system

Abstract

The system according to this embodiment aims to support users in making optimal purchase decisions by providing them with detailed information and price comparisons in real time when they select products. [Solution] The system according to the embodiment comprises a recognition unit, a display unit, a learning unit, a recommendation unit, a comparison unit, and a presentation unit. The recognition unit recognizes the product the user is looking at. The display unit displays detailed information of the product recognized by the recognition unit. The learning unit learns the user's past purchase history and preferences based on the information displayed by the display unit. The recommendation unit presents personalized recommended products based on the information learned by the learning unit. The comparison unit compares the prices and stock status of multiple online shops based on the information presented by the recommendation unit. The presentation unit presents the best place to buy based on the information compared by the comparison unit.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , ,

[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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] In the conventional technology, it is difficult for a user to perform real-time detailed information and price comparison when selecting a product, and there is room for improvement in supporting optimal purchase decisions.

[0005] The system according to the embodiment aims to provide real-time detailed information and price comparison when a user selects a product and support optimal purchase decisions.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a recognition unit, a display unit, a learning unit, a recommendation unit, a comparison unit, and a presentation unit. The recognition unit recognizes the product the user is looking at. The display unit displays detailed information about the product recognized by the recognition unit. The learning unit learns the user's past purchase history and preferences based on the information displayed by the display unit. The recommendation unit presents personalized recommended products based on the information learned by the learning unit. The comparison unit compares prices and stock availability at multiple online shops based on the information presented by the recommendation unit. The presentation unit presents the best place to buy based on the information compared by the comparison unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide users with detailed information and price comparisons in real time when they select products, supporting them in making optimal purchase decisions. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. 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 personal shopping assistant system according to an embodiment of the present invention is a system that utilizes AR glasses and generative AI to provide real-time advice and information to users when they select products. When a user looks at a product, the AR glasses recognize the product, and the generative AI displays detailed product information. Next, the generative AI learns the user's past purchase history and preferences, and presents personalized product recommendations. Furthermore, the generative AI compares prices and inventory status from multiple online shops in real time, and suggests the optimal place to buy. The generative AI also performs natural language processing, providing appropriate answers when the user asks questions by voice. This allows users to select products efficiently and improves their shopping experience. For example, when a user looks at a product, the AR glasses recognize the product, and the generative AI displays detailed product information. For example, product specifications, user reviews, price comparisons, and inventory status are displayed. This allows users to check detailed product information on the spot and make optimal purchase decisions. Next, the generative AI learns the user's past purchase history and preferences, and presents personalized product recommendations. For example, it recommends related products and new products based on products the user has purchased in the past and the user's preferences. This makes it easier for users to find products that suit them. Furthermore, the generative AI compares prices and inventory levels across multiple online shops in real time, suggesting the optimal place to buy. For example, if the same product is sold at multiple online shops, the generative AI will suggest the shop with the lowest price and available stock. This allows users to choose the best place to buy. The generative AI also performs natural language processing, providing appropriate answers when users ask questions by voice. For example, if a user asks, "What are the reviews like for this product?", the generative AI will display the reviews for that product. This allows users to easily obtain information by voice. In this way, the personal shopping assistant system utilizes AR glasses and generative AI to provide real-time advice and information to users when selecting products, supporting them in making optimal purchase decisions. This allows users to select products efficiently and improves their shopping experience.This allows the personal shopping assistant system to provide real-time advice and information to users as they choose products, supporting them in making optimal purchasing decisions.

[0029] The personal shopping assistant system according to this embodiment comprises a recognition unit, a display unit, a learning unit, a recommendation unit, a comparison unit, and a presentation unit. The recognition unit recognizes the product the user is looking at. The recognition unit tracks the user's gaze using, for example, a camera, and recognizes the product the user's gaze is fixed on. The recognition unit can also identify products using image recognition technology. For example, the recognition unit detects the user's gaze movement using an eye-tracking device and recognizes the product the user's gaze is fixed on for a certain period of time. Image recognition technology identifies products by comparing product images with a database. The display unit uses a generation AI to display detailed information about the product recognized by the recognition unit. This detailed information includes, for example, product specifications, user reviews, price comparisons, and stock availability. For example, the display unit uses the generation AI to obtain product specification information and display it on AR glasses. The display unit can also use the generation AI to analyze user reviews and display highly-rated reviews. Furthermore, the display unit can use the generation AI to obtain price information from multiple online shops and display the lowest price. The learning unit uses generative AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. For example, the learning unit analyzes the user's purchase history data to identify the user's preferences. The learning unit can also learn the user's interests based on the user's browsing and search history. For example, the learning unit analyzes data on products the user has purchased in the past to identify the user's preferences. It learns the product categories the user is interested in based on browsing and search history. The recommendation unit uses generative AI to present personalized product recommendations based on the information learned by the learning unit. For example, the recommendation unit recommends related products and new products based on the user's preferences. The recommendation unit can also suggest products that are likely to be repurchased based on the user's past purchase history. For example, the recommendation unit recommends products related to products the user has purchased in the past. It acquires information on new products and presents new products that match the user's preferences. The comparison unit uses generative AI to compare prices and stock availability from multiple online shops based on the information presented by the recommendation unit.The comparison unit, for example, if the same product is sold at multiple online shops, will present the shop with the lowest price or the shop with the item in stock. The comparison unit can also compare prices while considering delivery time and shipping costs. For example, the comparison unit will obtain price information from multiple online shops and present the lowest price. It will also check the product's stock status and present the shop with the item in stock. The presentation unit uses a generation AI to present the optimal place to buy based on the information compared by the comparison unit. For example, the presentation unit will present the user with the lowest price or the shop with the item in stock. The presentation unit can also prioritize presenting specific brands or shops based on the user's preferences. For example, the presentation unit will present the user with the shop with the lowest price. It will also prioritize presenting specific brands or shops based on the user's preferences. As a result, the personal shopping assistant system according to this embodiment can provide real-time advice and information to the user when they are choosing a product, supporting them in making the best purchase decision.

[0030] The recognition unit recognizes the product the user is looking at. For example, the recognition unit tracks the user's gaze using a camera and recognizes the product the user's gaze is fixed on. Specifically, the eye-tracking device detects the user's eye movements with high precision and identifies the product the user's gaze is fixed on for a certain period of time. Eye-tracking technology uses infrared cameras or high-resolution cameras to track the user's pupil movements in real time and calculate the direction of the gaze. Furthermore, image recognition technology compares the product the user is looking at with a database to identify the product name and model number. For example, when the eye-tracking device detects that the user's gaze is directed at a specific product, the image recognition technology takes a picture of that product with the camera and identifies the product by comparing it with an image in the database. This process is completed within seconds, allowing for rapid recognition of the product the user is looking at. This enables the recognition unit to accurately identify the product the user is interested in and proceed to the next step of displaying information or making recommendations.

[0031] The display unit uses a generation AI to display detailed information about products recognized by the recognition unit. This detailed information includes, for example, product specifications, user reviews, price comparisons, and stock availability. The generation AI collects and integrates information from multiple data sources on the internet for display. For example, the generation AI obtains specification information and user reviews from the product's official website, online shops, and review sites, organizes this information, and provides it to the user. Furthermore, the generation AI can obtain price information from multiple online shops in real time and display the lowest price. The display unit displays this information on AR glasses or smartphone screens, making it easily accessible to the user. For example, if the user is wearing AR glasses, the detailed information of the product they are looking at will be overlaid on their field of view. If using a smartphone, the detailed information will be displayed through an application. This allows the display unit to quickly obtain detailed information about products and support the user's purchase decision.

[0032] The learning unit uses generative AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. For example, the learning unit analyzes the user's purchase history data to identify the user's preferences. Specifically, the generative AI collects data on products the user has purchased in the past and analyzes patterns such as product category, brand, and price range. Furthermore, the learning unit can also learn the user's interests based on the user's browsing and search history. For example, it identifies product categories and brands that the user frequently searches for and learns the user's preferences based on this information. The learning unit continuously updates this data to respond to changes in the user's preferences and interests. As a result, the learning unit can provide personalized information based on the user's individual needs and preferences.

[0033] The recommendation unit uses generative AI to present personalized product recommendations based on information learned by the learning unit. For example, the recommendation unit recommends related or new products based on the user's preferences. Specifically, the generative AI analyzes the user's past purchase and browsing history to identify highly relevant products. For example, it recommends products in the same category as products the user has previously purchased, or new products from the same brand. The generative AI also filters products that meet specific criteria based on the user's preferences and presents the most suitable products. Furthermore, the recommendation unit can also suggest products that are likely to be repurchased based on the user's past purchase history. For example, it can predict the timing of repurchases of consumables or regularly purchased items and recommend them at the appropriate time. In this way, the recommendation unit can present the most suitable products to the user and improve the shopping experience.

[0034] The comparison unit uses generative AI to compare prices and availability at multiple online shops based on information presented by the recommendation unit. For example, if the same product is sold at multiple online shops, the comparison unit will present the shop with the lowest price and availability. Specifically, the generative AI obtains price and inventory information through APIs from multiple online shops and compares this information. Furthermore, the comparison unit can also consider delivery time and shipping costs when making comparisons. For example, if the same product is sold at different prices at different shops, it will calculate the overall cost, including not only the lowest price but also delivery time and shipping costs, and present the optimal place to buy. The comparison unit can also prioritize displaying specific brands or shops based on user preferences. In this way, the comparison unit can provide users with the most cost-effective purchase options and support their purchasing decisions.

[0035] The presentation unit uses generative AI to suggest the best place to buy based on the information compared by the comparison unit. For example, the presentation unit might show the user the shop with the lowest price or the shop with the item in stock. Specifically, the generative AI identifies the most cost-effective place to buy based on the price and stock information collected by the comparison unit. Furthermore, the presentation unit can also prioritize specific brands or shops based on the user's preferences. For example, if a user prefers a particular brand, it will prioritize displaying shops that have that brand's products in stock. The presentation unit can also prioritize displaying specific shops based on the user's past purchase history and preferences. This allows the presentation unit to provide users with the best possible purchase options and improve the shopping experience. In addition, the presentation unit centrally provides the information necessary for users to make purchase decisions, supporting quick and efficient purchasing decisions.

[0036] The recognition unit can track the user's eye movements during product recognition and determine recognition priorities based on the degree of gaze concentration. For example, if the user is looking at a particular product for a long time, the recognition unit will prioritize recognizing that product. Furthermore, if the user is shifting their gaze to multiple products, the recognition unit can prioritize recognizing the product that the user's gaze lingers on the longest. Additionally, if the user is frequently shifting their gaze, the recognition unit can analyze the eye movement patterns and recognize the product of the user's highest interest. For example, the recognition unit can detect the user's eye movements using an eye-tracking device and prioritize recognizing products where the user's gaze is fixed for a certain period. By analyzing the eye movement patterns, it identifies products of high user interest. This allows the recognition unit to prioritize product recognition based on the user's eye movements, thereby prioritizing the recognition of products of higher interest. Some or all of the above-described processes in the recognition unit may be performed using AI, or not. For example, the recognition unit can input eye-tracking data acquired by an eye-tracking device into a generating AI and have the generating AI analyze the eye movement patterns.

[0037] The recognition unit can improve the accuracy of product recognition by referring to the user's past gaze history. For example, the recognition unit can improve recognition accuracy by analyzing the user's current gaze movements based on products the user has previously looked at. The recognition unit can also identify the user's interest in specific product categories from their past gaze history and prioritize the recognition of products in those categories. Furthermore, the recognition unit can improve recognition accuracy by analyzing the user's gaze history and learning patterns of eye movements. For example, the recognition unit can analyze the user's past gaze data and identify patterns of eye movements. Based on the gaze history, it can identify product categories that the user is interested in. This allows the accuracy of product recognition to be improved by referring to the user's past gaze history. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input past gaze data into a generating AI and have the generating AI learn patterns of eye movements.

[0038] The recognition unit can prioritize recognizing highly relevant products by considering the user's geographical location information during product recognition. For example, if the user is in a specific region, the recognition unit can prioritize recognizing popular products in that region. Furthermore, if the user is traveling, the recognition unit can prioritize recognizing recommended products for their travel destination. Additionally, if the user is at home, the recognition unit can prioritize recognizing products available at nearby stores. For example, the recognition unit can acquire the user's geographical location information and identify popular products in that region. It can also acquire recommended products for the travel destination from a database and prioritize their recognition. This allows the recognition unit to prioritize recognizing highly relevant products by considering the user's geographical location information. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input geographical location information into a generating AI and have the generating AI identify highly relevant products.

[0039] The recognition unit can analyze the user's social media activity and recognize related products when recognizing products. For example, the recognition unit can prioritize recognizing products that the user has "liked" or commented on on social media. It can also prioritize recognizing products that have been introduced by influencers that the user follows. Furthermore, the recognition unit can analyze the content of the user's social media posts and prioritize recognizing products of high interest. For example, the recognition unit can acquire social media data and identify products that the user has "liked" or commented on. It can also acquire products introduced by influencers that the user follows from a database and prioritize their recognition. In this way, related products can be recognized by analyzing the user's social media activity. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input social media data into a generating AI and have the generating AI identify related products.

[0040] The display unit can customize the displayed content based on the user's past purchase history when displaying detailed product information. For example, the display unit can prioritize displaying information related to products the user has previously purchased. The display unit can also display detailed information on products that the user might be interested in based on their purchase history. Furthermore, the display unit can analyze the user's purchase history and display reviews and ratings of products they have previously purchased. For example, the display unit analyzes the user's purchase history data and obtains information on related products. Based on the purchase history, it displays detailed information on products that the user might be interested in. This allows for the provision of more relevant information by customizing the displayed content based on the user's past purchase history. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0041] The display unit can filter the displayed content based on the user's current areas of interest when displaying detailed product information. For example, the display unit can prioritize displaying product information in categories that the user is currently interested in. The display unit can also display detailed information on related products based on the user's recent search history. Furthermore, the display unit can analyze the user's areas of interest and display information on the most relevant products. For example, the display unit can analyze the user's search history data and obtain information on related products. Based on the areas of interest, it can display detailed information on products that the user is likely to be interested in. This allows the display unit to provide more relevant information by filtering the displayed content based on the user's current areas of interest. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input search history data into a generating AI and have the generating AI obtain information on related products.

[0042] The display unit can select the optimal display method when displaying detailed product information, taking into account the user's device information. For example, if the user is using a smartphone, the display unit provides a display method that matches the screen size. Furthermore, if the user is using a tablet, the display unit can provide a display method optimized for a larger screen. Additionally, if the user is using a smartwatch, the display unit can provide a concise and highly visible display method. For example, the display unit acquires device information and selects a display method that matches the screen size. It provides display methods according to the type of device, such as smartphones, tablets, and smartwatches. This allows the display unit to provide the optimal display method by considering the user's device information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input device information into a generating AI and have the generating AI select the optimal display method.

[0043] The display unit can analyze the user's social media activity and display relevant information when displaying detailed product information. For example, the display unit can display information related to products that the user has "liked" or commented on on social media. The display unit can also display detailed information about products introduced by influencers that the user follows. Furthermore, the display unit can analyze the content of the user's social media posts and display information about products of high interest. For example, the display unit can acquire social media data and identify products that the user has "liked" or commented on. It can acquire information about products introduced by influencers that the user follows and display it preferentially. In this way, relevant information can be displayed by analyzing the user's social media activity. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input social media data into a generating AI and have the generating AI identify relevant information.

[0044] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal algorithm based on past learning data. The learning unit can also adjust parameters to improve learning accuracy based on past learning data. Furthermore, the learning unit can analyze past learning data and identify areas for improvement in the learning algorithm. For example, the learning unit analyzes past learning data and selects the optimal algorithm. It adjusts parameters to improve learning accuracy. In this way, by referring to past learning data, the learning algorithm can be optimized and learning accuracy can be improved. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0045] The learning unit can improve the accuracy of its learning by analyzing the user's past purchase history during the learning process. For example, the learning unit incorporates relevant data into the learning process based on the user's past purchase history. The learning unit can also incorporate data on products that the user might be interested in, based on the user's purchase history. Furthermore, the learning unit can analyze the user's purchase history and select data to improve the accuracy of its learning. For example, the learning unit analyzes the user's purchase history data and incorporates relevant data into the learning process. Based on the purchase history, it incorporates data on products that the user might be interested in into the learning process. This allows the learning unit to improve the accuracy of its learning by analyzing the user's past purchase history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input purchase history data into a generating AI and have the generating AI select relevant data.

[0046] The learning unit can select training data while considering the user's geographical location information. For example, if the user is in a specific region, the learning unit can incorporate data on popular products in that region into its training. Furthermore, if the user is traveling, the learning unit can incorporate data on recommended products at their travel destination. Additionally, if the user is at home, the learning unit can incorporate data on products available at nearby stores. For example, the learning unit can acquire the user's geographical location information and identify data on popular products in that region. It can also acquire recommended product data for the travel destination from a database and incorporate it into its training. This allows the learning unit to incorporate highly relevant data by considering the user's geographical location information. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input geographical location information into a generating AI and have the generating AI identify highly relevant data.

[0047] The learning unit can analyze the user's social media activity during training and incorporate relevant data into its learning process. For example, the learning unit can incorporate product data that the user has "liked" or commented on on social media. It can also incorporate product data that has been introduced by influencers that the user follows. Furthermore, the learning unit can analyze the content of the user's social media posts and incorporate product data of high interest into its learning process. For example, the learning unit can acquire social media data and identify product data that the user has "liked" or commented on. It can also acquire product data introduced by influencers that the user follows from a database and incorporate it into its learning process. In this way, by analyzing the user's social media activity, relevant data can be incorporated into the learning process. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input social media data into a generating AI and have the generating AI identify relevant data.

[0048] The recommendation system can improve the accuracy of recommendations by referring to the user's past purchase history. For example, the recommendation system can prioritize recommending products related to products the user has previously purchased. It can also recommend products that the user might be interested in based on their purchase history. Furthermore, the recommendation system can analyze the user's purchase history and recommend the most relevant products. For example, the recommendation system can analyze the user's purchase history data and obtain information on related products. Based on the purchase history, it recommends products that the user might be interested in. This improves the accuracy of recommendations by referring to the user's past purchase history. Some or all of the above processes in the recommendation system may be performed using AI, for example, or without AI. For example, the recommendation system can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0049] The recommendation system can customize recommendations based on the user's current areas of interest. For example, it might prioritize recommending products in categories the user is currently interested in. It can also recommend relevant products based on the user's recent search history. Furthermore, it can analyze the user's areas of interest and recommend the most relevant products. For example, it might analyze the user's search history data to obtain information on relevant products. Based on these areas of interest, it recommends products that the user is likely to be interested in. This allows for the recommendation of more relevant products by customizing recommendations based on the user's current areas of interest. Some or all of the above processes in the recommendation system may be performed using AI, or not. For example, the recommendation system could input search history data into a generating AI and have the AI ​​obtain information on relevant products.

[0050] The recommendation system can recommend the most suitable products by considering the user's geographical location. For example, if the user is in a specific region, the recommendation system will prioritize recommending popular products in that region. Furthermore, if the user is traveling, the recommendation system can prioritize recommending products suitable for their travel destination. Additionally, if the user is at home, the recommendation system can prioritize recommending products available at nearby stores. For instance, the recommendation system obtains the user's geographical location and identifies popular products in that region. It retrieves recommended products from a database for the travel destination and prioritizes recommending them. This allows the system to recommend the most suitable products by considering the user's geographical location. Some or all of the above processing in the recommendation system may be performed using AI, or not. For example, the recommendation system can input geographical location information into a generating AI and have the AI ​​identify highly relevant products.

[0051] The recommendation system can analyze a user's social media activity and recommend relevant products. For example, it can prioritize recommending products that a user has "liked" or commented on on social media. It can also prioritize recommending products that have been featured by influencers that the user follows. Furthermore, it can analyze the content of a user's social media posts and prioritize recommending products that are of high interest to the user. For example, the recommendation system can acquire social media data and identify products that a user has "liked" or commented on. It can also acquire products that have been featured by influencers that the user follows from its database and recommend them preferentially. In this way, by analyzing a user's social media activity, it can recommend relevant products. Some or all of the above processes in the recommendation system may be performed using AI, for example, or not. For example, the recommendation system can input social media data into a generating AI and have the generating AI identify relevant products.

[0052] The comparison unit can improve the accuracy of comparisons by referring to the user's past purchase history when comparing prices and availability. For example, the comparison unit prioritizes displaying the prices and availability of products related to products the user has previously purchased. The comparison unit can also display the prices and availability of products that the user might be interested in based on their purchase history. Furthermore, the comparison unit can analyze the user's purchase history and display the prices and availability of the most relevant products. For example, the comparison unit analyzes the user's purchase history data and obtains information on related products. Based on the purchase history, it displays the prices and availability of products that the user might be interested in. This improves the accuracy of comparisons by referring to the user's past purchase history. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0053] The comparison unit can customize the comparison based on the user's current areas of interest when comparing prices and availability. For example, the comparison unit can prioritize comparing products in categories that the user is currently interested in. The comparison unit can also compare prices and availability of related products based on the user's recent search history. Furthermore, the comparison unit can analyze the user's areas of interest and compare prices and availability of the most relevant products. For example, the comparison unit can analyze the user's search history data and obtain information on related products. Based on the areas of interest, it compares prices and availability of products that the user is likely to be interested in. This allows the comparison unit to provide more relevant information by customizing the comparison based on the user's current areas of interest. Some or all of the above processing in the comparison unit may be performed using AI, for example, or not. For example, the comparison unit can input search history data into a generating AI and have the generating AI obtain information on related products.

[0054] The comparison unit can provide optimal comparison results by considering the user's geographical location when comparing prices and availability. For example, if the user is in a specific region, the comparison unit will prioritize displaying the prices and availability of products available in that region. Furthermore, if the user is traveling, the comparison unit can prioritize displaying the prices and availability of products available at their travel destination. Additionally, if the user is at home, the comparison unit can prioritize displaying the prices and availability of products available at nearby stores. For example, the comparison unit can acquire the user's geographical location and identify information on products available in that region. It can also acquire information on products available at the travel destination from a database and prioritize displaying that information. This allows the system to provide optimal comparison results by considering the user's geographical location. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input geographical location information into a generating AI and have the generating AI acquire information on related products.

[0055] The comparison unit can analyze the user's social media activity and incorporate relevant information into the comparison when comparing prices and availability. For example, the comparison unit can prioritize displaying the prices and availability of products that the user has "liked" or commented on on social media. It can also prioritize displaying the prices and availability of products that have been featured by influencers that the user follows. Furthermore, the comparison unit can analyze the content of the user's social media posts and prioritize displaying the prices and availability of products of high interest. For example, the comparison unit can acquire social media data and identify information about products that the user has "liked" or commented on. It can also acquire information about products featured by influencers that the user follows from a database and display it preferentially. In this way, relevant information can be incorporated into the comparison by analyzing the user's social media activity. Some or all of the above processing in the comparison unit may be performed using AI, for example, or not. For example, the comparison unit can input social media data into a generating AI and have the generating AI identify relevant information.

[0056] The display unit can customize its recommendations by referencing the user's past purchase history when suggesting the most suitable purchase destinations. For example, the display unit can prioritize displaying purchase destinations related to products the user has previously purchased. It can also suggest purchase destinations for products the user might be interested in based on their purchase history. Furthermore, the display unit can analyze the user's purchase history and suggest the most relevant purchase destinations. For example, the display unit can analyze the user's purchase history data and obtain information on related products. Based on the purchase history, it can suggest purchase destinations for products the user might be interested in. This allows the display unit to customize its recommendations by referencing the user's past purchase history and provide more appropriate information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0057] The presentation unit can filter the displayed content based on the user's current areas of interest when suggesting the most suitable place to buy. For example, the presentation unit can prioritize displaying products in categories that the user is currently interested in. The presentation unit can also suggest places to buy related products based on the user's recent search history. Furthermore, the presentation unit can analyze the user's areas of interest and suggest places to buy the most relevant products. For example, the presentation unit can analyze the user's search history data and obtain information on related products. Based on the areas of interest, it can suggest places to buy products that the user is likely to be interested in. This allows the presentation unit to provide more relevant information by filtering the displayed content based on the user's current areas of interest. Some or all of the above processing in the presentation unit may be performed using AI, for example, or without AI. For example, the presentation unit can input search history data into a generating AI and have the generating AI obtain information on related products.

[0058] The display unit can suggest the most suitable place to buy products by considering the user's geographical location. For example, if the user is in a specific region, the display unit will prioritize suggesting places to buy products available in that region. Furthermore, if the user is traveling, the display unit can prioritize suggesting places to buy products available at their travel destination. Additionally, if the user is at home, the display unit can prioritize suggesting places to buy products available at nearby stores. For example, the display unit can acquire the user's geographical location and identify information on products available in that region. It can also acquire information on products available at the travel destination from a database and prioritize its presentation. This allows the display unit to suggest the most suitable place to buy products by considering the user's geographical location. Some or all of the above processing in the display unit may be performed using AI, or without AI. For example, the display unit can input geographical location information into a generating AI and have the generating AI acquire information on related products.

[0059] The presentation unit can analyze the user's social media activity and present relevant information when suggesting the optimal place to buy. For example, the presentation unit can prioritize presenting the place to buy products that the user has "liked" or commented on on social media. It can also prioritize presenting the place to buy products that have been introduced by influencers that the user follows. Furthermore, the presentation unit can analyze the content of the user's social media posts and prioritize presenting the place to buy products of high interest. For example, the presentation unit can acquire social media data and identify information about products that the user has "liked" or commented on. It can also acquire information about products introduced by influencers that the user follows from a database and present it preferentially. In this way, relevant information can be presented by analyzing the user's social media activity. Some or all of the above processing in the presentation unit may be performed using AI, for example, or not using AI. For example, the presentation unit can input social media data into a generating AI and have the generating AI identify relevant information.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The personal shopping assistant system can also acquire user health data and recommend products based on their health status. For example, it can recommend healthy foods and fitness equipment based on data from the user's fitness tracker. It can also analyze the user's sleep data and recommend products that support comfortable sleep. Furthermore, it can monitor the user's heart rate and stress levels and recommend products with relaxing effects. This allows for a more personalized shopping experience by providing products tailored to the user's health condition.

[0062] The personal shopping assistant system can further analyze the user's purchase history and provide maintenance information for previously purchased items. For example, it can notify the user of maintenance schedules for home appliances they have purchased in the past. It can also provide instructions on how to care for furniture the user has purchased. Furthermore, it can suggest washing and storage methods for clothing the user has purchased. In this way, by providing maintenance information based on the user's purchase history, it can support the long-term use of products.

[0063] A personal shopping assistant system can further consider the user's geographical location to provide region-specific offers and event information. For example, if the user is in a specific region, it can provide information on sales and events taking place in that area. If the user is traveling, it can also provide offers and sightseeing information for their destination. Furthermore, if the user is at home, it can provide coupons and offers usable at nearby stores. This allows for a more personalized service by providing region-specific offers and event information based on the user's geographical location.

[0064] The personal shopping assistant system can further analyze the user's social media activity and provide relevant product trend information. For example, it can provide trend information on products featured by influencers the user follows. It can also provide trend information on products the user has "liked" or commented on. Furthermore, it can analyze the user's social media posts and provide trend information on products of high interest. By providing trend information based on the user's social media activity, it can deliver more relevant information.

[0065] The personal shopping assistant system can further consider the user's device information to provide an optimal interface. For example, if the user is using a smartphone, it can provide an interface optimized for touch operation. If the user is using a tablet, it can provide an interface optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible interface. This allows for a more comfortable user experience by providing the optimal interface based on the user's device information.

[0066] The personal shopping assistant system can further analyze the user's purchase history and manage warranty information for previously purchased items. For example, it can notify the user of the warranty period for previously purchased items. It can also send reminders before the warranty expires. Furthermore, it can provide support information for problems that occur within the warranty period. This strengthens after-sales support for products by managing warranty information based on the user's purchase history.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The recognition unit recognizes the product the user is looking at. The recognition unit tracks the user's gaze using a camera and recognizes the product that the user's gaze is fixed on. Alternatively, product identification can be done using image recognition technology. For example, an eye-tracking device can be used to detect the user's eye movements and recognize the product that the user's gaze is fixed on for a certain period of time. Image recognition technology identifies the product by comparing the product image with a database. Step 2: The display unit uses a generation AI to display detailed information about the product recognized by the recognition unit. This detailed information includes product specifications, user reviews, price comparisons, and stock availability. For example, the generation AI can acquire product specification information and display it on the AR glasses. The generation AI can also analyze user reviews and display highly rated reviews. Furthermore, the generation AI can acquire price information from multiple online shops and display the lowest price. Step 3: The learning unit uses generative AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. The learning unit analyzes the user's purchase history data to identify the user's preferences. It can also learn the user's interests based on their browsing and search history. For example, it can analyze data on products the user has purchased in the past to identify the user's preferences. It can also learn the product categories the user is interested in based on their browsing and search history. Step 4: The recommendation unit uses generative AI to present personalized product recommendations based on information learned by the learning unit. The recommendation unit recommends related and new products based on the user's preferences. It can also suggest products that are likely to be repurchased based on the user's past purchase history. For example, it may recommend products related to products the user has purchased in the past. It also acquires information on new products and presents new products that match the user's preferences. Step 5: The comparison unit uses a generation AI to compare prices and stock availability at multiple online shops based on the information presented by the recommendation unit. If the same product is sold at multiple online shops, the comparison unit will present the shop with the lowest price or the shop with the product in stock. It can also consider delivery time and shipping costs when making comparisons. For example, it can obtain price information from multiple online shops and present the lowest price. It can also check the product's stock availability and present the shop with the product in stock. Step 6: The presentation unit uses generating AI to suggest the best place to buy based on the information compared by the comparison unit. The presentation unit shows the user the shop with the lowest price or the shop with the item in stock. It can also prioritize specific brands or shops based on the user's preferences. For example, it can show the user the shop with the lowest price. It can also prioritize specific brands or shops based on the user's preferences.

[0069] (Example of form 2) The personal shopping assistant system according to an embodiment of the present invention is a system that utilizes AR glasses and generative AI to provide real-time advice and information to users when they select products. When a user looks at a product, the AR glasses recognize the product, and the generative AI displays detailed product information. Next, the generative AI learns the user's past purchase history and preferences, and presents personalized product recommendations. Furthermore, the generative AI compares prices and inventory status from multiple online shops in real time, and suggests the optimal place to buy. The generative AI also performs natural language processing, providing appropriate answers when the user asks questions by voice. This allows users to select products efficiently and improves their shopping experience. For example, when a user looks at a product, the AR glasses recognize the product, and the generative AI displays detailed product information. For example, product specifications, user reviews, price comparisons, and inventory status are displayed. This allows users to check detailed product information on the spot and make optimal purchase decisions. Next, the generative AI learns the user's past purchase history and preferences, and presents personalized product recommendations. For example, it recommends related products and new products based on products the user has purchased in the past and the user's preferences. This makes it easier for users to find products that suit them. Furthermore, the generative AI compares prices and inventory levels across multiple online shops in real time, suggesting the optimal place to buy. For example, if the same product is sold at multiple online shops, the generative AI will suggest the shop with the lowest price and available stock. This allows users to choose the best place to buy. The generative AI also performs natural language processing, providing appropriate answers when users ask questions by voice. For example, if a user asks, "What are the reviews like for this product?", the generative AI will display the reviews for that product. This allows users to easily obtain information by voice. In this way, the personal shopping assistant system utilizes AR glasses and generative AI to provide real-time advice and information to users when selecting products, supporting them in making optimal purchase decisions. This allows users to select products efficiently and improves their shopping experience.This allows the personal shopping assistant system to provide real-time advice and information to users as they choose products, supporting them in making optimal purchasing decisions.

[0070] The personal shopping assistant system according to this embodiment comprises a recognition unit, a display unit, a learning unit, a recommendation unit, a comparison unit, and a presentation unit. The recognition unit recognizes the product the user is looking at. The recognition unit tracks the user's gaze using, for example, a camera, and recognizes the product the user's gaze is fixed on. The recognition unit can also identify products using image recognition technology. For example, the recognition unit detects the user's gaze movement using an eye-tracking device and recognizes the product the user's gaze is fixed on for a certain period of time. Image recognition technology identifies products by comparing product images with a database. The display unit uses a generation AI to display detailed information about the product recognized by the recognition unit. This detailed information includes, for example, product specifications, user reviews, price comparisons, and stock availability. For example, the display unit uses the generation AI to obtain product specification information and display it on AR glasses. The display unit can also use the generation AI to analyze user reviews and display highly-rated reviews. Furthermore, the display unit can use the generation AI to obtain price information from multiple online shops and display the lowest price. The learning unit uses generative AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. For example, the learning unit analyzes the user's purchase history data to identify the user's preferences. The learning unit can also learn the user's interests based on the user's browsing and search history. For example, the learning unit analyzes data on products the user has purchased in the past to identify the user's preferences. It learns the product categories the user is interested in based on browsing and search history. The recommendation unit uses generative AI to present personalized product recommendations based on the information learned by the learning unit. For example, the recommendation unit recommends related products and new products based on the user's preferences. The recommendation unit can also suggest products that are likely to be repurchased based on the user's past purchase history. For example, the recommendation unit recommends products related to products the user has purchased in the past. It acquires information on new products and presents new products that match the user's preferences. The comparison unit uses generative AI to compare prices and stock availability from multiple online shops based on the information presented by the recommendation unit.The comparison unit, for example, if the same product is sold at multiple online shops, will present the shop with the lowest price or the shop with the item in stock. The comparison unit can also compare prices while considering delivery time and shipping costs. For example, the comparison unit will obtain price information from multiple online shops and present the lowest price. It will also check the product's stock status and present the shop with the item in stock. The presentation unit uses a generation AI to present the optimal place to buy based on the information compared by the comparison unit. For example, the presentation unit will present the user with the lowest price or the shop with the item in stock. The presentation unit can also prioritize presenting specific brands or shops based on the user's preferences. For example, the presentation unit will present the user with the shop with the lowest price. It will also prioritize presenting specific brands or shops based on the user's preferences. As a result, the personal shopping assistant system according to this embodiment can provide real-time advice and information to the user when they are choosing a product, supporting them in making the best purchase decision.

[0071] The recognition unit recognizes the product the user is looking at. For example, the recognition unit tracks the user's gaze using a camera and recognizes the product the user's gaze is fixed on. Specifically, the eye-tracking device detects the user's eye movements with high precision and identifies the product the user's gaze is fixed on for a certain period of time. Eye-tracking technology uses infrared cameras or high-resolution cameras to track the user's pupil movements in real time and calculate the direction of the gaze. Furthermore, image recognition technology compares the product the user is looking at with a database to identify the product name and model number. For example, when the eye-tracking device detects that the user's gaze is directed at a specific product, the image recognition technology takes a picture of that product with the camera and identifies the product by comparing it with an image in the database. This process is completed within seconds, allowing for rapid recognition of the product the user is looking at. This enables the recognition unit to accurately identify the product the user is interested in and proceed to the next step of displaying information or making recommendations.

[0072] The display unit uses a generation AI to display detailed information about products recognized by the recognition unit. This detailed information includes, for example, product specifications, user reviews, price comparisons, and stock availability. The generation AI collects and integrates information from multiple data sources on the internet for display. For example, the generation AI obtains specification information and user reviews from the product's official website, online shops, and review sites, organizes this information, and provides it to the user. Furthermore, the generation AI can obtain price information from multiple online shops in real time and display the lowest price. The display unit displays this information on AR glasses or smartphone screens, making it easily accessible to the user. For example, if the user is wearing AR glasses, the detailed information of the product they are looking at will be overlaid on their field of view. If using a smartphone, the detailed information will be displayed through an application. This allows the display unit to quickly obtain detailed information about products and support the user's purchase decision.

[0073] The learning unit uses generative AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. For example, the learning unit analyzes the user's purchase history data to identify the user's preferences. Specifically, the generative AI collects data on products the user has purchased in the past and analyzes patterns such as product category, brand, and price range. Furthermore, the learning unit can also learn the user's interests based on the user's browsing and search history. For example, it identifies product categories and brands that the user frequently searches for and learns the user's preferences based on this information. The learning unit continuously updates this data to respond to changes in the user's preferences and interests. As a result, the learning unit can provide personalized information based on the user's individual needs and preferences.

[0074] The recommendation unit uses generative AI to present personalized product recommendations based on information learned by the learning unit. For example, the recommendation unit recommends related or new products based on the user's preferences. Specifically, the generative AI analyzes the user's past purchase and browsing history to identify highly relevant products. For example, it recommends products in the same category as products the user has previously purchased, or new products from the same brand. The generative AI also filters products that meet specific criteria based on the user's preferences and presents the most suitable products. Furthermore, the recommendation unit can also suggest products that are likely to be repurchased based on the user's past purchase history. For example, it can predict the timing of repurchases of consumables or regularly purchased items and recommend them at the appropriate time. In this way, the recommendation unit can present the most suitable products to the user and improve the shopping experience.

[0075] The comparison unit uses generative AI to compare prices and availability at multiple online shops based on information presented by the recommendation unit. For example, if the same product is sold at multiple online shops, the comparison unit will present the shop with the lowest price and availability. Specifically, the generative AI obtains price and inventory information through APIs from multiple online shops and compares this information. Furthermore, the comparison unit can also consider delivery time and shipping costs when making comparisons. For example, if the same product is sold at different prices at different shops, it will calculate the overall cost, including not only the lowest price but also delivery time and shipping costs, and present the optimal place to buy. The comparison unit can also prioritize displaying specific brands or shops based on user preferences. In this way, the comparison unit can provide users with the most cost-effective purchase options and support their purchasing decisions.

[0076] The presentation unit uses generative AI to suggest the best place to buy based on the information compared by the comparison unit. For example, the presentation unit might show the user the shop with the lowest price or the shop with the item in stock. Specifically, the generative AI identifies the most cost-effective place to buy based on the price and stock information collected by the comparison unit. Furthermore, the presentation unit can also prioritize specific brands or shops based on the user's preferences. For example, if a user prefers a particular brand, it will prioritize displaying shops that have that brand's products in stock. The presentation unit can also prioritize displaying specific shops based on the user's past purchase history and preferences. This allows the presentation unit to provide users with the best possible purchase options and improve the shopping experience. In addition, the presentation unit centrally provides the information necessary for users to make purchase decisions, supporting quick and efficient purchasing decisions.

[0077] The recognition unit can estimate the user's emotions and adjust the accuracy of product recognition based on the estimated emotions. For example, if the user is excited, the recognition unit can increase the accuracy of product recognition and provide more detailed information. If the user is relaxed, the recognition unit can maintain normal product recognition accuracy and provide standard information. Furthermore, if the user is stressed, the recognition unit can lower the accuracy of product recognition and provide concise information. For example, the recognition unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the provision of more appropriate information by adjusting the accuracy of product recognition according to the user's emotions. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input image data of the user captured by the camera into a generating AI, which can then perform the estimation of the user's emotions.

[0078] The recognition unit can track the user's eye movements during product recognition and determine recognition priorities based on the degree of gaze concentration. For example, if the user is looking at a particular product for a long time, the recognition unit will prioritize recognizing that product. Furthermore, if the user is shifting their gaze to multiple products, the recognition unit can prioritize recognizing the product that the user's gaze lingers on the longest. Additionally, if the user is frequently shifting their gaze, the recognition unit can analyze the eye movement patterns and recognize the product of the user's highest interest. For example, the recognition unit can detect the user's eye movements using an eye-tracking device and prioritize recognizing products where the user's gaze is fixed for a certain period. By analyzing the eye movement patterns, it identifies products of high user interest. This allows the recognition unit to prioritize product recognition based on the user's eye movements, thereby prioritizing the recognition of products of higher interest. Some or all of the above-described processes in the recognition unit may be performed using AI, or not. For example, the recognition unit can input eye-tracking data acquired by an eye-tracking device into a generating AI and have the generating AI analyze the eye movement patterns.

[0079] The recognition unit can improve the accuracy of product recognition by referring to the user's past gaze history. For example, the recognition unit can improve recognition accuracy by analyzing the user's current gaze movements based on products the user has previously looked at. The recognition unit can also identify the user's interest in specific product categories from their past gaze history and prioritize the recognition of products in those categories. Furthermore, the recognition unit can improve recognition accuracy by analyzing the user's gaze history and learning patterns of eye movements. For example, the recognition unit can analyze the user's past gaze data and identify patterns of eye movements. Based on the gaze history, it can identify product categories that the user is interested in. This allows the accuracy of product recognition to be improved by referring to the user's past gaze history. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input past gaze data into a generating AI and have the generating AI learn patterns of eye movements.

[0080] The recognition unit can estimate the user's emotions and determine the priority of products to recognize based on the estimated user emotions. For example, if the user is excited, the recognition unit will prioritize recognizing the most interesting product among those the user is looking at. If the user is relaxed, the recognition unit can also recognize products with a standard priority based on eye movements. Furthermore, if the user is stressed, the recognition unit can also prioritize recognizing products that provide concise information based on eye movements. For example, the recognition unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the recognition of more appropriate products by prioritizing products based on the user's emotions. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input image data of the user captured by the camera into a generating AI, which can then perform the estimation of the user's emotions.

[0081] The recognition unit can prioritize recognizing highly relevant products by considering the user's geographical location information during product recognition. For example, if the user is in a specific region, the recognition unit can prioritize recognizing popular products in that region. Furthermore, if the user is traveling, the recognition unit can prioritize recognizing recommended products for their travel destination. Additionally, if the user is at home, the recognition unit can prioritize recognizing products available at nearby stores. For example, the recognition unit can acquire the user's geographical location information and identify popular products in that region. It can also acquire recommended products for the travel destination from a database and prioritize their recognition. This allows the recognition unit to prioritize recognizing highly relevant products by considering the user's geographical location information. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input geographical location information into a generating AI and have the generating AI identify highly relevant products.

[0082] The recognition unit can analyze the user's social media activity and recognize related products when recognizing products. For example, the recognition unit can prioritize recognizing products that the user has "liked" or commented on on social media. It can also prioritize recognizing products that have been introduced by influencers that the user follows. Furthermore, the recognition unit can analyze the content of the user's social media posts and prioritize recognizing products of high interest. For example, the recognition unit can acquire social media data and identify products that the user has "liked" or commented on. It can also acquire products introduced by influencers that the user follows from a database and prioritize their recognition. In this way, related products can be recognized by analyzing the user's social media activity. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input social media data into a generating AI and have the generating AI identify related products.

[0083] The display unit can estimate the user's emotions and adjust the level of detail of the information displayed based on the estimated emotions. For example, if the user is excited, the display unit can display detailed specifications and reviews. It can also display standard information if the user is relaxed. Furthermore, if the user is stressed, the display unit can display concise information. For example, the display unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, 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. This allows for the provision of more appropriate information by adjusting the level of detail of the information displayed based on the user's emotions. Some or all of the above processing in the display unit may be performed using AI, or not. For example, the display unit can input user image data captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0084] The display unit can customize the displayed content based on the user's past purchase history when displaying detailed product information. For example, the display unit can prioritize displaying information related to products the user has previously purchased. The display unit can also display detailed information on products that the user might be interested in based on their purchase history. Furthermore, the display unit can analyze the user's purchase history and display reviews and ratings of products they have previously purchased. For example, the display unit analyzes the user's purchase history data and obtains information on related products. Based on the purchase history, it displays detailed information on products that the user might be interested in. This allows for the provision of more relevant information by customizing the displayed content based on the user's past purchase history. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0085] The display unit can filter the displayed content based on the user's current areas of interest when displaying detailed product information. For example, the display unit can prioritize displaying product information in categories that the user is currently interested in. The display unit can also display detailed information on related products based on the user's recent search history. Furthermore, the display unit can analyze the user's areas of interest and display information on the most relevant products. For example, the display unit can analyze the user's search history data and obtain information on related products. Based on the areas of interest, it can display detailed information on products that the user is likely to be interested in. This allows the display unit to provide more relevant information by filtering the displayed content based on the user's current areas of interest. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input search history data into a generating AI and have the generating AI obtain information on related products.

[0086] The display unit can estimate the user's emotions and adjust the order of information displayed based on the estimated emotions. For example, if the user is excited, the display unit will display the most interesting information first. If the user is relaxed, the display unit can also display information in a standard order. Furthermore, if the user is stressed, the display unit can display concise information first. For example, the display unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, 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. This allows for the provision of more appropriate information by adjusting the order of information displayed based on the user's emotions. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input image data of the user captured by the camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0087] The display unit can select the optimal display method when displaying detailed product information, taking into account the user's device information. For example, if the user is using a smartphone, the display unit provides a display method that matches the screen size. Furthermore, if the user is using a tablet, the display unit can provide a display method optimized for a larger screen. Additionally, if the user is using a smartwatch, the display unit can provide a concise and highly visible display method. For example, the display unit acquires device information and selects a display method that matches the screen size. It provides display methods according to the type of device, such as smartphones, tablets, and smartwatches. This allows the display unit to provide the optimal display method by considering the user's device information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input device information into a generating AI and have the generating AI select the optimal display method.

[0088] The display unit can analyze the user's social media activity and display relevant information when displaying detailed product information. For example, the display unit can display information related to products that the user has "liked" or commented on on social media. The display unit can also display detailed information about products introduced by influencers that the user follows. Furthermore, the display unit can analyze the content of the user's social media posts and display information about products of high interest. For example, the display unit can acquire social media data and identify products that the user has "liked" or commented on. It can acquire information about products introduced by influencers that the user follows and display it preferentially. In this way, relevant information can be displayed by analyzing the user's social media activity. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input social media data into a generating AI and have the generating AI identify relevant information.

[0089] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is excited, the learning unit can incorporate detailed data into the training. If the user is relaxed, the learning unit can also incorporate standard data into the training. Furthermore, if the user is stressed, the learning unit can incorporate concise data into the training. For example, the learning unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expressions. Emotion estimation is achieved using an emotion estimation function, 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. This allows for the incorporation of more appropriate data into the training by selecting training data based on the user's emotions. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input image data of the user captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0090] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal algorithm based on past learning data. The learning unit can also adjust parameters to improve learning accuracy based on past learning data. Furthermore, the learning unit can analyze past learning data and identify areas for improvement in the learning algorithm. For example, the learning unit analyzes past learning data and selects the optimal algorithm. It adjusts parameters to improve learning accuracy. In this way, by referring to past learning data, the learning algorithm can be optimized and learning accuracy can be improved. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0091] The learning unit can improve the accuracy of its learning by analyzing the user's past purchase history during the learning process. For example, the learning unit incorporates relevant data into the learning process based on the user's past purchase history. The learning unit can also incorporate data on products that the user might be interested in, based on the user's purchase history. Furthermore, the learning unit can analyze the user's purchase history and select data to improve the accuracy of its learning. For example, the learning unit analyzes the user's purchase history data and incorporates relevant data into the learning process. Based on the purchase history, it incorporates data on products that the user might be interested in into the learning process. This allows the learning unit to improve the accuracy of its learning by analyzing the user's past purchase history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input purchase history data into a generating AI and have the generating AI select relevant data.

[0092] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is excited, the learning unit will increase the learning frequency. It can also learn at a standard frequency if the user is relaxed. Furthermore, it can decrease the learning frequency if the user is stressed. For example, the learning unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expressions. Emotion estimation is achieved using an emotion estimation function, 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. This allows for learning at a more appropriate time by adjusting the learning frequency based on the user's emotions. Some or all of the above processing in the learning unit may be performed using AI, or not. For example, the learning unit can input image data of the user captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0093] The learning unit can select training data while considering the user's geographical location information. For example, if the user is in a specific region, the learning unit can incorporate data on popular products in that region into its training. Furthermore, if the user is traveling, the learning unit can incorporate data on recommended products at their travel destination. Additionally, if the user is at home, the learning unit can incorporate data on products available at nearby stores. For example, the learning unit can acquire the user's geographical location information and identify data on popular products in that region. It can also acquire recommended product data for the travel destination from a database and incorporate it into its training. This allows the learning unit to incorporate highly relevant data by considering the user's geographical location information. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input geographical location information into a generating AI and have the generating AI identify highly relevant data.

[0094] The learning unit can analyze the user's social media activity during training and incorporate relevant data into its learning process. For example, the learning unit can incorporate product data that the user has "liked" or commented on on social media. It can also incorporate product data that has been introduced by influencers that the user follows. Furthermore, the learning unit can analyze the content of the user's social media posts and incorporate product data of high interest into its learning process. For example, the learning unit can acquire social media data and identify product data that the user has "liked" or commented on. It can also acquire product data introduced by influencers that the user follows from a database and incorporate it into its learning process. In this way, by analyzing the user's social media activity, relevant data can be incorporated into the learning process. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input social media data into a generating AI and have the generating AI identify relevant data.

[0095] The recommendation system can estimate the user's emotions and determine the priority of recommended products based on those emotions. For example, if the user is excited, the recommendation system will prioritize recommending the most interesting products. If the user is relaxed, the recommendation system can also recommend products with standard priority. Furthermore, if the user is stressed, the recommendation system can prioritize recommending products that provide concise information. For example, the recommendation system can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expressions. Emotion estimation is achieved using an emotion estimation function, 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. This allows for more appropriate product recommendations by prioritizing products based on the user's emotions. Some or all of the above processing in the recommendation system may be performed using AI, or not. For example, the recommendation system can input image data of the user captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0096] The recommendation system can improve the accuracy of recommendations by referring to the user's past purchase history. For example, the recommendation system can prioritize recommending products related to products the user has previously purchased. It can also recommend products that the user might be interested in based on their purchase history. Furthermore, the recommendation system can analyze the user's purchase history and recommend the most relevant products. For example, the recommendation system can analyze the user's purchase history data and obtain information on related products. Based on the purchase history, it recommends products that the user might be interested in. This improves the accuracy of recommendations by referring to the user's past purchase history. Some or all of the above processes in the recommendation system may be performed using AI, for example, or without AI. For example, the recommendation system can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0097] The recommendation system can customize recommendations based on the user's current areas of interest. For example, it might prioritize recommending products in categories the user is currently interested in. It can also recommend relevant products based on the user's recent search history. Furthermore, it can analyze the user's areas of interest and recommend the most relevant products. For example, it might analyze the user's search history data to obtain information on relevant products. Based on these areas of interest, it recommends products that the user is likely to be interested in. This allows for the recommendation of more relevant products by customizing recommendations based on the user's current areas of interest. Some or all of the above processes in the recommendation system may be performed using AI, or not. For example, the recommendation system could input search history data into a generating AI and have the AI ​​obtain information on relevant products.

[0098] The recommendation system can estimate the user's emotions and adjust how recommended products are displayed based on those emotions. For example, if the user is excited, the recommendation system can provide a visually stimulating display. If the user is relaxed, it can provide a standard display. Furthermore, if the user is stressed, it can provide a concise and easily understandable display. For example, the recommendation system can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, 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. This allows for a more appropriate display by adjusting how products are displayed based on the user's emotions. Some or all of the above processing in the recommendation system may be performed using AI, or not. For example, the recommendation system can input image data of the user captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0099] The recommendation system can recommend the most suitable products by considering the user's geographical location. For example, if the user is in a specific region, the recommendation system will prioritize recommending popular products in that region. Furthermore, if the user is traveling, the recommendation system can prioritize recommending products suitable for their travel destination. Additionally, if the user is at home, the recommendation system can prioritize recommending products available at nearby stores. For instance, the recommendation system obtains the user's geographical location and identifies popular products in that region. It retrieves recommended products from a database for the travel destination and prioritizes recommending them. This allows the system to recommend the most suitable products by considering the user's geographical location. Some or all of the above processing in the recommendation system may be performed using AI, or not. For example, the recommendation system can input geographical location information into a generating AI and have the AI ​​identify highly relevant products.

[0100] The recommendation system can analyze a user's social media activity and recommend relevant products. For example, it can prioritize recommending products that a user has "liked" or commented on on social media. It can also prioritize recommending products that have been featured by influencers that the user follows. Furthermore, it can analyze the content of a user's social media posts and prioritize recommending products that are of high interest to the user. For example, the recommendation system can acquire social media data and identify products that a user has "liked" or commented on. It can also acquire products that have been featured by influencers that the user follows from its database and recommend them preferentially. In this way, by analyzing a user's social media activity, it can recommend relevant products. Some or all of the above processes in the recommendation system may be performed using AI, for example, or not. For example, the recommendation system can input social media data into a generating AI and have the generating AI identify relevant products.

[0101] The comparison unit can estimate the user's emotions and adjust the price and inventory comparison criteria based on the estimated emotions. For example, if the user is excited, the comparison unit will prioritize displaying the lowest price. If the user is relaxed, the comparison unit can also display prices and inventory using standard comparison criteria. Furthermore, if the user is stressed, the comparison unit can prioritize displaying products with ample stock. For example, the comparison unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the provision of more appropriate information by adjusting the price and inventory comparison criteria based on the user's emotions. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input image data of the user captured by the camera into the generating AI, and have the generating AI perform the estimation of the user's emotions.

[0102] The comparison unit can improve the accuracy of comparisons by referring to the user's past purchase history when comparing prices and availability. For example, the comparison unit prioritizes displaying the prices and availability of products related to products the user has previously purchased. The comparison unit can also display the prices and availability of products that the user might be interested in based on their purchase history. Furthermore, the comparison unit can analyze the user's purchase history and display the prices and availability of the most relevant products. For example, the comparison unit analyzes the user's purchase history data and obtains information on related products. Based on the purchase history, it displays the prices and availability of products that the user might be interested in. This improves the accuracy of comparisons by referring to the user's past purchase history. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0103] The comparison unit can customize the comparison based on the user's current areas of interest when comparing prices and availability. For example, the comparison unit can prioritize comparing products in categories that the user is currently interested in. The comparison unit can also compare prices and availability of related products based on the user's recent search history. Furthermore, the comparison unit can analyze the user's areas of interest and compare prices and availability of the most relevant products. For example, the comparison unit can analyze the user's search history data and obtain information on related products. Based on the areas of interest, it compares prices and availability of products that the user is likely to be interested in. This allows the comparison unit to provide more relevant information by customizing the comparison based on the user's current areas of interest. Some or all of the above processing in the comparison unit may be performed using AI, for example, or not. For example, the comparison unit can input search history data into a generating AI and have the generating AI obtain information on related products.

[0104] The comparison unit can estimate the user's emotions and adjust the display method of the comparison results based on the estimated user emotions. For example, if the user is excited, the comparison unit can provide a visually stimulating display method. It can also provide a standard display method if the user is relaxed. Furthermore, if the user is stressed, the comparison unit can provide a concise and easily understandable display method. For example, the comparison unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. 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. This allows for a more appropriate display method to be provided by adjusting the display method of the comparison results based on the user's emotions. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input the user's image data captured by the camera into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0105] The comparison unit can provide optimal comparison results by considering the user's geographical location when comparing prices and availability. For example, if the user is in a specific region, the comparison unit will prioritize displaying the prices and availability of products available in that region. Furthermore, if the user is traveling, the comparison unit can prioritize displaying the prices and availability of products available at their travel destination. Additionally, if the user is at home, the comparison unit can prioritize displaying the prices and availability of products available at nearby stores. For example, the comparison unit can acquire the user's geographical location and identify information on products available in that region. It can also acquire information on products available at the travel destination from a database and prioritize displaying that information. This allows the system to provide optimal comparison results by considering the user's geographical location. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input geographical location information into a generating AI and have the generating AI acquire information on related products.

[0106] The comparison unit can analyze the user's social media activity and incorporate relevant information into the comparison when comparing prices and availability. For example, the comparison unit can prioritize displaying the prices and availability of products that the user has "liked" or commented on on social media. It can also prioritize displaying the prices and availability of products that have been featured by influencers that the user follows. Furthermore, the comparison unit can analyze the content of the user's social media posts and prioritize displaying the prices and availability of products of high interest. For example, the comparison unit can acquire social media data and identify information about products that the user has "liked" or commented on. It can also acquire information about products featured by influencers that the user follows from a database and display it preferentially. In this way, relevant information can be incorporated into the comparison by analyzing the user's social media activity. Some or all of the above processing in the comparison unit may be performed using AI, for example, or not. For example, the comparison unit can input social media data into a generating AI and have the generating AI identify relevant information.

[0107] The presentation unit can estimate the user's emotions and adjust the optimal presentation method based on the estimated user emotions. For example, if the user is excited, the presentation unit can provide a visually stimulating presentation method. It can also provide a standard presentation method if the user is relaxed. Furthermore, if the user is stressed, it can provide a concise and easily understandable presentation method. For example, the presentation unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, 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. This allows for a more appropriate display method by adjusting the optimal presentation method based on the user's emotions. Some or all of the above processing in the presentation unit may be performed using AI, for example, or without AI. For example, the display unit can input image data of the user captured by the camera into a generating AI, and have the generating AI perform the estimation of the user's emotions.

[0108] The display unit can customize its recommendations by referencing the user's past purchase history when suggesting the most suitable purchase destinations. For example, the display unit can prioritize displaying purchase destinations related to products the user has previously purchased. It can also suggest purchase destinations for products the user might be interested in based on their purchase history. Furthermore, the display unit can analyze the user's purchase history and suggest the most relevant purchase destinations. For example, the display unit can analyze the user's purchase history data and obtain information on related products. Based on the purchase history, it can suggest purchase destinations for products the user might be interested in. This allows the display unit to customize its recommendations by referencing the user's past purchase history and provide more appropriate information. Some or all of the above processing in the display unit may be performed using AI, for example, or without AI. For example, the display unit can input purchase history data into a generating AI and have the generating AI obtain information on related products.

[0109] The presentation unit can filter the displayed content based on the user's current areas of interest when suggesting the most suitable place to buy. For example, the presentation unit can prioritize displaying products in categories that the user is currently interested in. The presentation unit can also suggest places to buy related products based on the user's recent search history. Furthermore, the presentation unit can analyze the user's areas of interest and suggest places to buy the most relevant products. For example, the presentation unit can analyze the user's search history data and obtain information on related products. Based on the areas of interest, it can suggest places to buy products that the user is likely to be interested in. This allows the presentation unit to provide more relevant information by filtering the displayed content based on the user's current areas of interest. Some or all of the above processing in the presentation unit may be performed using AI, for example, or without AI. For example, the presentation unit can input search history data into a generating AI and have the generating AI obtain information on related products.

[0110] The presentation unit can estimate the user's emotions and determine the optimal purchase priority based on the estimated emotions. For example, if the user is excited, the presentation unit will prioritize the purchase with the lowest price. If the user is relaxed, the presentation unit can also prioritize purchases in a standard order of priority. Furthermore, if the user is stressed, the presentation unit can prioritize purchases with ample stock. For example, the presentation unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The emotion estimation algorithm calculates an emotion score based on changes in facial expression. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the provision of more appropriate information by determining the optimal purchase priority based on the user's emotions. Some or all of the above processing in the presentation unit may be performed using AI, for example, or without AI. For example, the display unit can input image data of the user captured by the camera into a generating AI, and have the generating AI perform the estimation of the user's emotions.

[0111] The display unit can suggest the most suitable place to buy products by considering the user's geographical location. For example, if the user is in a specific region, the display unit will prioritize suggesting places to buy products available in that region. Furthermore, if the user is traveling, the display unit can prioritize suggesting places to buy products available at their travel destination. Additionally, if the user is at home, the display unit can prioritize suggesting places to buy products available at nearby stores. For example, the display unit can acquire the user's geographical location and identify information on products available in that region. It can also acquire information on products available at the travel destination from a database and prioritize its presentation. This allows the display unit to suggest the most suitable place to buy products by considering the user's geographical location. Some or all of the above processing in the display unit may be performed using AI, or without AI. For example, the display unit can input geographical location information into a generating AI and have the generating AI acquire information on related products.

[0112] The presentation unit can analyze the user's social media activity and present relevant information when suggesting the optimal place to buy. For example, the presentation unit can prioritize presenting the place to buy products that the user has "liked" or commented on on social media. It can also prioritize presenting the place to buy products that have been introduced by influencers that the user follows. Furthermore, the presentation unit can analyze the content of the user's social media posts and prioritize presenting the place to buy products of high interest. For example, the presentation unit can acquire social media data and identify information about products that the user has "liked" or commented on. It can also acquire information about products introduced by influencers that the user follows from a database and present it preferentially. In this way, relevant information can be presented by analyzing the user's social media activity. Some or all of the above processing in the presentation unit may be performed using AI, for example, or not using AI. For example, the presentation unit can input social media data into a generating AI and have the generating AI identify relevant information.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] The personal shopping assistant system can also acquire user health data and recommend products based on their health status. For example, it can recommend healthy foods and fitness equipment based on data from the user's fitness tracker. It can also analyze the user's sleep data and recommend products that support comfortable sleep. Furthermore, it can monitor the user's heart rate and stress levels and recommend products with relaxing effects. This allows for a more personalized shopping experience by providing products tailored to the user's health condition.

[0115] The personal shopping assistant system can further estimate the user's emotions and filter product reviews based on those emotions. For example, if the user is excited, it can prioritize displaying positive reviews. If the user is relaxed, it can display balanced reviews. Furthermore, if the user is stressed, it can display concise and to-the-point reviews. This allows for the provision of more relevant information by offering reviews tailored to the user's emotions.

[0116] The personal shopping assistant system can further estimate the user's purchasing intent and provide discount information based on that intent. For example, if a user shows high purchasing intent, it can offer a special discount coupon. If a user shows low purchasing intent, it can offer a coupon with a higher discount rate. Furthermore, if a user shows moderate purchasing intent, it can offer limited-time discount information. In this way, by providing discount information tailored to the user's purchasing intent, it can increase purchasing intent.

[0117] The personal shopping assistant system can further estimate the user's emotions and adjust the product description based on those emotions. For example, if the user is excited, it can provide a visually stimulating description. If the user is relaxed, it can provide a standard description. Furthermore, if the user is stressed, it can provide a concise and easy-to-understand description. By adjusting the product description based on the user's emotions, it can provide more relevant information.

[0118] The personal shopping assistant system can further estimate the user's emotions and suggest delivery options based on those emotions. For example, if the user is excited, it can prioritize suggesting an expedited delivery option. If the user is relaxed, it can suggest a standard delivery option. Furthermore, if the user is stressed, it can suggest a concise and easy-to-understand delivery option. This allows for more appropriate service by suggesting delivery options based on the user's emotions.

[0119] The personal shopping assistant system can further analyze the user's purchase history and provide maintenance information for previously purchased items. For example, it can notify the user of maintenance schedules for home appliances they have purchased in the past. It can also provide instructions on how to care for furniture the user has purchased. Furthermore, it can suggest washing and storage methods for clothing the user has purchased. In this way, by providing maintenance information based on the user's purchase history, it can support the long-term use of products.

[0120] A personal shopping assistant system can further consider the user's geographical location to provide region-specific offers and event information. For example, if the user is in a specific region, it can provide information on sales and events taking place in that area. If the user is traveling, it can also provide offers and sightseeing information for their destination. Furthermore, if the user is at home, it can provide coupons and offers usable at nearby stores. This allows for a more personalized service by providing region-specific offers and event information based on the user's geographical location.

[0121] The personal shopping assistant system can further analyze the user's social media activity and provide relevant product trend information. For example, it can provide trend information on products featured by influencers the user follows. It can also provide trend information on products the user has "liked" or commented on. Furthermore, it can analyze the user's social media posts and provide trend information on products of high interest. By providing trend information based on the user's social media activity, it can deliver more relevant information.

[0122] The personal shopping assistant system can further consider the user's device information to provide an optimal interface. For example, if the user is using a smartphone, it can provide an interface optimized for touch operation. If the user is using a tablet, it can provide an interface optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible interface. This allows for a more comfortable user experience by providing the optimal interface based on the user's device information.

[0123] The personal shopping assistant system can further analyze the user's purchase history and manage warranty information for previously purchased items. For example, it can notify the user of the warranty period for previously purchased items. It can also send reminders before the warranty expires. Furthermore, it can provide support information for problems that occur within the warranty period. This strengthens after-sales support for products by managing warranty information based on the user's purchase history.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The recognition unit recognizes the product the user is looking at. The recognition unit tracks the user's gaze using a camera and recognizes the product that the user's gaze is fixed on. Alternatively, product identification can be done using image recognition technology. For example, an eye-tracking device can be used to detect the user's eye movements and recognize the product that the user's gaze is fixed on for a certain period of time. Image recognition technology identifies the product by comparing the product image with a database. Step 2: The display unit uses a generation AI to display detailed information about the product recognized by the recognition unit. This detailed information includes product specifications, user reviews, price comparisons, and stock availability. For example, the generation AI can acquire product specification information and display it on the AR glasses. The generation AI can also analyze user reviews and display highly rated reviews. Furthermore, the generation AI can acquire price information from multiple online shops and display the lowest price. Step 3: The learning unit uses generative AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. The learning unit analyzes the user's purchase history data to identify the user's preferences. It can also learn the user's interests based on their browsing and search history. For example, it can analyze data on products the user has purchased in the past to identify the user's preferences. It can also learn the product categories the user is interested in based on their browsing and search history. Step 4: The recommendation unit uses generative AI to present personalized product recommendations based on information learned by the learning unit. The recommendation unit recommends related and new products based on the user's preferences. It can also suggest products that are likely to be repurchased based on the user's past purchase history. For example, it may recommend products related to products the user has purchased in the past. It also acquires information on new products and presents new products that match the user's preferences. Step 5: The comparison unit uses a generation AI to compare prices and stock availability at multiple online shops based on the information presented by the recommendation unit. If the same product is sold at multiple online shops, the comparison unit will present the shop with the lowest price or the shop with the product in stock. It can also consider delivery time and shipping costs when making comparisons. For example, it can obtain price information from multiple online shops and present the lowest price. It can also check the product's stock availability and present the shop with the product in stock. Step 6: The presentation unit uses generating AI to suggest the best place to buy based on the information compared by the comparison unit. The presentation unit shows the user the shop with the lowest price or the shop with the item in stock. It can also prioritize specific brands or shops based on the user's preferences. For example, it can show the user the shop with the lowest price. It can also prioritize specific brands or shops based on the user's preferences.

[0126] 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.

[0127] 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 text generation AI, image generation AI, and multimodal generation AI. 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 with 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 from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts 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.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0128] 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.

[0129] Each of the multiple elements described above, including the recognition unit, display unit, learning unit, recommendation unit, comparison unit, and presentation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recognition unit tracks the user's gaze using the camera 42 of the smart device 14 and recognizes the product the user is looking at. The display unit uses a generation AI to display detailed information of the product recognized by the recognition unit on the display 40A of the smart device 14. The learning unit uses a generation AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. The recommendation unit uses a generation AI to present personalized recommended products based on the information learned by the learning unit. The comparison unit uses a generation AI to compare prices and stock availability at multiple online shops based on the information presented by the recommendation unit. The presentation unit uses a generation AI to present the best place to buy based on the information compared by the comparison unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the recognition unit, display unit, learning unit, recommendation unit, comparison unit, and presentation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the recognition unit tracks the user's gaze using the camera 42 of the smart glasses 214 and recognizes the product the user is looking at. The display unit uses a generation AI to display detailed information of the product recognized by the recognition unit on the display of the smart glasses 214. The learning unit uses a generation AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. The recommendation unit uses a generation AI to present personalized recommended products based on the information learned by the learning unit. The comparison unit uses a generation AI to compare prices and stock availability at multiple online shops based on the information presented by the recommendation unit. The presentation unit uses a generation AI to present the best place to buy based on the information compared by the comparison unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the recognition unit, display unit, learning unit, recommendation unit, comparison unit, and presentation unit, is implemented in at least one of the following: a headset terminal 314 and a data processing unit 12. For example, the recognition unit tracks the user's gaze using the camera 42 of the headset terminal 314 and recognizes the product the user is looking at. The display unit uses a generation AI to display detailed information of the product recognized by the recognition unit on the display 343 of the headset terminal 314. The learning unit uses a generation AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. The recommendation unit uses a generation AI to present personalized recommended products based on the information learned by the learning unit. The comparison unit uses a generation AI to compare prices and stock availability at multiple online shops based on the information presented by the recommendation unit. The presentation unit uses a generation AI to present the best place to buy based on the information compared by the comparison unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the recognition unit, display unit, learning unit, recommendation unit, comparison unit, and presentation unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the recognition unit tracks the user's gaze using the camera 42 of the robot 414 and recognizes the product the user is looking at. The display unit uses a generation AI to display detailed information of the product recognized by the recognition unit on the display of the robot 414. The learning unit uses a generation AI to learn the user's past purchase history and preferences based on the information displayed by the display unit. The recommendation unit uses a generation AI to present personalized recommended products based on the information learned by the learning unit. The comparison unit uses a generation AI to compare prices and stock availability at multiple online shops based on the information presented by the recommendation unit. The presentation unit uses a generation AI to present the best place to buy based on the information compared by the comparison unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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."

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] (Note 1) A recognition unit that recognizes the product the user is looking at, A display unit that displays detailed information of the product recognized by the recognition unit, A learning unit that learns the user's past purchase history and preferences based on the information displayed by the aforementioned display unit, A recommendation unit presents personalized product recommendations based on the information learned by the aforementioned learning unit, A comparison unit that compares the prices and stock availability of multiple online shops based on the information provided by the recommendation unit, The system includes a presentation unit that presents the optimal supplier based on the information compared by the comparison unit. A system characterized by the following features. (Note 2) The aforementioned recognition unit, The system estimates the user's emotions and adjusts the accuracy of product recognition based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned recognition unit, During product recognition, the system tracks the user's eye movements and determines recognition priorities based on the degree of focus on the gaze. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned recognition unit, When recognizing products, the system improves recognition accuracy by referencing the user's past eye-tracking history. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned recognition unit, It estimates the user's emotions and determines the priority of products to recognize based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned recognition unit, When recognizing products, the system prioritizes recognizing highly relevant products by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned recognition unit, During product recognition, the system analyzes the user's social media activity to identify related products. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned display unit is It estimates the user's emotions and adjusts the level of detail displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned display unit is When displaying product details, customize the displayed content based on the user's past purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned display unit is When displaying product details, the displayed content is filtered based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned display unit is It estimates the user's emotions and adjusts the order of information displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned display unit is When displaying detailed product information, the system selects the optimal display method considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned display unit is When displaying product details, the system analyzes the user's social media activity and displays relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, During training, the system analyzes the user's past purchase history to improve the accuracy of the learning process. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning unit, During training, the training data is selected taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned learning unit, During training, the system analyzes users' social media activity and incorporates relevant data into the learning process. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned recommendation department, It estimates the user's emotions and determines the priority of recommended products based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned recommendation department, When making recommendations, we improve the accuracy of recommendations by referencing the user's past purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned recommendation department, When making recommendations, customize the recommendations based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned recommendation department, We estimate the user's emotions and adjust how recommended products are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned recommendation department, When making recommendations, the system takes the user's geographical location into consideration to suggest the most suitable products. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned recommendation department, When making recommendations, the system analyzes the user's social media activity and recommends relevant products. The system described in Appendix 1, characterized by the features described herein. (Note 26) The comparison unit is, It estimates user sentiment and adjusts price and inventory comparison criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The comparison unit is, When comparing prices and availability, we improve the accuracy of comparisons by referencing the user's past purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The comparison unit is, When comparing prices and availability, the comparison is customized based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 29) The comparison unit is, It estimates the user's emotions and adjusts how comparison results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The comparison unit is, When comparing prices and availability, we take the user's geographical location into consideration to provide the most optimal comparison results. The system described in Appendix 1, characterized by the features described herein. (Note 31) The comparison unit is, When comparing prices and availability, analyze users' social media activity and incorporate relevant information into the comparison. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned display unit is, It estimates the user's emotions and adjusts the method of suggesting the best place to buy based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned display unit is, When suggesting the best place to buy, the system customizes the suggestions by referencing the user's past purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned display unit is, When suggesting the best place to buy, the suggestions are filtered based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned display unit is, It estimates the user's emotions and determines the optimal purchase destination based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned display unit is, When suggesting the best place to buy, the system will take the user's geographical location into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned display unit is, When suggesting the best place to buy, the system analyzes the user's social media activity and presents relevant information. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0198] 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. A recognition unit that recognizes the product the user is looking at, A display unit that displays detailed information of the product recognized by the recognition unit, A learning unit that learns the user's past purchase history and preferences based on the information displayed by the aforementioned display unit, A recommendation unit presents personalized product recommendations based on the information learned by the aforementioned learning unit, A comparison unit that compares the prices and stock availability of multiple online shops based on the information provided by the recommendation unit, The system includes a presentation unit that presents the optimal supplier based on the information compared by the comparison unit. A system characterized by the following features.

2. The aforementioned recognition unit, The system estimates the user's emotions and adjusts the accuracy of product recognition based on those estimated emotions. The system according to feature 1.

3. The aforementioned recognition unit, During product recognition, the system tracks the user's eye movements and determines recognition priorities based on the degree of focus on the gaze. The system according to feature 1.

4. The aforementioned recognition unit, When recognizing products, the system improves recognition accuracy by referencing the user's past eye-tracking history. The system according to feature 1.

5. The aforementioned recognition unit, It estimates the user's emotions and determines the priority of products to recognize based on the estimated user emotions. The system according to feature 1.

6. The aforementioned recognition unit, When recognizing products, the system prioritizes recognizing highly relevant products by considering the user's geographical location. The system according to feature 1.

7. The aforementioned recognition unit, During product recognition, the system analyzes the user's social media activity to identify related products. The system according to feature 1.

8. The aforementioned display unit is It estimates the user's emotions and adjusts the level of detail displayed based on those emotions. The system according to feature 1.

Images