AI can improve the accuracy of the analysis. The generating AI can also refer to product data used in past programs, and to refer to past viewer reaction data, and to improve the accuracy of the analysis. In this way, the accuracy of the analysis is improved by referring to past data. Some or all of the above processes in the image analysis unit are performed using the generating AI. For example, the image analysis unit inputs past analysis data into the generating AI, and the generating AI improves the accuracy of the analysis.

[0037] The image analysis unit can determine the priority of analysis by referring to the viewer's gaze data during image analysis. For example, the image analysis unit will prioritize analyzing products that the viewer has looked at for a long time. It will also prioritize analyzing products that the viewer has frequently moved their gaze to. If the viewer concentrates their gaze on a specific area, it will prioritize analyzing products in that area. In this way, the priority of analysis can be determined by referring to the viewer's gaze data. Some or all of the above processing in the image analysis unit is performed using a generating AI. For example, the image analysis unit inputs the viewer's gaze data into the generating AI, and the generating AI determines the priority of analysis.

[0038] The image analysis unit can adjust the accuracy of its analysis based on the program's broadcast time. For example, during prime time, the generating AI enhances the accuracy of the image analysis and extracts detailed product information. During late-night hours, the generating AI maintains normal image analysis accuracy and extracts standard product information. During early morning hours, the generating AI reduces the accuracy of the image analysis and extracts simplified product information. This allows the accuracy of the analysis to be adjusted according to the broadcast time. Some or all of the above processing in the image analysis unit is performed using the generating AI. For example, the image analysis unit inputs the program's broadcast time information into the generating AI, and the generating AI adjusts the accuracy of the analysis.

[0039] The product identification unit can apply different identification algorithms depending on the product category when identifying a product. For example, in the clothing category, the product identification unit applies an algorithm where the generating AI identifies products based on color and design. In the home appliance category, the generating AI applies an algorithm where the generating AI identifies products based on function and brand. In the food category, the generating AI applies an algorithm where the generating AI identifies products based on ingredients and packaging. This enables optimal identification according to the product category. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs product category information into the generating AI, and the generating AI applies the most suitable identification algorithm.

[0040] The product identification unit can improve the accuracy of product identification by referring to past identification data. For example, the product identification unit can refer to data of the same product that was previously identified, and the generating AI can improve the accuracy of identification. The generating AI can also refer to product data used in past programs to improve the accuracy of identification. The generating AI can also refer to past viewer reaction data to improve the accuracy of identification. In this way, the accuracy of identification is improved by referring to past data. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs past identification data into the generating AI, and the generating AI improves the accuracy of identification.

[0041] The product identification unit can determine specific priorities when identifying products by referring to the viewer's purchase history. For example, the product identification unit may prioritize identifying products similar to those the viewer has previously purchased. It may also prioritize identifying products in categories that the viewer frequently purchases. If the viewer prefers a particular brand, it may prioritize identifying products from that brand. In this way, specific priorities can be determined by referring to the viewer's purchase history. Some or all of the above processing in the product identification unit is performed using a generating AI. For example, the product identification unit inputs the viewer's purchase history data into the generating AI, and the generating AI determines specific priorities.

[0042] The product identification unit can adjust the accuracy of product identification based on the product's price range. For example, for high-priced products, the generating AI increases the accuracy of product identification and provides detailed product information. For mid-priced products, the generating AI maintains a normal level of accuracy and provides standard product information. For low-priced products, the generating AI lowers the accuracy of product identification and provides simplified product information. This allows the accuracy of product identification to be adjusted according to the product's price range. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs product price range information into the generating AI, and the generating AI adjusts the accuracy of product identification.

[0043] The recommendation unit can adjust the level of detail in recommendations based on the popularity of the products. For example, for highly popular products, the generating AI provides detailed recommendation information. For moderately popular products, the generating AI provides standard recommendation information. For less popular products, the generating AI provides simplified recommendation information. This allows the level of detail in recommendations to be adjusted according to the popularity of the products. Some or all of the above processing in the recommendation unit is performed using the generating AI. For example, the recommendation unit inputs product popularity data into the generating AI, and the generating AI adjusts the level of detail in the recommendations.

[0044] The recommendation unit can improve the accuracy of recommendations by referring to the viewer's past recommendation history. For example, the recommendation unit can recommend products similar to those the viewer has shown interest in in the past, products related to products the viewer has previously purchased, and products in the same category as products the viewer has previously given high ratings to. In this way, the accuracy of recommendations is improved by referring to the viewer's past recommendation history. Some or all of the above processes in the recommendation unit are performed using a generative AI. For example, the recommendation unit inputs the viewer's past recommendation history data into the generative AI, which then improves the accuracy of recommendations.

[0045] The recommendation unit can determine recommendation priorities by referring to the viewer's eye-tracking data. For example, the recommendation unit may prioritize recommending products that the viewer has looked at for a long time, products that the viewer has frequently moved their eyes to, or products in a specific area if the viewer has focused their gaze on that area. In this way, the recommendation unit can determine recommendation priorities by referring to the viewer's eye-tracking data. Some or all of the above processing in the recommendation unit is performed using a generative AI. For example, the recommendation unit inputs the viewer's eye-tracking data into the generative AI, which then determines the recommendation priorities.

[0046] The recommendation unit can adjust the accuracy of its recommendations based on the product's inventory status. For example, for products with ample stock, the generating AI provides detailed recommendation information. For products with low stock, the generating AI provides standard recommendation information. For products that are out of stock, the generating AI provides recommendations for alternative products. This allows the recommendation unit to adjust the accuracy of its recommendations according to the product's inventory status. Some or all of the above processing in the recommendation unit is performed using the generating AI. For example, the recommendation unit inputs product inventory data into the generating AI, and the generating AI adjusts the accuracy of the recommendations.

[0047] The eye-tracking unit can improve tracking accuracy by analyzing the viewer's gaze patterns during eye tracking. For example, the eye-tracking unit analyzes patterns in which viewers concentrate their gaze on specific areas, and the AI ​​improves tracking accuracy. The AI ​​also analyzes patterns in which viewers frequently shift their gaze, and the AI ​​improves tracking accuracy by analyzing patterns in which viewers fix their gaze for extended periods. In this way, tracking accuracy is improved by analyzing the viewer's gaze patterns. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs viewer gaze pattern data into the AI, and the AI ​​improves tracking accuracy.

[0048] The eye-tracking unit can adjust the tracking accuracy by referring to the viewer's device information during eye tracking. For example, if the viewer is using a smartphone, the AI ​​adjusts the tracking accuracy based on the device's screen size. If the viewer is using a tablet, the AI ​​adjusts the tracking accuracy based on the device's screen size. If the viewer is using a smart TV, the AI ​​adjusts the tracking accuracy based on the device's screen size. This allows the tracking accuracy to be adjusted based on the viewer's device information. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's device information into the AI, and the AI ​​adjusts the tracking accuracy.

[0049] The eye-tracking unit can improve tracking accuracy by analyzing the viewer's gaze data in real time during eye tracking. For example, the eye-tracking unit analyzes data on where the viewer moves their gaze in real time, and the AI ​​improves tracking accuracy. The AI ​​analyzes data on where the viewer fixes their gaze in real time, and the AI ​​improves tracking accuracy. The AI ​​analyzes data on where the viewer concentrates their gaze in real time, and the AI ​​improves tracking accuracy. In this way, tracking accuracy is improved by analyzing the viewer's gaze data in real time. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's real-time gaze data into the AI, and the AI ​​improves tracking accuracy.

[0050] The eye-tracking unit can adjust the tracking accuracy by comparing the viewer's eye-tracking data with past data during eye-tracking. For example, the eye-tracking unit improves tracking accuracy by comparing it with the viewer's past eye-tracking data, and by comparing it with the viewer's past eye-tracking patterns, and by comparing it with the viewer's past eye movement data. In this way, tracking accuracy is improved by comparing it with the viewer's past data. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's past eye-tracking data into the AI, and the AI ​​adjusts the tracking accuracy.

[0051] The purchase acceptance unit can improve the accuracy of its acceptance process by referring to the viewer's past purchase history. For example, the purchase acceptance unit may prioritize accepting orders for products similar to those the viewer has previously purchased. It may also prioritize accepting orders for products in categories that the viewer frequently purchases. If the viewer prefers a particular brand, it may prioritize accepting orders for products from that brand. This improves the accuracy of the acceptance process by referring to the viewer's past purchase history. Some or all of the above processes in the purchase acceptance unit are performed using AI. For example, the purchase acceptance unit inputs the viewer's past purchase history data into the AI, which then improves the accuracy of the acceptance process.

[0052] The purchase acceptance unit can customize the acceptance method by referring to the viewer's device information when accepting a purchase. For example, if the viewer is using a smartphone, the AI ​​provides a purchase acceptance method optimized for the device. If the viewer is using a tablet, the AI ​​provides a purchase acceptance method optimized for the device. If the viewer is using a smart TV, the AI ​​provides a purchase acceptance method optimized for the device. This allows the acceptance method to be customized based on the viewer's device information. Some or all of the above processing in the purchase acceptance unit is performed using AI. For example, the purchase acceptance unit inputs the viewer's device information into the AI, and the AI ​​customizes the acceptance method.

[0053] The purchase acceptance unit can improve the accuracy of its acceptance process by referring to the viewer's eye-tracking data during the acceptance process. For example, the purchase acceptance unit prioritizes accepting orders for products that the viewer has looked at for an extended period of time. It also prioritizes accepting orders for products that the viewer has frequently shifted their gaze to. If the viewer concentrates their gaze on a particular area, it prioritizes accepting orders for products in that area. In this way, the accuracy of the acceptance process is improved by referring to the viewer's eye-tracking data. Some or all of the above processing in the purchase acceptance unit is performed using AI. For example, the purchase acceptance unit inputs the viewer's eye-tracking data into the AI, which then improves the accuracy of the acceptance process.

[0054] The purchase acceptance unit can analyze the viewer's purchase history in real time and adjust the acceptance method accordingly. For example, the purchase acceptance unit may prioritize accepting orders for products similar to those the viewer has previously purchased. It may also prioritize accepting orders for products in categories that the viewer frequently purchases. If the viewer prefers a particular brand, it may prioritize accepting orders for products from that brand. In this way, the acceptance method can be adjusted by analyzing the viewer's purchase history in real time. Some or all of the above processes in the purchase acceptance unit are performed using AI. For example, the purchase acceptance unit inputs the viewer's purchase history data into the AI, and the AI ​​adjusts the acceptance method.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The product purchase system can also include a history analysis unit that analyzes the user's purchase history. Based on past purchase data, the history analysis unit identifies product categories and brands preferred by the viewer and provides this information to the recommendation unit. For example, it can prioritize recommending product categories that the viewer has frequently purchased in the past. Furthermore, if the viewer prefers a particular brand, it can prioritize recommending products from that brand. It can also predict and recommend new products that the viewer might be interested in, based on their purchase history. This allows for more personalized recommendations by leveraging the viewer's purchase history.

[0057] The product purchase system can also include a social media analytics unit that analyzes viewers' social media activity. This unit identifies products and brands mentioned by viewers on social media and provides this information to the recommendation unit. For example, it can prioritize recommending product categories that viewers frequently mention on social media. It can also recommend products featured by brands and influencers that viewers follow. Furthermore, it can predict and recommend products that viewers might be interested in based on their social media responses. This enables more personalized recommendations by leveraging viewers' social media activity.

[0058] The product purchase system can also include a location information analysis unit that utilizes the viewer's location information. Based on the viewer's current location and past travel history, the location information analysis unit identifies products that the viewer might be interested in and provides them to the recommendation unit. For example, it can prioritize recommending products sold in stores in areas the viewer frequently visits. If the viewer is traveling, it can also recommend local specialties or popular items from tourist destinations in that area. Furthermore, based on the viewer's location information, it can provide information on events and sales that the viewer might be interested in. This enables more personalized recommendations by leveraging the viewer's location information.

[0059] The product purchase system can also include a health data analysis department that utilizes viewers' health data. The health data analysis department identifies products likely to interest viewers based on their health status and fitness data, and provides this information to the recommendation department. For example, if a viewer is interested in fitness, fitness-related products can be prioritized for recommendation. Furthermore, if a viewer has specific health goals, products related to those goals can be recommended. Additionally, based on viewers' health data, it's possible to predict and recommend health foods and supplements that viewers might be interested in. This enables more personalized recommendations by leveraging viewers' health data.

[0060] The product purchase system can also include an incentive provision section to further enhance viewers' purchasing intent. This incentive provision section offers benefits and discounts when viewers purchase products. For example, it could offer a coupon usable for future purchases when a viewer buys a specific product. It could also offer free shipping or point rewards when viewers purchase products above a certain amount. Furthermore, if a viewer refers a friend who makes a purchase, both the referrer and the referred person can receive benefits. This can increase viewers' purchasing intent and encourage the use of the product purchase system.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The image analysis unit analyzes images to recognize products displayed on television screens. For example, it uses generative AI and deep learning algorithms to detect objects in images and identify products. It recognizes products by extracting features from images and comparing them with a database. It can also analyze text information in images to identify product names and brand names. Step 2: The product identification unit identifies products based on images analyzed by the image analysis unit. For example, it can use a generation AI to identify products based on features in the image and then compare them with a database. It can also analyze text information in the image to identify product names and brand names. Step 3: The recommendation unit recommends products identified by the product identification unit to the viewer. For example, it can use generative AI to recommend products based on the viewer's interests and preferences. By analyzing the viewer's eye-tracking data and past purchase history, it can recommend the most suitable products. It can also track the viewer's gaze and identify products they are interested in. Step 4: The eye-tracking unit tracks the viewer's gaze and identifies products that the viewer is interested in. For example, using an eye-tracking device, the viewer's gaze is tracked in real time to identify products that the viewer is interested in. It is also possible to analyze the viewer's gaze data to identify their interests and preferences. Step 5: The purchase reception unit receives information from viewers to purchase products. For example, if a viewer says "OK!", the unit receives the information to purchase the product. The unit can analyze the viewer's voice data to confirm their intention to purchase. It can also analyze the viewer's eye-tracking data to identify products that the viewer is interested in.

[0063] (Example of form 2) The product purchase system according to an embodiment of the present invention is a system that allows users to directly purchase products shown on a television program screen with an "OK!". This product purchase system uses generative AI to recognize products shown on the television program screen and recommends them to the viewer. Using an eye-tracking device that tracks the viewer's gaze, when the viewer looks at a product they are interested in, information about that product is displayed, and the viewer can purchase it directly through an "OK!". Furthermore, when a viewer purchases a product, they are provided with a $99 eye-tracking device. This device is used to track the viewer's gaze and identify products they are interested in. The viewer can use this device to purchase products directly from the television program screen. This mechanism allows viewers to easily purchase products they are interested in while watching television programs, improving advertising effectiveness. In addition, television program production teams can obtain product information from videos in the same way as before, so there is no increase in production effort. For example, the generative AI analyzes images to recognize products shown on the television program screen. Next, the generative AI makes recommendations to the viewer based on the products it has identified. These recommendations are made using an eye-tracking device that tracks the viewer's gaze. When a viewer looks at a product they are interested in, information about that product is displayed, and the viewer can purchase it directly through "OK!". Furthermore, when a viewer makes a purchase, they are provided with a $99 eye-tracking device. This device is used to track the viewer's gaze and identify the product they are interested in. Viewers can use this device to purchase products directly from the TV program screen. This system allows viewers to easily purchase products they are interested in while watching TV, improving advertising effectiveness. Also, TV program producers can obtain product information in videos in the same way as before, so there is no increase in production effort. In short, the product purchase system allows viewers to purchase products directly from the TV program screen.

[0064] The product purchase system according to this embodiment comprises an image analysis unit, a product identification unit, a recommendation unit, an eye-tracking unit, and a purchase acceptance unit. The image analysis unit analyzes images to recognize products displayed on a television program screen. For example, the image analysis unit uses a generation AI to recognize products displayed on a television program screen. The generation AI uses a deep learning algorithm to detect objects in an image and identify products. For example, the generation AI can recognize products by extracting features from an image and comparing them with a database. The generation AI can also analyze text information in an image to identify product names and brand names. The product identification unit identifies products based on the images analyzed by the image analysis unit. For example, the product identification unit uses a generation AI to identify products based on features in an image. The generation AI can identify products by comparing them with a database. The product identification unit can also analyze text information in an image to identify product names and brand names. The recommendation unit recommends products identified by the product identification unit to viewers. For example, the recommendation unit uses generative AI to recommend products based on the viewer's interests and preferences. The generative AI can analyze the viewer's eye-tracking data and past purchase history to recommend the most suitable products. The recommendation unit can also track the viewer's gaze and identify products they are interested in. The eye-tracking unit tracks the viewer's gaze and identifies products they are interested in. For example, the eye-tracking unit uses an eye-tracking device to track the viewer's gaze. The eye-tracking device acquires the viewer's eye-tracking data in real time and can identify products the viewer is interested in. The eye-tracking unit can also analyze the viewer's eye-tracking data to identify the viewer's interests and preferences. The purchase acceptance unit receives information from the viewer to purchase a product. For example, the purchase acceptance unit accepts information from the viewer when they say "OK!". The purchase acceptance unit can analyze the viewer's voice data to confirm their intention to purchase. The purchase acceptance unit can also analyze the viewer's eye-tracking data to identify products the viewer is interested in. As a result, the product purchase system according to this embodiment allows viewers to purchase products directly from the television program screen.

[0065] The image analysis unit can recognize products displayed on a television program screen. For example, the image analysis unit uses a generative AI to recognize products displayed on the television program screen. The generative AI uses a deep learning algorithm to detect objects in the image and identify products. For example, the generative AI can recognize products by extracting features from the image and comparing them with a database. The generative AI can also analyze text information in the image to identify product names and brand names. This allows for accurate recognition of products displayed on the television program screen. Some or all of the above-described processes in the image analysis unit are performed using the generative AI. For example, to recognize products displayed on a television program screen, the image analysis unit inputs image data into the generative AI, which then identifies the products.

[0066] The product identification unit can identify products based on images analyzed by the image analysis unit. For example, the product identification unit uses a generation AI to identify products based on features in the image. The generation AI can identify products by comparing them with a database. The product identification unit can also analyze text information in the image to identify product names and brand names. This allows for accurate product identification based on the analyzed image. Some or all of the above-described processes in the product identification unit are performed using the generation AI. For example, the product identification unit inputs image data analyzed by the image analysis unit into the generation AI, which then identifies the product.

[0067] The recommendation unit can recommend products identified by the product identification unit to viewers. The recommendation unit, for example, uses a generative AI to recommend products based on the viewer's interests and preferences. The generative AI can analyze the viewer's eye-tracking data and past purchase history to recommend the most suitable products. The recommendation unit can also track the viewer's gaze and identify products they are interested in. This allows for the effective recommendation of identified products to viewers. Some or all of the above-described processes in the recommendation unit are performed using the generative AI. For example, the recommendation unit inputs product data identified by the product identification unit into the generative AI, which then recommends the most suitable products to the viewer.

[0068] The eye-tracking unit can track the viewer's gaze and identify products that the viewer is interested in. For example, the eye-tracking unit uses an eye-tracking device to track the viewer's gaze. The eye-tracking device acquires the viewer's gaze data in real time and can identify products that the viewer is interested in. The eye-tracking unit can also analyze the viewer's gaze data to identify the viewer's interests and preferences. This allows for the accurate identification of products that the viewer is interested in. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's gaze data into the AI, which then identifies products that the viewer is interested in.

[0069] The purchase reception unit can receive information from viewers to purchase products. For example, the purchase reception unit can receive information to purchase a product when a viewer says "OK!". The purchase reception unit can analyze the viewer's voice data to confirm their intention to purchase. The purchase reception unit can also analyze the viewer's eye-tracking data to identify products that the viewer is interested in. This makes it easy for viewers to purchase products. Some or all of the above processes in the purchase reception unit are performed using AI. For example, the purchase reception unit inputs the viewer's voice data into the AI, and the AI ​​confirms the intention to purchase.

[0070] The image analysis unit can estimate the viewer's emotions and adjust the accuracy of the image analysis based on the estimated viewer emotions. For example, if the viewer is excited, the generating AI will increase the accuracy of the image analysis and extract more detailed product information. If the viewer is relaxed, the generating AI will maintain normal accuracy and extract standard product information. If the viewer is tired, the generating AI will decrease the accuracy of the image analysis and extract simplified product information. This allows the accuracy of the image analysis to be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the image analysis unit is performed using the generating AI. For example, the image analysis unit inputs viewer emotion data into the generating AI, and the generating AI adjusts the accuracy of the image analysis.

[0071] The image analysis unit can apply different image analysis algorithms depending on the genre of the program. For example, in a drama program, the generating AI applies an image analysis algorithm that focuses on the characters' costumes and props. In a cooking program, the generating AI applies an image analysis algorithm that focuses on ingredients and cooking utensils. In a sports program, the generating AI applies an image analysis algorithm that focuses on sports equipment and the athletes' gear. This enables optimal image analysis according to the genre of the program. Some or all of the above processing in the image analysis unit is performed using the generating AI. For example, the image analysis unit inputs program genre information into the generating AI, and the generating AI applies the most suitable image analysis algorithm.

[0072] The image analysis unit can improve the accuracy of its analysis by referring to past analysis data during image analysis. For example, the image analysis unit can refer to data of the same product that has been analyzed in the past, and the generating AI can improve the accuracy of the analysis. The generating AI can also refer to product data used in past programs, and to refer to past viewer reaction data, and to improve the accuracy of the analysis. In this way, the accuracy of the analysis is improved by referring to past data. Some or all of the above processes in the image analysis unit are performed using the generating AI. For example, the image analysis unit inputs past analysis data into the generating AI, and the generating AI improves the accuracy of the analysis.

[0073] The image analysis unit can estimate the viewer's emotions and adjust the display method of the analysis results based on the estimated viewer emotions. For example, if the viewer is excited, the generating AI will visually highlight and display the analysis results. If the viewer is relaxed, the generating AI will display the analysis results gently. If the viewer is tired, the generating AI will display the analysis results concisely. In this way, the display method of the analysis results can be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the image analysis unit is performed using the generating AI. For example, the image analysis unit inputs viewer emotion data into the generating AI, and the generating AI adjusts the display method of the analysis results.

[0074] The image analysis unit can determine the priority of analysis by referring to the viewer's gaze data during image analysis. For example, the image analysis unit will prioritize analyzing products that the viewer has looked at for a long time. It will also prioritize analyzing products that the viewer has frequently moved their gaze to. If the viewer concentrates their gaze on a specific area, it will prioritize analyzing products in that area. In this way, the priority of analysis can be determined by referring to the viewer's gaze data. Some or all of the above processing in the image analysis unit is performed using a generating AI. For example, the image analysis unit inputs the viewer's gaze data into the generating AI, and the generating AI determines the priority of analysis.

[0075] The image analysis unit can adjust the accuracy of its analysis based on the program's broadcast time. For example, during prime time, the generating AI enhances the accuracy of the image analysis and extracts detailed product information. During late-night hours, the generating AI maintains normal image analysis accuracy and extracts standard product information. During early morning hours, the generating AI reduces the accuracy of the image analysis and extracts simplified product information. This allows the accuracy of the analysis to be adjusted according to the broadcast time. Some or all of the above processing in the image analysis unit is performed using the generating AI. For example, the image analysis unit inputs the program's broadcast time information into the generating AI, and the generating AI adjusts the accuracy of the analysis.

[0076] The product identification unit can estimate the viewer's emotions and adjust the accuracy of product identification based on the estimated viewer emotions. For example, if the viewer is excited, the product identification unit's generating AI will increase the accuracy of product identification and provide detailed product information. If the viewer is relaxed, the generating AI will maintain a normal level of accuracy and provide standard product information. If the viewer is tired, the generating AI will decrease the accuracy of product identification and provide simplified product information. This allows the accuracy of product identification to be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs viewer emotion data into the generating AI, and the generating AI adjusts the accuracy of product identification.

[0077] The product identification unit can apply different identification algorithms depending on the product category when identifying a product. For example, in the clothing category, the product identification unit applies an algorithm where the generating AI identifies products based on color and design. In the home appliance category, the generating AI applies an algorithm where the generating AI identifies products based on function and brand. In the food category, the generating AI applies an algorithm where the generating AI identifies products based on ingredients and packaging. This enables optimal identification according to the product category. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs product category information into the generating AI, and the generating AI applies the most suitable identification algorithm.

[0078] The product identification unit can improve the accuracy of product identification by referring to past identification data. For example, the product identification unit can refer to data of the same product that was previously identified, and the generating AI can improve the accuracy of identification. The generating AI can also refer to product data used in past programs to improve the accuracy of identification. The generating AI can also refer to past viewer reaction data to improve the accuracy of identification. In this way, the accuracy of identification is improved by referring to past data. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs past identification data into the generating AI, and the generating AI improves the accuracy of identification.

[0079] The product identification unit can estimate the viewer's emotions and adjust how the identified product is displayed based on the estimated viewer emotions. For example, if the viewer is excited, the product identification unit's generating AI will visually highlight the identified product. If the viewer is relaxed, the generating AI will display the identified product gently. If the viewer is tired, the generating AI will display the identified product concisely. This allows the product display method to be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs viewer emotion data into the generating AI, and the generating AI adjusts how the product is displayed.

[0080] The product identification unit can determine specific priorities when identifying products by referring to the viewer's purchase history. For example, the product identification unit may prioritize identifying products similar to those the viewer has previously purchased. It may also prioritize identifying products in categories that the viewer frequently purchases. If the viewer prefers a particular brand, it may prioritize identifying products from that brand. In this way, specific priorities can be determined by referring to the viewer's purchase history. Some or all of the above processing in the product identification unit is performed using a generating AI. For example, the product identification unit inputs the viewer's purchase history data into the generating AI, and the generating AI determines specific priorities.

[0081] The product identification unit can adjust the accuracy of product identification based on the product's price range. For example, for high-priced products, the generating AI increases the accuracy of product identification and provides detailed product information. For mid-priced products, the generating AI maintains a normal level of accuracy and provides standard product information. For low-priced products, the generating AI lowers the accuracy of product identification and provides simplified product information. This allows the accuracy of product identification to be adjusted according to the product's price range. Some or all of the above processing in the product identification unit is performed using the generating AI. For example, the product identification unit inputs product price range information into the generating AI, and the generating AI adjusts the accuracy of product identification.

[0082] The recommendation unit can estimate the viewer's emotions and adjust the way recommendations are presented based on those emotions. For example, if the viewer is excited, the generative AI will visually highlight the recommendations. If the viewer is relaxed, the generative AI will present the recommendations gently. If the viewer is tired, the generative AI will present the recommendations concisely. This allows the recommendation unit to adjust the way recommendations are presented according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recommendation unit is performed using the generative AI. For example, the recommendation unit inputs viewer emotion data into the generative AI, and the generative AI adjusts the way recommendations are presented.

[0083] The recommendation unit can adjust the level of detail in recommendations based on the popularity of the products. For example, for highly popular products, the generating AI provides detailed recommendation information. For moderately popular products, the generating AI provides standard recommendation information. For less popular products, the generating AI provides simplified recommendation information. This allows the level of detail in recommendations to be adjusted according to the popularity of the products. Some or all of the above processing in the recommendation unit is performed using the generating AI. For example, the recommendation unit inputs product popularity data into the generating AI, and the generating AI adjusts the level of detail in the recommendations.

[0084] The recommendation unit can improve the accuracy of recommendations by referring to the viewer's past recommendation history. For example, the recommendation unit can recommend products similar to those the viewer has shown interest in in the past, products related to products the viewer has previously purchased, and products in the same category as products the viewer has previously given high ratings to. In this way, the accuracy of recommendations is improved by referring to the viewer's past recommendation history. Some or all of the above processes in the recommendation unit are performed using a generative AI. For example, the recommendation unit inputs the viewer's past recommendation history data into the generative AI, which then improves the accuracy of recommendations.

[0085] The recommendation unit can estimate the viewer's emotions and adjust the order of recommendations based on the estimated emotions. For example, if the viewer is excited, the generative AI will first recommend products that are visually highlighted. If the viewer is relaxed, the generative AI will first recommend products that are displayed calmly. If the viewer is tired, the generative AI will first recommend products that are displayed concisely. This allows the order of recommendations to be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recommendation unit is performed using the generative AI. For example, the recommendation unit inputs viewer emotion data into the generative AI, and the generative AI adjusts the order of recommendations.

[0086] The recommendation unit can determine recommendation priorities by referring to the viewer's eye-tracking data. For example, the recommendation unit may prioritize recommending products that the viewer has looked at for a long time, products that the viewer has frequently moved their eyes to, or products in a specific area if the viewer has focused their gaze on that area. In this way, the recommendation unit can determine recommendation priorities by referring to the viewer's eye-tracking data. Some or all of the above processing in the recommendation unit is performed using a generative AI. For example, the recommendation unit inputs the viewer's eye-tracking data into the generative AI, which then determines the recommendation priorities.

[0087] The recommendation unit can adjust the accuracy of its recommendations based on the product's inventory status. For example, for products with ample stock, the generating AI provides detailed recommendation information. For products with low stock, the generating AI provides standard recommendation information. For products that are out of stock, the generating AI provides recommendations for alternative products. This allows the recommendation unit to adjust the accuracy of its recommendations according to the product's inventory status. Some or all of the above processing in the recommendation unit is performed using the generating AI. For example, the recommendation unit inputs product inventory data into the generating AI, and the generating AI adjusts the accuracy of the recommendations.

[0088] The eye-tracking unit can estimate the viewer's emotions and adjust the accuracy of eye-tracking based on the estimated emotions. For example, if the viewer is excited, the AI ​​increases the accuracy of eye-tracking and acquires detailed eye-tracking data. If the viewer is relaxed, the AI ​​maintains normal accuracy and acquires standard eye-tracking data. If the viewer is tired, the AI ​​decreases the accuracy of eye-tracking and acquires simplified eye-tracking data. This allows the accuracy of eye-tracking to be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or AI. The AI ​​is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs viewer emotion data into the AI, and the AI ​​adjusts the accuracy of eye-tracking.

[0089] The eye-tracking unit can improve tracking accuracy by analyzing the viewer's gaze patterns during eye tracking. For example, the eye-tracking unit analyzes patterns in which viewers concentrate their gaze on specific areas, and the AI ​​improves tracking accuracy. The AI ​​also analyzes patterns in which viewers frequently shift their gaze, and the AI ​​improves tracking accuracy by analyzing patterns in which viewers fix their gaze for extended periods. In this way, tracking accuracy is improved by analyzing the viewer's gaze patterns. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs viewer gaze pattern data into the AI, and the AI ​​improves tracking accuracy.

[0090] The eye-tracking unit can adjust the tracking accuracy by referring to the viewer's device information during eye tracking. For example, if the viewer is using a smartphone, the AI ​​adjusts the tracking accuracy based on the device's screen size. If the viewer is using a tablet, the AI ​​adjusts the tracking accuracy based on the device's screen size. If the viewer is using a smart TV, the AI ​​adjusts the tracking accuracy based on the device's screen size. This allows the tracking accuracy to be adjusted based on the viewer's device information. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's device information into the AI, and the AI ​​adjusts the tracking accuracy.

[0091] The eye-tracking unit can estimate the viewer's emotions and adjust how it displays the eye-tracking results based on the estimated emotions. For example, if the viewer is excited, the AI ​​visually highlights and displays the eye-tracking results. If the viewer is relaxed, the AI ​​displays the eye-tracking results gently. If the viewer is tired, the AI ​​displays the eye-tracking results concisely. This allows the display method of eye-tracking results to be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or AI. The AI ​​is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs viewer emotion data into the AI, and the AI ​​adjusts how it displays the eye-tracking results.

[0092] The eye-tracking unit can improve tracking accuracy by analyzing the viewer's gaze data in real time during eye tracking. For example, the eye-tracking unit analyzes data on where the viewer moves their gaze in real time, and the AI ​​improves tracking accuracy. The AI ​​analyzes data on where the viewer fixes their gaze in real time, and the AI ​​improves tracking accuracy. The AI ​​analyzes data on where the viewer concentrates their gaze in real time, and the AI ​​improves tracking accuracy. In this way, tracking accuracy is improved by analyzing the viewer's gaze data in real time. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's real-time gaze data into the AI, and the AI ​​improves tracking accuracy.

[0093] The eye-tracking unit can adjust the tracking accuracy by comparing the viewer's eye-tracking data with past data during eye-tracking. For example, the eye-tracking unit improves tracking accuracy by comparing it with the viewer's past eye-tracking data, and by comparing it with the viewer's past eye-tracking patterns, and by comparing it with the viewer's past eye movement data. In this way, tracking accuracy is improved by comparing it with the viewer's past data. Some or all of the above processing in the eye-tracking unit is performed using AI. For example, the eye-tracking unit inputs the viewer's past eye-tracking data into the AI, and the AI ​​adjusts the tracking accuracy.

[0094] The purchase acceptance unit can estimate the viewer's emotions and adjust the purchase acceptance method based on the estimated viewer emotions. For example, if the viewer is excited, the AI ​​provides a quick purchase acceptance method. If the viewer is relaxed, the AI ​​provides a detailed purchase acceptance method. If the viewer is tired, the AI ​​provides a concise purchase acceptance method. This allows the purchase acceptance method to be adjusted according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or AI. The AI ​​is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the purchase acceptance unit is performed using AI. For example, the purchase acceptance unit inputs viewer emotion data into the AI, and the AI ​​adjusts the purchase acceptance method.

[0095] The purchase acceptance unit can improve the accuracy of its acceptance process by referring to the viewer's past purchase history. For example, the purchase acceptance unit may prioritize accepting orders for products similar to those the viewer has previously purchased. It may also prioritize accepting orders for products in categories that the viewer frequently purchases. If the viewer prefers a particular brand, it may prioritize accepting orders for products from that brand. This improves the accuracy of the acceptance process by referring to the viewer's past purchase history. Some or all of the above processes in the purchase acceptance unit are performed using AI. For example, the purchase acceptance unit inputs the viewer's past purchase history data into the AI, which then improves the accuracy of the acceptance process.

[0096] The purchase acceptance unit can customize the acceptance method by referring to the viewer's device information when accepting a purchase. For example, if the viewer is using a smartphone, the AI ​​provides a purchase acceptance method optimized for the device. If the viewer is using a tablet, the AI ​​provides a purchase acceptance method optimized for the device. If the viewer is using a smart TV, the AI ​​provides a purchase acceptance method optimized for the device. This allows the acceptance method to be customized based on the viewer's device information. Some or all of the above processing in the purchase acceptance unit is performed using AI. For example, the purchase acceptance unit inputs the viewer's device information into the AI, and the AI ​​customizes the acceptance method.

[0097] The purchase order processing unit can estimate the viewer's emotions and determine the priority of purchase orders based on the estimated emotions. For example, if the viewer is excited, the AI ​​will prioritize orders for visually highlighted products. If the viewer is relaxed, the AI ​​will prioritize orders for calmly displayed products. If the viewer is tired, the AI ​​will prioritize orders for concisely displayed products. This allows the purchase order processing unit to determine the priority of purchase orders according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or AI. The AI ​​may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the purchase order processing unit is performed using AI. For example, the purchase order processing unit inputs viewer emotion data into the AI, and the AI ​​determines the priority of purchase orders.

[0098] The purchase acceptance unit can improve the accuracy of its acceptance process by referring to the viewer's eye-tracking data during the acceptance process. For example, the purchase acceptance unit prioritizes accepting orders for products that the viewer has looked at for an extended period of time. It also prioritizes accepting orders for products that the viewer has frequently shifted their gaze to. If the viewer concentrates their gaze on a particular area, it prioritizes accepting orders for products in that area. In this way, the accuracy of the acceptance process is improved by referring to the viewer's eye-tracking data. Some or all of the above processing in the purchase acceptance unit is performed using AI. For example, the purchase acceptance unit inputs the viewer's eye-tracking data into the AI, which then improves the accuracy of the acceptance process.

[0099] The purchase acceptance unit can analyze the viewer's purchase history in real time and adjust the acceptance method accordingly. For example, the purchase acceptance unit may prioritize accepting orders for products similar to those the viewer has previously purchased. It may also prioritize accepting orders for products in categories that the viewer frequently purchases. If the viewer prefers a particular brand, it may prioritize accepting orders for products from that brand. In this way, the acceptance method can be adjusted by analyzing the viewer's purchase history in real time. Some or all of the above processes in the purchase acceptance unit are performed using AI. For example, the purchase acceptance unit inputs the viewer's purchase history data into the AI, and the AI ​​adjusts the acceptance method. === Hard Collateral 1-1 === Each of the multiple elements described above, including the image analysis unit, product identification unit, recommendation unit, eye-tracking unit, and purchase acceptance unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the smart device 14 to capture the television program screen and the identification processing unit 290 of the data processing unit 12 analyzes the image. The product identification unit identifies products using the identification processing unit 290 of the data processing unit 12. The recommendation unit recommends products to the viewer using the identification processing unit 290 of the data processing unit 12. The eye-tracking unit tracks the viewer's gaze using the camera 42 and control unit 46A of the smart device 14. The purchase acceptance unit analyzes the viewer's voice using the microphone 38B and control unit 46A of the smart device 14 to confirm the intention to purchase. === Hard Collateral 1-2 === Each of the multiple elements described above, including the image analysis unit, product identification unit, recommendation unit, eye-tracking unit, and purchase acceptance unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the smart glasses 214 to capture the television program screen and the identification processing unit 290 of the data processing unit 12 analyzes the image. The product identification unit identifies products using the identification processing unit 290 of the data processing unit 12. The recommendation unit recommends products to the viewer using the identification processing unit 290 of the data processing unit 12. The eye-tracking unit tracks the viewer's gaze using the camera 42 and control unit 46A of the smart glasses 214. The purchase acceptance unit analyzes the viewer's voice using the microphone 238 and control unit 46A of the smart glasses 214 to confirm the intention to purchase. === Hard Collateral 1-3 === Each of the multiple elements described above, including the image analysis unit, product identification unit, recommendation unit, eye-tracking unit, and purchase acceptance unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the headset terminal 314 to capture the television program screen and the identification processing unit 290 of the data processing unit 12 analyzes the image. The product identification unit identifies products using the identification processing unit 290 of the data processing unit 12. The recommendation unit recommends products to the viewer using the identification processing unit 290 of the data processing unit 12. The eye-tracking unit tracks the viewer's gaze using the camera 42 and control unit 46A of the headset terminal 314. The purchase acceptance unit analyzes the viewer's voice using the microphone 238 and control unit 46A of the headset terminal 314 to confirm the intention to purchase. === Hard Collateral 1-4 === Each of the multiple elements described above, including the image analysis unit, product identification unit, recommendation unit, eye-tracking unit, and purchase acceptance unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the image analysis unit uses the camera 42 of the robot 414 to capture the television program screen and the identification processing unit 290 of the data processing unit 12 analyzes the image. The product identification unit identifies products using the identification processing unit 290 of the data processing unit 12. The recommendation unit recommends products to the viewer using the identification processing unit 290 of the data processing unit 12. The eye-tracking unit tracks the viewer's gaze using the camera 42 and control unit 46A of the robot 414. The purchase acceptance unit analyzes the viewer's voice using the microphone 238 and control unit 46A of the robot 414 to confirm the intention to purchase.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The product purchase system can also include a history analysis unit that analyzes the user's purchase history. Based on past purchase data, the history analysis unit identifies product categories and brands preferred by the viewer and provides this information to the recommendation unit. For example, it can prioritize recommending product categories that the viewer has frequently purchased in the past. Furthermore, if the viewer prefers a particular brand, it can prioritize recommending products from that brand. It can also predict and recommend new products that the viewer might be interested in, based on their purchase history. This allows for more personalized recommendations by leveraging the viewer's purchase history.

[0102] The product purchase system can also include a social media analytics unit that analyzes viewers' social media activity. This unit identifies products and brands mentioned by viewers on social media and provides this information to the recommendation unit. For example, it can prioritize recommending product categories that viewers frequently mention on social media. It can also recommend products featured by brands and influencers that viewers follow. Furthermore, it can predict and recommend products that viewers might be interested in based on their social media responses. This enables more personalized recommendations by leveraging viewers' social media activity.

[0103] The product purchase system can also include a location information analysis unit that utilizes the viewer's location information. Based on the viewer's current location and past travel history, the location information analysis unit identifies products that the viewer might be interested in and provides them to the recommendation unit. For example, it can prioritize recommending products sold in stores in areas the viewer frequently visits. If the viewer is traveling, it can also recommend local specialties or popular items from tourist destinations in that area. Furthermore, based on the viewer's location information, it can provide information on events and sales that the viewer might be interested in. This enables more personalized recommendations by leveraging the viewer's location information.

[0104] The product purchase system can also include a health data analysis department that utilizes viewers' health data. The health data analysis department identifies products likely to interest viewers based on their health status and fitness data, and provides this information to the recommendation department. For example, if a viewer is interested in fitness, fitness-related products can be prioritized for recommendation. Furthermore, if a viewer has specific health goals, products related to those goals can be recommended. Additionally, based on viewers' health data, it's possible to predict and recommend health foods and supplements that viewers might be interested in. This enables more personalized recommendations by leveraging viewers' health data.

[0105] The product purchase system can also include an incentive provision section to further enhance viewers' purchasing intent. This incentive provision section offers benefits and discounts when viewers purchase products. For example, it could offer a coupon usable for future purchases when a viewer buys a specific product. It could also offer free shipping or point rewards when viewers purchase products above a certain amount. Furthermore, if a viewer refers a friend who makes a purchase, both the referrer and the referred person can receive benefits. This can increase viewers' purchasing intent and encourage the use of the product purchase system.

[0106] The product purchase system can estimate the viewer's emotions and adjust the timing of recommendations based on those emotions. For example, if the viewer is excited, the generative AI will immediately display recommendations to keep the viewer interested. If the viewer is relaxed, the generative AI will display recommendations gently to give the viewer a sense of ease. If the viewer is tired, the generative AI will display recommendations discreetly to avoid burdening the viewer. This allows the timing of recommendations to be adjusted according to the viewer's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The product purchase system can estimate the viewer's emotions and adjust the way the product is described based on those emotions. For example, if the viewer is excited, the generative AI will visually emphasize the product description to keep the viewer interested. If the viewer is relaxed, the generative AI will describe the product gently, allowing the viewer to relax. If the viewer is tired, the generative AI will describe the product concisely to avoid burdening the viewer. This allows the product description to be adjusted according to the viewer's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] A product purchase system can estimate the viewer's emotions and adjust the steps of the purchase process based on those emotions. For example, if the viewer is excited, the generative AI will expedite the purchase process to maintain the viewer's desire to buy. If the viewer is relaxed, the generative AI will proceed through the purchase process gently, giving the viewer ample time. If the viewer is tired, the generative AI will simplify the purchase process to avoid burdening the viewer. This allows the steps of the purchase process to be adjusted according to the viewer's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0109] The product purchase system can estimate the viewer's emotions and adjust post-purchase follow-up based on those emotions. For example, if the viewer is excited, the generative AI will provide quick post-purchase follow-up to increase viewer satisfaction. If the viewer is relaxed, the generative AI will provide gentle post-purchase follow-up to allow the viewer to relax. If the viewer is tired, the generative AI will provide concise post-purchase follow-up to avoid burdening the viewer. This allows post-purchase follow-up to be adjusted according to the viewer's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The product purchase system can estimate the viewer's emotions and adjust its customer support response based on those emotions. For example, if the viewer is excited, the generative AI will respond quickly to customer support, increasing viewer satisfaction. If the viewer is relaxed, the generative AI will respond calmly to customer support, allowing the viewer to relax. If the viewer is tired, the generative AI will respond concisely to customer support, minimizing the viewer's burden. This allows the customer support response to be adjusted according to the viewer's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The image analysis unit analyzes images to recognize products displayed on television screens. For example, it uses generative AI and deep learning algorithms to detect objects in images and identify products. It recognizes products by extracting features from images and comparing them with a database. It can also analyze text information in images to identify product names and brand names. Step 2: The product identification unit identifies products based on images analyzed by the image analysis unit. For example, it can use a generation AI to identify products based on features in the image and then compare them with a database. It can also analyze text information in the image to identify product names and brand names. Step 3: The recommendation unit recommends products identified by the product identification unit to the viewer. For example, it can use generative AI to recommend products based on the viewer's interests and preferences. By analyzing the viewer's eye-tracking data and past purchase history, it can recommend the most suitable products. It can also track the viewer's gaze and identify products they are interested in. Step 4: The eye-tracking unit tracks the viewer's gaze and identifies products that the viewer is interested in. For example, using an eye-tracking device, the viewer's gaze is tracked in real time to identify products that the viewer is interested in. It is also possible to analyze the viewer's gaze data to identify their interests and preferences. Step 5: The purchase reception unit receives information from viewers to purchase products. For example, if a viewer says "OK!", the unit receives the information to purchase the product. The unit can analyze the viewer's voice data to confirm their intention to purchase. It can also analyze the viewer's eye-tracking data to identify products that the viewer is interested in.

[0113] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0116] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 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.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0166] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] 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.

[0176] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The image analysis unit analyzes the image, A product identification unit identifies a product based on an image analyzed by the aforementioned image analysis unit, A recommendation unit that recommends products identified by the aforementioned product identification unit to viewers, An eye-tracking unit that tracks the viewer's gaze, It includes a purchase reception area for viewers to purchase products. A system characterized by the following features.

2. The aforementioned image analysis unit, Recognizing products displayed on a television screen. The system according to feature 1.

3. The aforementioned product identification unit is, The product is identified based on the image analyzed by the aforementioned image analysis unit. The system according to feature 1.

4. The recommendation unit is, The product identified by the aforementioned product identification unit is recommended to the viewer. The system according to feature 1.

5. The aforementioned eye-tracking unit, Track viewers' gaze and identify products they are interested in. The system according to feature 1.

6. The aforementioned purchase reception department is We accept information from viewers to help them purchase products. The system according to feature 1.

7. The aforementioned image analysis unit, It estimates the viewer's emotions and adjusts the accuracy of image analysis based on the estimated viewer emotions. The system according to feature 1.

8. The aforementioned image analysis unit, Apply different image analysis algorithms depending on the program genre. The system according to feature 1.

Images