system

Abstract

We provide the system. [Solution] An image recognition means that analyzes visual information to recognize products from visual data, A recommendation method for generating recommendation information about products, A gaze tracking means that tracks the user's gaze and acquires gaze information, Action recognition means that recognizes the user's actions and determines their intention, A system that includes a means for initiating a transaction based on the user's selection.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional television shopping is limited to specific programs, and there are problems involving difficulties and complexities when viewers purchase products. For example, viewers have to purchase products via phone calls or websites, and in the process, the viewers' motivation may decline. Furthermore, there has been a lack of means for viewers to easily identify and immediately purchase products they are interested in while watching TV programs. The object of this invention is to provide a system that enables viewers to purchase products in a simple and intuitive way while maintaining the TV viewing experience.

Means for Solving the Problems

[0005] This invention solves the target problem by providing an image recognition means that analyzes visual information and recognizes products from the visual data. This makes it possible to automatically identify products displayed in television images. Furthermore, by providing a recommendation means that generates recommendation information about products, it provides product information optimized for the user. In addition, by including an eye-tracking means that tracks the user's gaze and acquires eye-gaze information, and a motion recognition means that recognizes the user's actions and determines their intention, it is possible to select products based on the user's natural actions. Finally, by using a transaction initiation means that starts a transaction based on the user's selection, a smooth purchase procedure is realized. With this configuration, a system is provided that allows viewers to easily purchase products without interrupting their television viewing.

[0006] "Visual information" is a general term for data obtained from images and videos that users can visually recognize.

[0007] "Image recognition means" refers to a device or program that uses technical methods to analyze visual information and identify specific objects or patterns.

[0008] A "recommendation system" is a system that presents highly relevant products and information based on the user's characteristics and behavioral history.

[0009] "Eye-tracking technology" refers to a technology that detects the movement of a user's eyes and determines where their gaze is directed.

[0010] "Motion recognition means" refers to a device or program that uses technical methods to detect a user's physical movements and determine the user's intentions based on those movements.

[0011] A "transaction initiation system" is a system that executes purchase procedures and orders based on user input and selections. [Brief explanation of the drawing]

[0012] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] The 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.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing user actions, and an eye-tracking device.

[0034] First, the server continuously receives video footage from television programs and recognizes products from the visual information. The image recognition system uses a machine learning model to detect products and analyze their features. The detected products are compared with a database to generate detailed product information and recommendation information. The recommendation system presents relevant products based on the user's past purchase history and preferences.

[0035] Next, the terminal collects gaze data from an eye-tracking device to track the user's gaze. The eye-tracking means recognizes when the user's gaze is focused on a specific part of the screen and sends that information to a server.

[0036] Furthermore, the device uses cameras and sensors to detect the user's hand gestures. The motion recognition system identifies specific gestures (for example, the "OK!" gesture) and transmits them to the server as an intention to purchase.

[0037] Once the user has finished selecting items, the terminal initiates the purchase process using the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After the user confirms, the server performs a secure payment process and completes the transaction. The server then sends the user a purchase completion notification and updates the purchase history.

[0038] As a concrete example, suppose a user is watching a cooking show and becomes interested in a pot used in it. The server analyzes the video data, identifies the pot, and sends related information to the user's terminal. The user then looks at the pot and makes an "OK!" gesture to begin the purchase process, easily completing the purchase. In this way, the system of the present invention makes user interaction almost unconscious, significantly improving the shopping experience.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server receives video data from television programs in real time and uses image processing algorithms to identify products. Once a product is identified, the information is matched against a database to retrieve relevant product identification information and detailed information.

[0042] Step 2:

[0043] The server uses AI generation based on acquired product information to create product recommendations tailored to the user. Based on past viewing and purchase history, it scores and prioritizes highly relevant products for presentation.

[0044] Step 3:

[0045] The device receives data from an eye-tracking device to track the user's gaze. The eye-tracking algorithm analyzes the position of the gaze and identifies which part of the image the user is focusing on.

[0046] Step 4:

[0047] The device transmits gaze information about the product area that it has visually identified to the server. This includes information such as how long the user's gaze remained in a particular location.

[0048] Step 5:

[0049] The device detects user gestures using high-sensitivity sensors and cameras. When the motion recognition algorithm detects an "OK!" gesture, it interprets the user's intention as a purchase and notifies the server.

[0050] Step 6:

[0051] Once a user indicates their intention to purchase, the server sends detailed information about the potential purchase items and a purchase confirmation screen to the user's device. Here, the user can make a final confirmation of their purchase.

[0052] Step 7:

[0053] After the user makes a final confirmation of their purchase, the server initiates payment processing via the payment gateway. The user's secure payment information is used during this process.

[0054] Step 8:

[0055] Once a transaction is complete, the server sends a purchase confirmation to the user and updates the purchase history database. This information is used for future recommendations.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] A challenge with traditional online shopping systems is that users have to go through a lot of trouble and time to obtain product information and make a purchase. Specifically, the process of identifying products of interest, checking detailed information, and completing the purchase procedure is cumbersome, resulting in a poor user experience.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes an image analysis means for analyzing visual information and recognizing items from the visual data; a recommendation generation means for generating recommendation information about the items; an eye-tracking device for tracking the user's gaze and acquiring gaze data; an action detection means for detecting the user's actions and determining their intentions; and a transaction initiation processing means for initiating a transaction based on the user's selection. This makes it possible for users to instantly identify products of interest from the video they are watching and to proceed with the purchase process intuitively.

[0061] "Visual information" refers to video and image data acquired by cameras and sensors.

[0062] "Image analysis means" refers to a part of the function that constitutes a system that recognizes objects from visual data and extracts their characteristics.

[0063] A "recommendation generation method" has the function of presenting relevant information and alternatives suitable for the user based on the recognized items.

[0064] An "eye-tracking device" is a device that detects the user's eye movements and measures and analyzes where their gaze is directed on the screen.

[0065] A "motion detection means" is a component that analyzes the user's body movements and determines their intentions.

[0066] A "transaction initiation processing mechanism" is a part of a system that initiates the purchase procedure for goods based on the user's selection.

[0067] A "gaze focus recognition means" is a function that detects when a user's gaze data is focused on a specific screen area and transmits that information to a server.

[0068] A "means of conveying intent" refers to a system element that senses the user's gestures and accurately transmits their intent to the server.

[0069] In this embodiment of the invention, a server plays a crucial role. The server continuously receives video signals from a television receiver and processes the visual information. Specifically, it recognizes objects from the visual data using an image analysis means employing a machine learning algorithm. In this process, deep learning technology and database matching are combined to identify objects and extract their features. Regarding the recognized objects, the server uses a recommendation generation means to generate and present relevant information and alternative product information suitable for the user.

[0070] The terminal acts as the interface with the user. The terminal includes an eye-tracking device that collects the user's gaze data in real time. This device can identify which part of the screen the user is focusing on. The terminal also uses a camera and motion sensors to detect user movements. Utilizing the motion detection means, when it receives a gesture from the user, such as a hand signal, it notifies the server of this intent and prepares to begin the purchase process.

[0071] When a user selects a product they are interested in within a video they are watching, the device transmits this information to the server through the user's gaze and gestures towards that product. The server then uses a transaction initiation process to quickly proceed with the purchase. Advanced image recognition technology allows users to easily select the desired product and experience the purchase process intuitively.

[0072] For example, if a user becomes interested in a cooking utensil while watching a cooking show, the device detects the user's gaze towards the utensil and checks their gesture. Based on this information, the server identifies the utensil and displays related purchase information. The user signals their intention to purchase to the server with an "OK!" gesture, and the system completes the purchase process. This series of operations allows the user to enjoy an efficient and seamless shopping experience.

[0073] An example of a prompt using a generative AI model would be an instruction such as, "Please describe a system that visually recognizes products featured on a television program and assists the user in the purchase process through their gaze and gestures."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server receives visual information in real time from the television receiver. It takes this visual information as input and uses image analysis to recognize objects. In this process, machine learning algorithms scan each frame of the visual data and extract the features of the objects. As output, a list of identified objects is generated. For example, cooking utensils shown in a program are identified as pots and pans.

[0077] Step 2:

[0078] The server matches the characteristics of the items recognized in step 1 against a database. This database contains detailed product information, from which the server obtains input to generate relevant recommendation information. Based on the matching results from the database, it outputs recommendation information to present to the user. Specifically, this includes the price of the cookware, the manufacturer, and information on online stores where it can be purchased.

[0079] Step 3:

[0080] The device collects user gaze data using an eye-tracking device. The eye-tracking device receives the user's eye movements as input and performs data calculations to detect which part of the screen the gaze is directed towards. The output provides the gaze position and focus. This allows for the identification of objects the user is particularly interested in.

[0081] Step 4:

[0082] The device records user movements using a camera and motion sensors. The user's movements are used as input, and data processing is performed by a motion detection system to identify specific gestures. The output then identifies clear gestures indicating purchase intent. For example, if a user makes an "OK!" gesture, this is converted into a signal that is transmitted to the server indicating their purchase intent.

[0083] Step 5:

[0084] The user confirms the items they wish to purchase through their gaze and gestures. The terminal instructs the server to initiate the transaction based on these inputs. The server retrieves this information, generates a prompt message on the screen displaying the purchase details of the items, and asks the user for confirmation. Upon user confirmation, the purchase process begins, and a secure payment process is executed.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] Currently, in many physical stores, customers need to spend time individually obtaining product information, which often makes the purchasing process cumbersome. Furthermore, manual verification and waiting times at the checkout are unavoidable when purchasing specific items. These factors cause stress for consumers and degrade the quality of the shopping experience. Therefore, innovative methods are needed to make the in-store purchasing process more efficient and intuitive.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes image recognition means for analyzing visual information and recognizing objects from the visual data, generation means for generating presentation information about the objects, and eye-tracking means for tracking the user's gaze and acquiring gaze data. This enables the user to intuitively select products in a physical store and complete the purchase with minimal effort.

[0090] "Visual information" refers to image and video data acquired using digital cameras or sensors.

[0091] "Image recognition means" refers to algorithms and devices that use computer vision technology to identify objects and scenes from visual information.

[0092] "Generation means" refers to devices or software that perform a process of generating relevant information and recommendations based on recognized objects.

[0093] "Eye-tracking means" refers to technologies and devices that measure the direction of a user's gaze and acquire that data.

[0094] "Gesture recognition means" refers to technologies and devices that use sensors or cameras to detect the movements of a user's hands or body and interpret them as specific intentions or commands.

[0095] A "transaction initiation mechanism" is a system that automatically or semi-automatically initiates the purchase process based on the selected object.

[0096] "Augmented reality display means" refers to devices and technologies for overlaying and displaying digital information onto the real world.

[0097] To realize this application, the system primarily uses a server, terminals, eye-tracking devices, and gesture recognition technology. The server first acquires visual information through a digital camera, uses image recognition to identify products, and generates presentation information about those products. Machine learning frameworks such as TENSORFLOW® and PyTorch are used for image recognition. The server then performs object identification and information generation in physical stores.

[0098] Next, the device tracks the user's gaze. Using a Tobii eye-tracking device, it collects gaze data in real time. This data is sent to a server for processing to determine which objects the user is interested in. If the gaze remains on a specific object for a certain period of time, information about that object is presented by the augmented reality display system.

[0099] Furthermore, the server uses gesture recognition to detect the user's hand and body movements. Using OpenCV and MediaPipe, it interprets the user's gestures and determines their purchase intent. For example, if an "OK!" gesture is detected, the transaction process to purchase that item is initiated.

[0100] To give a concrete example, if a user finds a smart toy in a physical store and their intention to purchase is confirmed by gesture recognition while they are looking at the toy, the transaction process will proceed immediately, improving the user experience. Throughout this entire process, augmented reality information is presented via devices such as HMDs, providing the user with intuitive product information and purchase options.

[0101] Examples of prompt statements for generative AI models include the following:

[0102] "Propose a prototype of a system that recognizes products based on image data, identifies user interests using eye-tracking information, and allows users to decide on the purchase of a specific product through gestures."

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server receives visual information from a digital camera transmitted from a terminal. Using this visual information as input, it utilizes image recognition and a generative AI model to identify products and analyze their characteristics. After data processing, detailed information and related data of the identified products are output.

[0106] Step 2:

[0107] The device acquires the user's gaze data in real time using a Tobii eye-tracking device. This gaze information is sent to a server, which uses the gaze information to perform data calculations to identify products of interest to the user. When the gaze is focused on a specific object, that information is output, and details of the corresponding product are displayed.

[0108] Step 3:

[0109] The user makes a gesture indicating their intention to purchase after reviewing the product. The terminal recognizes this gesture using OpenCV or MediaPipe. This gesture data is sent to the server as input, and the server processes the data to determine the intention. If the judgment results in a gesture that is interpreted as an intention to purchase, the purchase process is initiated.

[0110] Step 4:

[0111] The server executes the purchase process. Using the transaction initiation method, it generates a purchase screen based on the previously obtained product information and presents it to the user via the terminal. After final confirmation, the server securely executes the payment process and completes the purchase. As output, a transaction completion notification is sent to the user.

[0112] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0113] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing the user's actions and emotions, and an eye-tracking device and an emotion recognition engine.

[0114] First, the server receives video data from television programs in real time and uses image processing algorithms to identify products. The server generates information about the identified products and related recommendation information. The recommendation system suggests products that are highly relevant to the user based on the user's past viewing and purchase history, as well as their emotional state.

[0115] The device collects user gaze data using an eye-tracking device. The eye-tracking means identifies which part of the screen the user is fixating on and sends that information to a server. Furthermore, the device is equipped with an emotion recognition engine that obtains emotion information by analyzing changes in the user's facial expressions. This emotion information is taken into consideration by the recommendation system and used to improve the accuracy of product recommendations.

[0116] Furthermore, the device has a motion recognition function that identifies gestures made by the user. The motion recognition means recognizes the "OK!" gesture and sends the intention to the server as a purchase intent.

[0117] Once the user has finished selecting products, the terminal initiates the purchase process through the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After confirmation, the server performs a secure payment process. Upon completion of the transaction, the server sends the user a purchase completion notification, records the purchase history and sentiment information in a database, and uses it for future recommendations.

[0118] As a concrete example, consider a scenario where a user becomes interested in an outfit that appears in a movie. The server identifies the outfit in the video and provides relevant information. In addition, an emotion recognition engine analyzes the user's facial expressions, and if it detects positive emotions, it uses that information to provide even more appropriate product recommendations. This invention allows users to have a more personalized shopping experience.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server receives video data from television programs in real time and uses machine learning algorithms to identify products within the video. Once a product is identified, its detailed information is retrieved from a database.

[0122] Step 2:

[0123] The server uses AI to generate personalized recommendations based on the acquired product information. Specifically, it lists relevant products by taking into account the user's purchase history, viewing history, and real-time sentiment information.

[0124] Step 3:

[0125] The device uses an eye-tracking device to receive the user's gaze data and identify where on the screen the user is fixating. The gaze information is immediately sent to the server.

[0126] Step 4:

[0127] The device analyzes the user's facial expressions in real time via a facial recognition camera and extracts emotional information using an emotion recognition engine. This emotional information quantifies the user's current mood and level of interest.

[0128] Step 5:

[0129] The server integrates gaze and emotion information transmitted from the device to further optimize recommendations and provides the results to the user. This results in personalized recommendations that focus on products the user has looked at or products that have elicited positive emotions.

[0130] Step 6:

[0131] The device uses sensors to detect the user's hand gestures and a motion recognition algorithm to recognize the "OK!" gesture. Once this action is recognized, the selected product is confirmed.

[0132] Step 7:

[0133] The server initiates the transaction start step and displays a purchase confirmation dialog on the screen. The user can then make a final confirmation of the purchase.

[0134] Step 8:

[0135] Once the user finalizes the purchase, the server proceeds with the payment process, ensuring that the transaction is securely verified. After the transaction is complete, the server sends a purchase completion notification and updates the user's purchase history and associated sentiment information.

[0136] (Example 2)

[0137] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0138] Traditional online shopping systems have limited the user experience due to insufficient personalized product recommendations based on user interests and emotions. Furthermore, a lack of intuitive controls for users to smoothly select and purchase products remains a challenge.

[0139] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0140] In this invention, the server includes image processing means for analyzing visual information and recognizing products from the visual data, information generation means for generating recommendation information about products based on past history and emotional state, and gaze detection means for tracking the user's gaze and acquiring gaze information. This enables personalized product recommendations that are tailored to the user's interests and emotions.

[0141] "Analyzing visual information" refers to the process of detecting specific objects or features from image or video data and performing data processing to identify them.

[0142] "Recognizing a product" means analyzing the characteristics of a product and comparing them with information in a database to identify its specific product name and attributes.

[0143] "Information generation means" refers to a device or program that has the function of creating appropriate recommendation information based on past historical data and the user's current emotional state.

[0144] "Eye-gaze detection means" refers to a device or program that analyzes the movement of the user's eyeballs and the point of fixation to determine where they are looking.

[0145] An "emotion analysis tool" is a device or program that analyzes the user's facial expressions and infers the type and intensity of emotions from them.

[0146] "Motion detection means" refers to a device or program that analyzes the user's body movements and gestures to determine a specific intention or command.

[0147] "Means of performing a procedure" refers to a device or program that controls a series of actions necessary to initiate a transaction and executes payment processing and verification steps.

[0148] To implement this invention, a system including a server, terminals, and various devices is constructed. The server receives video data in real time via a television receiver and identifies products in the visual data using an image processing library. This process uses OpenCV, a common image recognition library, to extract features of products shown in the video and match them with a database.

[0149] Next, the device uses an eye-tracking device to track the user's gaze. This device utilizes a common eye-tracking technology to identify where the user is looking on the screen. Based on this result, the user's interests are measured.

[0150] Furthermore, the device is equipped with an emotion analysis engine that monitors the user's facial expressions via a camera. Using general emotion recognition software, it analyzes changes in the user's facial expressions and determines their emotional state. This information is used by the server to improve the accuracy of product recommendations.

[0151] The terminal also has motion detection capabilities, recognizing the user's hand gestures with its camera. Motion recognition uses a machine learning model to interpret the gestures; for example, an "OK!" command is interpreted as an intention to purchase. This information is transmitted to a server and used as a means to initiate a transaction.

[0152] For example, if a user becomes interested in an outfit while watching a movie, the server analyzes the video of that scene and extracts detailed information about the outfit. The emotion recognition engine reads the user's facial expressions, and if it detects a positive emotion, it suggests related products based on that.

[0153] An example of a prompt to input into a generative AI model would be: "Please provide detailed information about the costumes the user showed interest in while watching the movie. Based on the user's emotional state, please also recommend related products."

[0154] In this way, users can receive personalized product recommendations based on their viewing experience and enjoy a more fulfilling shopping experience.

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The server receives video data in real time from the television receiver. Using this video data as input, it identifies products using an image processing algorithm. Specifically, it uses OpenCV to convert the images in the video to grayscale and performs edge detection to recognize the contours of the products. This data processing outputs characteristic data of the identified products.

[0158] Step 2:

[0159] The device collects user gaze information using an eye-tracking device. This gaze data is used as input to identify where the user is fixating on the screen. Specifically, an eye-tracking algorithm analyzes the user's eye movements and outputs the coordinates of the point of fixation. This output is sent to the server as information indicating the user's area of ​​interest.

[0160] Step 3:

[0161] The device uses an emotion recognition engine to analyze the user's facial expressions and obtain emotional information. This facial data is then used as input to estimate the emotional category (e.g., joy, surprise) using a deep learning model. The model extracts facial features and outputs an emotional label based on them. This emotional information is also sent to the server and used as a basis for product recommendation decisions.

[0162] Step 4:

[0163] The server uses a generative AI model to recommend products based on product identification results, user gaze data, and sentiment information. Using this information as input, a machine learning model, which also considers historical data, generates an optimal product list. As a result of this data processing, product recommendations are output to the user.

[0164] Step 5:

[0165] The terminal uses motion detection to recognize the user's gestures. A motion analysis algorithm takes the gesture video as input, identifies gestures such as "OK!", and outputs their intent to the server. This confirms the user's purchase intention.

[0166] Step 6:

[0167] The server initiates a transaction based on user gesture recognition. Using product information and screen display data for purchase confirmation as input, it calls the payment processing system to securely complete the transaction. As an output of this process, a purchase completion notification is sent to the user, and the purchase history is recorded in the database.

[0168] (Application Example 2)

[0169] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0170] Traditional e-commerce systems present challenges such as a cumbersome process from product selection to purchase, making it difficult to provide personalized recommendations. Furthermore, mechanical recommendations often fail to consider the user's emotional state, hindering the improvement of the user experience. The lack of a payment process that quickly and naturally reflects purchase intent is also a significant issue.

[0171] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0172] In this invention, the server includes image recognition means for analyzing visual information and recognizing products from visual data, recommendation means for generating recommendation information about products, eye-tracking means for tracking the user's gaze and acquiring eye-tracking information, emotion recognition means for analyzing the user's facial expressions and recognizing emotions, and action recognition means for recognizing the user's actions and determining their intentions. This enables highly accurate product recommendations based on the user's interests and emotional state, and a smooth purchase process through intuitive actions.

[0173] "Image recognition means" refers to a technology or device for analyzing visual information to recognize products from visual data.

[0174] "Recommendation methods" refer to technologies or devices for generating highly relevant information about a product and suggesting it to the user.

[0175] "Eye-tracking means" refers to a technology or device that tracks the movement of a user's eyes and identifies which part they are fixating on.

[0176] "Emotion recognition means" refers to technology or devices for identifying an emotional state by analyzing the user's facial expressions.

[0177] "Motion recognition means" refers to a technology or device for analyzing the user's body movements and determining the user's intentions from those movements.

[0178] "Transaction initiation means" refers to technology or equipment for initiating a transaction, such as a purchase, based on the user's choice.

[0179] The system for implementing this invention provides users with a personalized purchasing experience by utilizing various devices and software. The system mainly consists of a server, terminals, eye-tracking devices, and an emotion recognition engine.

[0180] The server is the central hub for calculations and processing, using image recognition algorithms to analyze product information from video footage. The server also generates relevant recommendations based on this analysis. These recommendations are customized based on the user's viewing history, purchase history, and even their emotional state, which is captured in real time.

[0181] The user's device uses an eye-tracking device to collect eye-tracking information and accurately measure the user's eye movements. This data is used to identify which part of the screen the user is fixating on, and the identified eye-tracking information is sent to a server. The device also has an emotion recognition engine that analyzes the user's facial expressions in real time, allowing it to understand the user's emotional state.

[0182] The system combines user gaze and emotion data to improve the accuracy of product recommendations. Furthermore, it can initiate a transaction by recognizing specific gestures made by the user (e.g., a thumbs-up "OK!" gesture) and interpreting them as a purchase intention. The server performs secure payment processing and notifies the user when the transaction is complete. The recorded purchase history and emotion information are stored in a database and used for future recommendations.

[0183] For example, when a user becomes interested in an outfit they see while watching a movie or TV show, the eye-tracking device and emotion recognition engine can work together to determine whether the outfit is being viewed favorably. By integrating eye-tracking and emotion information in this way, the system can recommend the most suitable product for the user and facilitate a smooth purchase process.

[0184] An example of a prompt message is: "The user found a product they liked in the video they were watching. We want to confirm their interest in the product using eye-tracking and simplify the purchase process."

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The server receives video data from television programs in real time and identifies products using an image recognition algorithm. The input is video data, and the output is information about the identified products. Products are identified by analyzing the pixels of the image data and extracting patterns and shapes characteristic of the product.

[0188] Step 2:

[0189] The server generates recommendation information related to the identified product. Inputs include past viewing and purchase history, as well as real-time sentiment information. The output is personalized recommendations used to present the user with highly relevant products. Recommendations are prioritized based on relevance, matching historical and sentiment data.

[0190] Step 3:

[0191] The device uses an eye-tracking device to collect user gaze data. The input is the user's visual gaze information, and the output is the specific location on the screen where the gaze is directed. The gaze position is determined by analyzing eye movements in real time via the camera and calculating the point of fixation.

[0192] Step 4:

[0193] The device uses an emotion recognition engine to acquire emotional information from the user's facial expressions. The input is image data of the user's face, and the output is the detected emotional state. Through image analysis, features related to facial expressions are extracted, and the emotional state is identified. This emotional information is used by recommendation systems to improve the accuracy of product recommendations.

[0194] Step 5:

[0195] The device recognizes the user's gestures to determine their purchase intent. The input is the user's gesture actions, and the output is confirmation information regarding the user's intention. A motion recognition algorithm is used to analyze the state of the gestures and identify their intent.

[0196] Step 6:

[0197] The server initiates the purchase process through the transaction initiation method and performs secure payment processing. Input is user verification information, and output is a transaction completion notification. Payment processing utilizes a payment API to integrate with external payment systems, ensuring a secure transaction.

[0198] 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.

[0199] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0200] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0201] [Second Embodiment]

[0202] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0203] 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.

[0204] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0205] 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.

[0206] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0207] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0208] 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.

[0209] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0210] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0211] The 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.

[0212] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0213] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0214] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing user actions, and an eye-tracking device.

[0215] First, the server continuously receives video footage from television programs and recognizes products from the visual information. The image recognition system uses a machine learning model to detect products and analyze their features. The detected products are compared with a database to generate detailed product information and recommendation information. The recommendation system presents relevant products based on the user's past purchase history and preferences.

[0216] Next, the terminal collects gaze data from an eye-tracking device to track the user's gaze. The eye-tracking means recognizes when the user's gaze is focused on a specific part of the screen and sends that information to a server.

[0217] Furthermore, the device uses cameras and sensors to detect the user's hand gestures. The motion recognition system identifies specific gestures (for example, the "OK!" gesture) and transmits them to the server as an intention to purchase.

[0218] Once the user has finished selecting items, the terminal initiates the purchase process using the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After the user confirms, the server performs a secure payment process and completes the transaction. The server then sends the user a purchase completion notification and updates the purchase history.

[0219] As a concrete example, suppose a user is watching a cooking show and becomes interested in a pot used in it. The server analyzes the video data, identifies the pot, and sends related information to the user's terminal. The user then looks at the pot and makes an "OK!" gesture to begin the purchase process, easily completing the purchase. In this way, the system of the present invention makes user interaction almost unconscious, significantly improving the shopping experience.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] The server receives video data from television programs in real time and uses image processing algorithms to identify products. Once a product is identified, the information is matched against a database to retrieve relevant product identification information and detailed information.

[0223] Step 2:

[0224] The server uses AI generation based on acquired product information to create product recommendations tailored to the user. Based on past viewing and purchase history, it scores and prioritizes highly relevant products for presentation.

[0225] Step 3:

[0226] The device receives data from an eye-tracking device to track the user's gaze. The eye-tracking algorithm analyzes the position of the gaze and identifies which part of the image the user is focusing on.

[0227] Step 4:

[0228] The device transmits gaze information about the product area that it has visually identified to the server. This includes information such as how long the user's gaze remained in a particular location.

[0229] Step 5:

[0230] The device detects user gestures using high-sensitivity sensors and cameras. When the motion recognition algorithm detects an "OK!" gesture, it interprets the user's intention as a purchase and notifies the server.

[0231] Step 6:

[0232] Once a user indicates their intention to purchase, the server sends detailed information about the potential purchase items and a purchase confirmation screen to the user's device. Here, the user can make a final confirmation of their purchase.

[0233] Step 7:

[0234] After the user makes a final confirmation of their purchase, the server initiates payment processing via the payment gateway. The user's secure payment information is used during this process.

[0235] Step 8:

[0236] Once a transaction is complete, the server sends a purchase confirmation to the user and updates the purchase history database. This information is used for future recommendations.

[0237] (Example 1)

[0238] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0239] A challenge with traditional online shopping systems is that users have to go through a lot of trouble and time to obtain product information and make a purchase. Specifically, the process of identifying products of interest, checking detailed information, and completing the purchase procedure is cumbersome, resulting in a poor user experience.

[0240] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0241] In this invention, the server includes an image analysis means for analyzing visual information and recognizing items from the visual data; a recommendation generation means for generating recommendation information about the items; an eye-tracking device for tracking the user's gaze and acquiring gaze data; an action detection means for detecting the user's actions and determining their intentions; and a transaction initiation processing means for initiating a transaction based on the user's selection. This makes it possible for users to instantly identify products of interest from the video they are watching and to proceed with the purchase process intuitively.

[0242] "Visual information" refers to video and image data acquired by cameras and sensors.

[0243] "Image analysis means" refers to a part of the function that constitutes a system that recognizes objects from visual data and extracts their characteristics.

[0244] A "recommendation generation method" has the function of presenting relevant information and alternatives suitable for the user based on the recognized items.

[0245] An "eye-tracking device" is a device that detects the user's eye movements and measures and analyzes where their gaze is directed on the screen.

[0246] A "motion detection means" is a component that analyzes the user's body movements and determines their intentions.

[0247] A "transaction initiation processing mechanism" is a part of a system that initiates the purchase procedure for goods based on the user's selection.

[0248] A "gaze focus recognition means" is a function that detects when a user's gaze data is focused on a specific screen area and transmits that information to a server.

[0249] A "means of conveying intent" refers to a system element that senses the user's gestures and accurately transmits their intent to the server.

[0250] In this embodiment of the invention, a server plays a crucial role. The server continuously receives video signals from a television receiver and processes the visual information. Specifically, it recognizes objects from the visual data using an image analysis means employing a machine learning algorithm. In this process, deep learning technology and database matching are combined to identify objects and extract their features. Regarding the recognized objects, the server uses a recommendation generation means to generate and present relevant information and alternative product information suitable for the user.

[0251] The terminal acts as the interface with the user. The terminal includes an eye-tracking device that collects the user's gaze data in real time. This device can identify which part of the screen the user is focusing on. The terminal also uses a camera and motion sensors to detect user movements. Utilizing the motion detection means, when it receives a gesture from the user, such as a hand signal, it notifies the server of this intent and prepares to begin the purchase process.

[0252] When a user selects a product they are interested in within a video they are watching, the device transmits this information to the server through the user's gaze and gestures towards that product. The server then uses a transaction initiation process to quickly proceed with the purchase. Advanced image recognition technology allows users to easily select the desired product and experience the purchase process intuitively.

[0253] For example, if a user becomes interested in a cooking utensil while watching a cooking show, the device detects the user's gaze towards the utensil and checks their gesture. Based on this information, the server identifies the utensil and displays related purchase information. The user signals their intention to purchase to the server with an "OK!" gesture, and the system completes the purchase process. This series of operations allows the user to enjoy an efficient and seamless shopping experience.

[0254] An example of a prompt using a generative AI model would be an instruction such as, "Please describe a system that visually recognizes products featured on a television program and assists the user in the purchase process through their gaze and gestures."

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The server receives visual information in real time from the television receiver. It takes this visual information as input and uses image analysis to recognize objects. In this process, machine learning algorithms scan each frame of the visual data and extract the features of the objects. As output, a list of identified objects is generated. For example, cooking utensils shown in a program are identified as pots and pans.

[0258] Step 2:

[0259] The server matches the characteristics of the items recognized in step 1 against a database. This database contains detailed product information, from which the server obtains input to generate relevant recommendation information. Based on the matching results from the database, it outputs recommendation information to present to the user. Specifically, this includes the price of the cookware, the manufacturer, and information on online stores where it can be purchased.

[0260] Step 3:

[0261] The device collects user gaze data using an eye-tracking device. The eye-tracking device receives the user's eye movements as input and performs data calculations to detect which part of the screen the gaze is directed towards. The output provides the gaze position and focus. This allows for the identification of objects the user is particularly interested in.

[0262] Step 4:

[0263] The device records user movements using a camera and motion sensors. The user's movements are used as input, and data processing is performed by a motion detection system to identify specific gestures. The output then identifies clear gestures indicating purchase intent. For example, if a user makes an "OK!" gesture, this is converted into a signal that is transmitted to the server indicating their purchase intent.

[0264] Step 5:

[0265] The user confirms the items they wish to purchase through their gaze and gestures. The terminal instructs the server to initiate the transaction based on these inputs. The server retrieves this information, generates a prompt message on the screen displaying the purchase details of the items, and asks the user for confirmation. Upon user confirmation, the purchase process begins, and a secure payment process is executed.

[0266] (Application Example 1)

[0267] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0268] Currently, in many physical stores, customers need to spend time individually obtaining product information, which often makes the purchasing process cumbersome. Furthermore, manual verification and waiting times at the checkout are unavoidable when purchasing specific items. These factors cause stress for consumers and degrade the quality of the shopping experience. Therefore, innovative methods are needed to make the in-store purchasing process more efficient and intuitive.

[0269] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0270] In this invention, the server includes image recognition means for analyzing visual information and recognizing objects from the visual data, generation means for generating presentation information about the objects, and eye-tracking means for tracking the user's gaze and acquiring gaze data. This enables the user to intuitively select products in a physical store and complete the purchase with minimal effort.

[0271] "Visual information" refers to image and video data acquired using digital cameras or sensors.

[0272] "Image recognition means" refers to algorithms and devices that use computer vision technology to identify objects and scenes from visual information.

[0273] "Generation means" refers to devices or software that perform a process of generating relevant information and recommendations based on recognized objects.

[0274] "Eye-tracking means" refers to technologies and devices that measure the direction of a user's gaze and acquire that data.

[0275] "Gesture recognition means" refers to technologies and devices that use sensors or cameras to detect the movements of a user's hands or body and interpret them as specific intentions or commands.

[0276] A "transaction initiation mechanism" is a system that automatically or semi-automatically initiates the purchase process based on the selected object.

[0277] "Augmented reality display means" refers to devices and technologies for overlaying and displaying digital information onto the real world.

[0278] To realize this application, the system primarily uses a server, terminals, eye-tracking devices, and gesture recognition technology. The server first acquires visual information through a digital camera, uses image recognition to identify products, and generates presentation information about those products. Machine learning frameworks such as TensorFlow and PyTorch are used for image recognition. The server then performs object identification and information generation in physical stores.

[0279] Next, the device tracks the user's gaze. Using a Tobii eye-tracking device, it collects gaze data in real time. This data is sent to a server for processing to determine which objects the user is interested in. If the gaze remains on a specific object for a certain period of time, information about that object is presented by the augmented reality display system.

[0280] Furthermore, the server uses gesture recognition to detect the user's hand and body movements. Using OpenCV and MediaPipe, it interprets the user's gestures and determines their purchase intent. For example, if an "OK!" gesture is detected, the transaction process to purchase that item is initiated.

[0281] For example, when a user finds a smart toy in a physical store and the gesture recognition means confirms the intention to purchase while the user is looking at the toy, the transaction process immediately proceeds, improving the user experience. Throughout this entire process, augmented reality information is presented via a device such as an HMD, intuitively providing the user with product information and purchase options.

[0282] Examples of the prompt text for the generative AI model include the following:

[0283] [[ID=⑧]]"Propose a prototype of a system that recognizes products based on image data, identifies the user's interests using gaze tracking information, and determines the purchase of a specific product with a gesture."

[0284] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0285] Step 1:

[0286] The server receives visual information from a digital camera transmitted from the terminal. Using this visual information as input, it utilizes image recognition means and uses a generative AI model to identify the product and analyze its features. Through data processing, detailed information and related data of the identified product are output.

[0287] Step 2:

[0288] The terminal acquires the user's gaze data in real time using a Tobii-made gaze tracking device. This gaze information is transmitted to the server, and the server performs data calculations to identify the products that the user is interested in based on the gaze information. When the gaze focuses on a specific object, that information is output and the details of the corresponding product are displayed.

[0289] Step 3:

[0290] The user makes a gesture indicating their intention to purchase after reviewing the product. The terminal recognizes this gesture using OpenCV or MediaPipe. This gesture data is sent to the server as input, and the server processes the data to determine the intention. If the judgment results in a gesture that is interpreted as an intention to purchase, the purchase process is initiated.

[0291] Step 4:

[0292] The server executes the purchase process. Using the transaction initiation method, it generates a purchase screen based on the previously obtained product information and presents it to the user via the terminal. After final confirmation, the server securely executes the payment process and completes the purchase. As output, a transaction completion notification is sent to the user.

[0293] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0294] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing the user's actions and emotions, and an eye-tracking device and an emotion recognition engine.

[0295] First, the server receives video data from television programs in real time and uses image processing algorithms to identify products. The server generates information about the identified products and related recommendation information. The recommendation system suggests products that are highly relevant to the user based on the user's past viewing and purchase history, as well as their emotional state.

[0296] The device collects user gaze data using an eye-tracking device. The eye-tracking means identifies which part of the screen the user is fixating on and sends that information to a server. Furthermore, the device is equipped with an emotion recognition engine that obtains emotion information by analyzing changes in the user's facial expressions. This emotion information is taken into consideration by the recommendation system and used to improve the accuracy of product recommendations.

[0297] Furthermore, the device has a motion recognition function that identifies gestures made by the user. The motion recognition means recognizes the "OK!" gesture and sends the intention to the server as a purchase intent.

[0298] Once the user has finished selecting products, the terminal initiates the purchase process through the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After confirmation, the server performs a secure payment process. Upon completion of the transaction, the server sends the user a purchase completion notification, records the purchase history and sentiment information in a database, and uses it for future recommendations.

[0299] As a concrete example, consider a scenario where a user becomes interested in an outfit that appears in a movie. The server identifies the outfit in the video and provides relevant information. In addition, an emotion recognition engine analyzes the user's facial expressions, and if it detects positive emotions, it uses that information to provide even more appropriate product recommendations. This invention allows users to have a more personalized shopping experience.

[0300] The following describes the processing flow.

[0301] Step 1:

[0302] The server receives video data from television programs in real time and uses machine learning algorithms to identify products within the video. Once a product is identified, its detailed information is retrieved from a database.

[0303] Step 2:

[0304] The server creates recommendation information suitable for the user by leveraging the generative AI from the acquired product information. Specifically, it lists relevant products considering the user's purchase history, viewing history, and real-time sentiment information.

[0305] Step 3:

[0306] The terminal uses a gaze tracking device to receive the user's gaze data and identify where the user is looking on the screen. The gaze information is immediately sent to the server.

[0307] Step 4:

[0308] The terminal analyzes the user's facial expressions in real time through a face recognition camera and extracts sentiment information using a sentiment recognition engine. This sentiment information quantifies the user's current mood and level of interest.

[0309] Step 5:

[0310] The server integrates the gaze information and sentiment information sent from the terminal to further optimize the recommendation information and provides the result to the user. This enables personalized recommendations that focus on products towards which the user's gaze is directed or products that show positive sentiment.

[0311] Step 6:

[0312] The terminal uses a sensor to detect the gestures made by the user's hand and recognizes the "OK!" gesture using a motion recognition algorithm. When this operation is recognized, the selected product is confirmed.

[0313] Step 7:

[0314] The server initiates the transaction start step and displays a purchase confirmation dialog on the screen. The user can perform the final confirmation of the purchase here.

[0315] Step 8:

[0316] Once the user finalizes the purchase, the server proceeds with the payment process, ensuring that the transaction is securely verified. After the transaction is complete, the server sends a purchase completion notification and updates the user's purchase history and associated sentiment information.

[0317] (Example 2)

[0318] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0319] Traditional online shopping systems have limited the user experience due to insufficient personalized product recommendations based on user interests and emotions. Furthermore, a lack of intuitive controls for users to smoothly select and purchase products remains a challenge.

[0320] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0321] In this invention, the server includes image processing means for analyzing visual information and recognizing products from the visual data, information generation means for generating recommendation information about products based on past history and emotional state, and gaze detection means for tracking the user's gaze and acquiring gaze information. This enables personalized product recommendations that are tailored to the user's interests and emotions.

[0322] "Analyzing visual information" refers to the process of detecting specific objects or features from image or video data and performing data processing to identify them.

[0323] "Recognizing a product" means analyzing the characteristics of a product and comparing them with information in a database to identify its specific product name and attributes.

[0324] "Information generation means" refers to a device or program that has the function of creating appropriate recommendation information based on past historical data and the user's current emotional state.

[0325] "Eye-gaze detection means" refers to a device or program that analyzes the movement of the user's eyeballs and the point of fixation to determine where they are looking.

[0326] An "emotion analysis tool" is a device or program that analyzes the user's facial expressions and infers the type and intensity of emotions from them.

[0327] "Motion detection means" refers to a device or program that analyzes the user's body movements and gestures to determine a specific intention or command.

[0328] "Means of performing a procedure" refers to a device or program that controls a series of actions necessary to initiate a transaction and executes payment processing and verification steps.

[0329] To implement this invention, a system including a server, terminals, and various devices is constructed. The server receives video data in real time via a television receiver and identifies products in the visual data using an image processing library. This process uses OpenCV, a common image recognition library, to extract features of products shown in the video and match them with a database.

[0330] Next, the device uses an eye-tracking device to track the user's gaze. This device utilizes a common eye-tracking technology to identify where the user is looking on the screen. Based on this result, the user's interests are measured.

[0331] Furthermore, the device is equipped with an emotion analysis engine that monitors the user's facial expressions via a camera. Using general emotion recognition software, it analyzes changes in the user's facial expressions and determines their emotional state. This information is used by the server to improve the accuracy of product recommendations.

[0332] The terminal also has motion detection capabilities, recognizing the user's hand gestures with its camera. Motion recognition uses a machine learning model to interpret the gestures; for example, an "OK!" command is interpreted as an intention to purchase. This information is transmitted to a server and used as a means to initiate a transaction.

[0333] For example, if a user becomes interested in an outfit while watching a movie, the server analyzes the video of that scene and extracts detailed information about the outfit. The emotion recognition engine reads the user's facial expressions, and if it detects a positive emotion, it suggests related products based on that.

[0334] An example of a prompt to input into a generative AI model would be: "Please provide detailed information about the costumes the user showed interest in while watching the movie. Based on the user's emotional state, please also recommend related products."

[0335] In this way, users can receive personalized product recommendations based on their viewing experience and enjoy a more fulfilling shopping experience.

[0336] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0337] Step 1:

[0338] The server receives video data in real time from the television receiver. Using this video data as input, it identifies products using an image processing algorithm. Specifically, it uses OpenCV to convert the images in the video to grayscale and performs edge detection to recognize the contours of the products. This data processing outputs characteristic data of the identified products.

[0339] Step 2:

[0340] The device collects user gaze information using an eye-tracking device. This gaze data is used as input to identify where the user is fixating on the screen. Specifically, an eye-tracking algorithm analyzes the user's eye movements and outputs the coordinates of the point of fixation. This output is sent to the server as information indicating the user's area of ​​interest.

[0341] Step 3:

[0342] The device uses an emotion recognition engine to analyze the user's facial expressions and obtain emotional information. This facial data is then used as input to estimate the emotional category (e.g., joy, surprise) using a deep learning model. The model extracts facial features and outputs an emotional label based on them. This emotional information is also sent to the server and used as a basis for product recommendation decisions.

[0343] Step 4:

[0344] The server uses a generative AI model to recommend products based on product identification results, user gaze data, and sentiment information. Using this information as input, a machine learning model, which also considers historical data, generates an optimal product list. As a result of this data processing, product recommendations are output to the user.

[0345] Step 5:

[0346] The terminal uses motion detection to recognize the user's gestures. A motion analysis algorithm takes the gesture video as input, identifies gestures such as "OK!", and outputs their intent to the server. This confirms the user's purchase intention.

[0347] Step 6:

[0348] The server initiates a transaction based on user gesture recognition. Using product information and screen display data for purchase confirmation as input, it calls the payment processing system to securely complete the transaction. As an output of this process, a purchase completion notification is sent to the user, and the purchase history is recorded in the database.

[0349] (Application Example 2)

[0350] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0351] Traditional e-commerce systems present challenges such as a cumbersome process from product selection to purchase, making it difficult to provide personalized recommendations. Furthermore, mechanical recommendations often fail to consider the user's emotional state, hindering the improvement of the user experience. The lack of a payment process that quickly and naturally reflects purchase intent is also a significant issue.

[0352] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0353] In this invention, the server includes image recognition means for analyzing visual information and recognizing products from visual data, recommendation means for generating recommendation information about products, eye-tracking means for tracking the user's gaze and acquiring eye-tracking information, emotion recognition means for analyzing the user's facial expressions and recognizing emotions, and action recognition means for recognizing the user's actions and determining their intentions. This enables highly accurate product recommendations based on the user's interests and emotional state, and a smooth purchase process through intuitive actions.

[0354] "Image recognition means" refers to a technology or device for analyzing visual information to recognize products from visual data.

[0355] "Recommendation methods" refer to technologies or devices for generating highly relevant information about a product and suggesting it to the user.

[0356] "Eye-tracking means" refers to a technology or device that tracks the movement of a user's eyes and identifies which part they are fixating on.

[0357] "Emotion recognition means" refers to technology or devices for identifying an emotional state by analyzing the user's facial expressions.

[0358] "Motion recognition means" refers to a technology or device for analyzing the user's body movements and determining the user's intentions from those movements.

[0359] "Transaction initiation means" refers to technology or equipment for initiating a transaction, such as a purchase, based on the user's choice.

[0360] The system for implementing this invention provides users with a personalized purchasing experience by utilizing various devices and software. The system mainly consists of a server, terminals, eye-tracking devices, and an emotion recognition engine.

[0361] The server is the central hub for calculations and processing, using image recognition algorithms to analyze product information from video footage. The server also generates relevant recommendations based on this analysis. These recommendations are customized based on the user's viewing history, purchase history, and even their emotional state, which is captured in real time.

[0362] The user's device uses an eye-tracking device to collect eye-tracking information and accurately measure the user's eye movements. This data is used to identify which part of the screen the user is fixating on, and the identified eye-tracking information is sent to a server. The device also has an emotion recognition engine that analyzes the user's facial expressions in real time, allowing it to understand the user's emotional state.

[0363] The system combines user gaze and emotion data to improve the accuracy of product recommendations. Furthermore, it can initiate a transaction by recognizing specific gestures made by the user (e.g., a thumbs-up "OK!" gesture) and interpreting them as a purchase intention. The server performs secure payment processing and notifies the user when the transaction is complete. The recorded purchase history and emotion information are stored in a database and used for future recommendations.

[0364] For example, when a user becomes interested in an outfit they see while watching a movie or TV show, the eye-tracking device and emotion recognition engine can work together to determine whether the outfit is being viewed favorably. By integrating eye-tracking and emotion information in this way, the system can recommend the most suitable product for the user and facilitate a smooth purchase process.

[0365] An example of a prompt message is: "The user found a product they liked in the video they were watching. We want to confirm their interest in the product using eye-tracking and simplify the purchase process."

[0366] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0367] Step 1:

[0368] The server receives video data from television programs in real time and identifies products using an image recognition algorithm. The input is video data, and the output is information about the identified products. Products are identified by analyzing the pixels of the image data and extracting patterns and shapes characteristic of the product.

[0369] Step 2:

[0370] The server generates recommendation information related to the identified product. Inputs include past viewing and purchase history, as well as real-time sentiment information. The output is personalized recommendations used to present the user with highly relevant products. Recommendations are prioritized based on relevance, matching historical and sentiment data.

[0371] Step 3:

[0372] The device uses an eye-tracking device to collect user gaze data. The input is the user's visual gaze information, and the output is the specific location on the screen where the gaze is directed. The gaze position is determined by analyzing eye movements in real time via the camera and calculating the point of fixation.

[0373] Step 4:

[0374] The device uses an emotion recognition engine to acquire emotional information from the user's facial expressions. The input is image data of the user's face, and the output is the detected emotional state. Through image analysis, features related to facial expressions are extracted, and the emotional state is identified. This emotional information is used by recommendation systems to improve the accuracy of product recommendations.

[0375] Step 5:

[0376] The device recognizes the user's gestures to determine their purchase intent. The input is the user's gesture actions, and the output is confirmation information regarding the user's intention. A motion recognition algorithm is used to analyze the state of the gestures and identify their intent.

[0377] Step 6:

[0378] The server initiates the purchase process through the transaction initiation method and performs secure payment processing. Input is user verification information, and output is a transaction completion notification. Payment processing utilizes a payment API to integrate with external payment systems, ensuring a secure transaction.

[0379] 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.

[0380] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0381] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0382] [Third Embodiment]

[0383] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0384] 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.

[0385] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0386] 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.

[0387] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0388] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0389] 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.

[0390] 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.

[0391] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0392] The 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.

[0393] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0394] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0395] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing user actions, and an eye-tracking device.

[0396] First, the server continuously receives video footage from television programs and recognizes products from the visual information. The image recognition system uses a machine learning model to detect products and analyze their features. The detected products are compared with a database to generate detailed product information and recommendation information. The recommendation system presents relevant products based on the user's past purchase history and preferences.

[0397] Next, the terminal collects gaze data from an eye-tracking device to track the user's gaze. The eye-tracking means recognizes when the user's gaze is focused on a specific part of the screen and sends that information to a server.

[0398] Furthermore, the device uses cameras and sensors to detect the user's hand gestures. The motion recognition system identifies specific gestures (for example, the "OK!" gesture) and transmits them to the server as an intention to purchase.

[0399] Once the user has finished selecting items, the terminal initiates the purchase process using the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After the user confirms, the server performs a secure payment process and completes the transaction. The server then sends the user a purchase completion notification and updates the purchase history.

[0400] As a concrete example, suppose a user is watching a cooking show and becomes interested in a pot used in it. The server analyzes the video data, identifies the pot, and sends related information to the user's terminal. The user then looks at the pot and makes an "OK!" gesture to begin the purchase process, easily completing the purchase. In this way, the system of the present invention makes user interaction almost unconscious, significantly improving the shopping experience.

[0401] The following describes the processing flow.

[0402] Step 1:

[0403] The server receives video data from television programs in real time and uses image processing algorithms to identify products. Once a product is identified, the information is matched against a database to retrieve relevant product identification information and detailed information.

[0404] Step 2:

[0405] The server uses AI generation based on acquired product information to create product recommendations tailored to the user. Based on past viewing and purchase history, it scores and prioritizes highly relevant products for presentation.

[0406] Step 3:

[0407] The device receives data from an eye-tracking device to track the user's gaze. The eye-tracking algorithm analyzes the position of the gaze and identifies which part of the image the user is focusing on.

[0408] Step 4:

[0409] The device transmits gaze information about the product area that it has visually identified to the server. This includes information such as how long the user's gaze remained in a particular location.

[0410] Step 5:

[0411] The device detects user gestures using high-sensitivity sensors and cameras. When the motion recognition algorithm detects an "OK!" gesture, it interprets the user's intention as a purchase and notifies the server.

[0412] Step 6:

[0413] Once a user indicates their intention to purchase, the server sends detailed information about the potential purchase items and a purchase confirmation screen to the user's device. Here, the user can make a final confirmation of their purchase.

[0414] Step 7:

[0415] After the user makes a final confirmation of their purchase, the server initiates payment processing via the payment gateway. The user's secure payment information is used during this process.

[0416] Step 8:

[0417] Once a transaction is complete, the server sends a purchase confirmation to the user and updates the purchase history database. This information is used for future recommendations.

[0418] (Example 1)

[0419] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0420] A challenge with traditional online shopping systems is that users have to go through a lot of trouble and time to obtain product information and make a purchase. Specifically, the process of identifying products of interest, checking detailed information, and completing the purchase procedure is cumbersome, resulting in a poor user experience.

[0421] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0422] In this invention, the server includes an image analysis means for analyzing visual information and recognizing items from the visual data; a recommendation generation means for generating recommendation information about the items; an eye-tracking device for tracking the user's gaze and acquiring gaze data; an action detection means for detecting the user's actions and determining their intentions; and a transaction initiation processing means for initiating a transaction based on the user's selection. This makes it possible for users to instantly identify products of interest from the video they are watching and to proceed with the purchase process intuitively.

[0423] "Visual information" refers to video and image data acquired by cameras and sensors.

[0424] "Image analysis means" refers to a part of the function that constitutes a system that recognizes objects from visual data and extracts their characteristics.

[0425] A "recommendation generation method" has the function of presenting relevant information and alternatives suitable for the user based on the recognized items.

[0426] An "eye-tracking device" is a device that detects the user's eye movements and measures and analyzes where their gaze is directed on the screen.

[0427] A "motion detection means" is a component that analyzes the user's body movements and determines their intentions.

[0428] A "transaction initiation processing mechanism" is a part of a system that initiates the purchase procedure for goods based on the user's selection.

[0429] A "gaze focus recognition means" is a function that detects when a user's gaze data is focused on a specific screen area and transmits that information to a server.

[0430] A "means of conveying intent" refers to a system element that senses the user's gestures and accurately transmits their intent to the server.

[0431] In this embodiment of the invention, a server plays a crucial role. The server continuously receives video signals from a television receiver and processes the visual information. Specifically, it recognizes objects from the visual data using an image analysis means employing a machine learning algorithm. In this process, deep learning technology and database matching are combined to identify objects and extract their features. Regarding the recognized objects, the server uses a recommendation generation means to generate and present relevant information and alternative product information suitable for the user.

[0432] The terminal acts as the interface with the user. The terminal includes an eye-tracking device that collects the user's gaze data in real time. This device can identify which part of the screen the user is focusing on. The terminal also uses a camera and motion sensors to detect user movements. Utilizing the motion detection means, when it receives a gesture from the user, such as a hand signal, it notifies the server of this intent and prepares to begin the purchase process.

[0433] When a user selects a product they are interested in within a video they are watching, the device transmits this information to the server through the user's gaze and gestures towards that product. The server then uses a transaction initiation process to quickly proceed with the purchase. Advanced image recognition technology allows users to easily select the desired product and experience the purchase process intuitively.

[0434] For example, if a user becomes interested in a cooking utensil while watching a cooking show, the device detects the user's gaze towards the utensil and checks their gesture. Based on this information, the server identifies the utensil and displays related purchase information. The user signals their intention to purchase to the server with an "OK!" gesture, and the system completes the purchase process. This series of operations allows the user to enjoy an efficient and seamless shopping experience.

[0435] An example of a prompt using a generative AI model would be an instruction such as, "Please describe a system that visually recognizes products featured on a television program and assists the user in the purchase process through their gaze and gestures."

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The server receives visual information in real time from the television receiver. It takes this visual information as input and uses image analysis to recognize objects. In this process, machine learning algorithms scan each frame of the visual data and extract the features of the objects. As output, a list of identified objects is generated. For example, cooking utensils shown in a program are identified as pots and pans.

[0439] Step 2:

[0440] The server matches the characteristics of the items recognized in step 1 against a database. This database contains detailed product information, from which the server obtains input to generate relevant recommendation information. Based on the matching results from the database, it outputs recommendation information to present to the user. Specifically, this includes the price of the cookware, the manufacturer, and information on online stores where it can be purchased.

[0441] Step 3:

[0442] The device collects user gaze data using an eye-tracking device. The eye-tracking device receives the user's eye movements as input and performs data calculations to detect which part of the screen the gaze is directed towards. The output provides the gaze position and focus. This allows for the identification of objects the user is particularly interested in.

[0443] Step 4:

[0444] The device records user movements using a camera and motion sensors. The user's movements are used as input, and data processing is performed by a motion detection system to identify specific gestures. The output then identifies clear gestures indicating purchase intent. For example, if a user makes an "OK!" gesture, this is converted into a signal that is transmitted to the server indicating their purchase intent.

[0445] Step 5:

[0446] The user confirms the items they wish to purchase through their gaze and gestures. The terminal instructs the server to initiate the transaction based on these inputs. The server retrieves this information, generates a prompt message on the screen displaying the purchase details of the items, and asks the user for confirmation. Upon user confirmation, the purchase process begins, and a secure payment process is executed.

[0447] (Application Example 1)

[0448] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0449] Currently, in many physical stores, customers need to spend time individually obtaining product information, which often makes the purchasing process cumbersome. Furthermore, manual verification and waiting times at the checkout are unavoidable when purchasing specific items. These factors cause stress for consumers and degrade the quality of the shopping experience. Therefore, innovative methods are needed to make the in-store purchasing process more efficient and intuitive.

[0450] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0451] In this invention, the server includes image recognition means for analyzing visual information and recognizing objects from the visual data, generation means for generating presentation information about the objects, and eye-tracking means for tracking the user's gaze and acquiring gaze data. This enables the user to intuitively select products in a physical store and complete the purchase with minimal effort.

[0452] "Visual information" refers to image and video data acquired using digital cameras or sensors.

[0453] "Image recognition means" refers to algorithms and devices that use computer vision technology to identify objects and scenes from visual information.

[0454] "Generation means" refers to devices or software that perform a process of generating relevant information and recommendations based on recognized objects.

[0455] "Eye-tracking means" refers to technologies and devices that measure the direction of a user's gaze and acquire that data.

[0456] "Gesture recognition means" refers to technologies and devices that use sensors or cameras to detect the movements of a user's hands or body and interpret them as specific intentions or commands.

[0457] A "transaction initiation mechanism" is a system that automatically or semi-automatically initiates the purchase process based on the selected object.

[0458] "Augmented reality display means" refers to devices and technologies for overlaying and displaying digital information onto the real world.

[0459] To realize this application, the system primarily uses a server, terminals, eye-tracking devices, and gesture recognition technology. The server first acquires visual information through a digital camera, uses image recognition to identify products, and generates presentation information about those products. Machine learning frameworks such as TensorFlow and PyTorch are used for image recognition. The server then performs object identification and information generation in physical stores.

[0460] Next, the device tracks the user's gaze. Using a Tobii eye-tracking device, it collects gaze data in real time. This data is sent to a server for processing to determine which objects the user is interested in. If the gaze remains on a specific object for a certain period of time, information about that object is presented by the augmented reality display system.

[0461] Furthermore, the server uses gesture recognition to detect the user's hand and body movements. Using OpenCV and MediaPipe, it interprets the user's gestures and determines their purchase intent. For example, if an "OK!" gesture is detected, the transaction process to purchase that item is initiated.

[0462] To give a concrete example, if a user finds a smart toy in a physical store and their intention to purchase is confirmed by gesture recognition while they are looking at the toy, the transaction process will proceed immediately, improving the user experience. Throughout this entire process, augmented reality information is presented via devices such as HMDs, providing the user with intuitive product information and purchase options.

[0463] Examples of prompt statements for generative AI models include the following:

[0464] "Propose a prototype of a system that recognizes products based on image data, identifies user interests using eye-tracking information, and allows users to decide on the purchase of a specific product through gestures."

[0465] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0466] Step 1:

[0467] The server receives visual information from a digital camera transmitted from a terminal. Using this visual information as input, it utilizes image recognition and a generative AI model to identify products and analyze their characteristics. After data processing, detailed information and related data of the identified products are output.

[0468] Step 2:

[0469] The device acquires the user's gaze data in real time using a Tobii eye-tracking device. This gaze information is sent to a server, which uses the gaze information to perform data calculations to identify products of interest to the user. When the gaze is focused on a specific object, that information is output, and details of the corresponding product are displayed.

[0470] Step 3:

[0471] The user makes a gesture indicating their intention to purchase after reviewing the product. The terminal recognizes this gesture using OpenCV or MediaPipe. This gesture data is sent to the server as input, and the server processes the data to determine the intention. If the judgment results in a gesture that is interpreted as an intention to purchase, the purchase process is initiated.

[0472] Step 4:

[0473] The server executes the purchase process. Using the transaction initiation method, it generates a purchase screen based on the previously obtained product information and presents it to the user via the terminal. After final confirmation, the server securely executes the payment process and completes the purchase. As output, a transaction completion notification is sent to the user.

[0474] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0475] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing the user's actions and emotions, and an eye-tracking device and an emotion recognition engine.

[0476] First, the server receives video data from television programs in real time and uses image processing algorithms to identify products. The server generates information about the identified products and related recommendation information. The recommendation system suggests products that are highly relevant to the user based on the user's past viewing and purchase history, as well as their emotional state.

[0477] The device collects user gaze data using an eye-tracking device. The eye-tracking means identifies which part of the screen the user is fixating on and sends that information to a server. Furthermore, the device is equipped with an emotion recognition engine that obtains emotion information by analyzing changes in the user's facial expressions. This emotion information is taken into consideration by the recommendation system and used to improve the accuracy of product recommendations.

[0478] Furthermore, the device has a motion recognition function that identifies gestures made by the user. The motion recognition means recognizes the "OK!" gesture and sends the intention to the server as a purchase intent.

[0479] Once the user has finished selecting products, the terminal initiates the purchase process through the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After confirmation, the server performs a secure payment process. Upon completion of the transaction, the server sends the user a purchase completion notification, records the purchase history and sentiment information in a database, and uses it for future recommendations.

[0480] As a concrete example, consider a scenario where a user becomes interested in an outfit that appears in a movie. The server identifies the outfit in the video and provides relevant information. In addition, an emotion recognition engine analyzes the user's facial expressions, and if it detects positive emotions, it uses that information to provide even more appropriate product recommendations. This invention allows users to have a more personalized shopping experience.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The server receives video data from television programs in real time and uses machine learning algorithms to identify products within the video. Once a product is identified, its detailed information is retrieved from a database.

[0484] Step 2:

[0485] The server uses AI to generate personalized recommendations based on the acquired product information. Specifically, it lists relevant products by taking into account the user's purchase history, viewing history, and real-time sentiment information.

[0486] Step 3:

[0487] The device uses an eye-tracking device to receive the user's gaze data and identify where on the screen the user is fixating. The gaze information is immediately sent to the server.

[0488] Step 4:

[0489] The device analyzes the user's facial expressions in real time via a facial recognition camera and extracts emotional information using an emotion recognition engine. This emotional information quantifies the user's current mood and level of interest.

[0490] Step 5:

[0491] The server integrates gaze and emotion information transmitted from the device to further optimize recommendations and provides the results to the user. This results in personalized recommendations that focus on products the user has looked at or products that have elicited positive emotions.

[0492] Step 6:

[0493] The device uses sensors to detect the user's hand gestures and a motion recognition algorithm to recognize the "OK!" gesture. Once this action is recognized, the selected product is confirmed.

[0494] Step 7:

[0495] The server initiates the transaction start step and displays a purchase confirmation dialog on the screen. The user can then make a final confirmation of the purchase.

[0496] Step 8:

[0497] Once the user finalizes the purchase, the server proceeds with the payment process, ensuring that the transaction is securely verified. After the transaction is complete, the server sends a purchase completion notification and updates the user's purchase history and associated sentiment information.

[0498] (Example 2)

[0499] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] Traditional online shopping systems have limited the user experience due to insufficient personalized product recommendations based on user interests and emotions. Furthermore, a lack of intuitive controls for users to smoothly select and purchase products remains a challenge.

[0501] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0502] In this invention, the server includes image processing means for analyzing visual information and recognizing products from the visual data, information generation means for generating recommendation information about products based on past history and emotional state, and gaze detection means for tracking the user's gaze and acquiring gaze information. This enables personalized product recommendations that are tailored to the user's interests and emotions.

[0503] "Analyzing visual information" refers to the process of detecting specific objects or features from image or video data and performing data processing to identify them.

[0504] "Recognizing a product" means analyzing the characteristics of a product and comparing them with information in a database to identify its specific product name and attributes.

[0505] "Information generation means" refers to a device or program that has the function of creating appropriate recommendation information based on past historical data and the user's current emotional state.

[0506] "Eye-gaze detection means" refers to a device or program that analyzes the movement of the user's eyeballs and the point of fixation to determine where they are looking.

[0507] An "emotion analysis tool" is a device or program that analyzes the user's facial expressions and infers the type and intensity of emotions from them.

[0508] "Motion detection means" refers to a device or program that analyzes the user's body movements and gestures to determine a specific intention or command.

[0509] "Means of performing a procedure" refers to a device or program that controls a series of actions necessary to initiate a transaction and executes payment processing and verification steps.

[0510] To implement this invention, a system including a server, terminals, and various devices is constructed. The server receives video data in real time via a television receiver and identifies products in the visual data using an image processing library. This process uses OpenCV, a common image recognition library, to extract features of products shown in the video and match them with a database.

[0511] Next, the device uses an eye-tracking device to track the user's gaze. This device utilizes a common eye-tracking technology to identify where the user is looking on the screen. Based on this result, the user's interests are measured.

[0512] Furthermore, the device is equipped with an emotion analysis engine that monitors the user's facial expressions via a camera. Using general emotion recognition software, it analyzes changes in the user's facial expressions and determines their emotional state. This information is used by the server to improve the accuracy of product recommendations.

[0513] The terminal also has motion detection capabilities, recognizing the user's hand gestures with its camera. Motion recognition uses a machine learning model to interpret the gestures; for example, an "OK!" command is interpreted as an intention to purchase. This information is transmitted to a server and used as a means to initiate a transaction.

[0514] For example, if a user becomes interested in an outfit while watching a movie, the server analyzes the video of that scene and extracts detailed information about the outfit. The emotion recognition engine reads the user's facial expressions, and if it detects a positive emotion, it suggests related products based on that.

[0515] An example of a prompt to input into a generative AI model would be: "Please provide detailed information about the costumes the user showed interest in while watching the movie. Based on the user's emotional state, please also recommend related products."

[0516] In this way, users can receive personalized product recommendations based on their viewing experience and enjoy a more fulfilling shopping experience.

[0517] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0518] Step 1:

[0519] The server receives video data in real time from the television receiver. Using this video data as input, it identifies products using an image processing algorithm. Specifically, it uses OpenCV to convert the images in the video to grayscale and performs edge detection to recognize the contours of the products. This data processing outputs characteristic data of the identified products.

[0520] Step 2:

[0521] The device collects user gaze information using an eye-tracking device. This gaze data is used as input to identify where the user is fixating on the screen. Specifically, an eye-tracking algorithm analyzes the user's eye movements and outputs the coordinates of the point of fixation. This output is sent to the server as information indicating the user's area of ​​interest.

[0522] Step 3:

[0523] The device uses an emotion recognition engine to analyze the user's facial expressions and obtain emotional information. This facial data is then used as input to estimate the emotional category (e.g., joy, surprise) using a deep learning model. The model extracts facial features and outputs an emotional label based on them. This emotional information is also sent to the server and used as a basis for product recommendation decisions.

[0524] Step 4:

[0525] The server uses a generative AI model to recommend products based on product identification results, user gaze data, and sentiment information. Using this information as input, a machine learning model, which also considers historical data, generates an optimal product list. As a result of this data processing, product recommendations are output to the user.

[0526] Step 5:

[0527] The terminal uses motion detection to recognize the user's gestures. A motion analysis algorithm takes the gesture video as input, identifies gestures such as "OK!", and outputs their intent to the server. This confirms the user's purchase intention.

[0528] Step 6:

[0529] The server initiates a transaction based on user gesture recognition. Using product information and screen display data for purchase confirmation as input, it calls the payment processing system to securely complete the transaction. As an output of this process, a purchase completion notification is sent to the user, and the purchase history is recorded in the database.

[0530] (Application Example 2)

[0531] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0532] Traditional e-commerce systems present challenges such as a cumbersome process from product selection to purchase, making it difficult to provide personalized recommendations. Furthermore, mechanical recommendations often fail to consider the user's emotional state, hindering the improvement of the user experience. The lack of a payment process that quickly and naturally reflects purchase intent is also a significant issue.

[0533] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0534] In this invention, the server includes image recognition means for analyzing visual information and recognizing products from visual data, recommendation means for generating recommendation information about products, eye-tracking means for tracking the user's gaze and acquiring eye-tracking information, emotion recognition means for analyzing the user's facial expressions and recognizing emotions, and action recognition means for recognizing the user's actions and determining their intentions. This enables highly accurate product recommendations based on the user's interests and emotional state, and a smooth purchase process through intuitive actions.

[0535] "Image recognition means" refers to a technology or device for analyzing visual information to recognize products from visual data.

[0536] "Recommendation methods" refer to technologies or devices for generating highly relevant information about a product and suggesting it to the user.

[0537] "Eye-tracking means" refers to a technology or device that tracks the movement of a user's eyes and identifies which part they are fixating on.

[0538] "Emotion recognition means" refers to technology or devices for identifying an emotional state by analyzing the user's facial expressions.

[0539] "Motion recognition means" refers to a technology or device for analyzing the user's body movements and determining the user's intentions from those movements.

[0540] "Transaction initiation means" refers to technology or equipment for initiating a transaction, such as a purchase, based on the user's choice.

[0541] The system for implementing this invention provides users with a personalized purchasing experience by utilizing various devices and software. The system mainly consists of a server, terminals, eye-tracking devices, and an emotion recognition engine.

[0542] The server is the central hub for calculations and processing, using image recognition algorithms to analyze product information from video footage. The server also generates relevant recommendations based on this analysis. These recommendations are customized based on the user's viewing history, purchase history, and even their emotional state, which is captured in real time.

[0543] The user's device uses an eye-tracking device to collect eye-tracking information and accurately measure the user's eye movements. This data is used to identify which part of the screen the user is fixating on, and the identified eye-tracking information is sent to a server. The device also has an emotion recognition engine that analyzes the user's facial expressions in real time, allowing it to understand the user's emotional state.

[0544] The system combines user gaze and emotion data to improve the accuracy of product recommendations. Furthermore, it can initiate a transaction by recognizing specific gestures made by the user (e.g., a thumbs-up "OK!" gesture) and interpreting them as a purchase intention. The server performs secure payment processing and notifies the user when the transaction is complete. The recorded purchase history and emotion information are stored in a database and used for future recommendations.

[0545] For example, when a user becomes interested in an outfit they see while watching a movie or TV show, the eye-tracking device and emotion recognition engine can work together to determine whether the outfit is being viewed favorably. By integrating eye-tracking and emotion information in this way, the system can recommend the most suitable product for the user and facilitate a smooth purchase process.

[0546] An example of a prompt message is: "The user found a product they liked in the video they were watching. We want to confirm their interest in the product using eye-tracking and simplify the purchase process."

[0547] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0548] Step 1:

[0549] The server receives video data from television programs in real time and identifies products using an image recognition algorithm. The input is video data, and the output is information about the identified products. Products are identified by analyzing the pixels of the image data and extracting patterns and shapes characteristic of the product.

[0550] Step 2:

[0551] The server generates recommendation information related to the identified product. Inputs include past viewing and purchase history, as well as real-time sentiment information. The output is personalized recommendations used to present the user with highly relevant products. Recommendations are prioritized based on relevance, matching historical and sentiment data.

[0552] Step 3:

[0553] The device uses an eye-tracking device to collect user gaze data. The input is the user's visual gaze information, and the output is the specific location on the screen where the gaze is directed. The gaze position is determined by analyzing eye movements in real time via the camera and calculating the point of fixation.

[0554] Step 4:

[0555] The device uses an emotion recognition engine to acquire emotional information from the user's facial expressions. The input is image data of the user's face, and the output is the detected emotional state. Through image analysis, features related to facial expressions are extracted, and the emotional state is identified. This emotional information is used by recommendation systems to improve the accuracy of product recommendations.

[0556] Step 5:

[0557] The device recognizes the user's gestures to determine their purchase intent. The input is the user's gesture actions, and the output is confirmation information regarding the user's intention. A motion recognition algorithm is used to analyze the state of the gestures and identify their intent.

[0558] Step 6:

[0559] The server initiates the purchase process through the transaction initiation method and performs secure payment processing. Input is user verification information, and output is a transaction completion notification. Payment processing utilizes a payment API to integrate with external payment systems, ensuring a secure transaction.

[0560] 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.

[0561] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0562] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0563] [Fourth Embodiment]

[0564] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0565] 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.

[0566] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0567] 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.

[0568] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0569] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0570] 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.

[0571] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0572] 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.

[0573] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0574] The 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.

[0575] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0576] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0577] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing user actions, and an eye-tracking device.

[0578] First, the server continuously receives video footage from television programs and recognizes products from the visual information. The image recognition system uses a machine learning model to detect products and analyze their features. The detected products are compared with a database to generate detailed product information and recommendation information. The recommendation system presents relevant products based on the user's past purchase history and preferences.

[0579] Next, the terminal collects gaze data from an eye-tracking device to track the user's gaze. The eye-tracking means recognizes when the user's gaze is focused on a specific part of the screen and sends that information to a server.

[0580] Furthermore, the device uses cameras and sensors to detect the user's hand gestures. The motion recognition system identifies specific gestures (for example, the "OK!" gesture) and transmits them to the server as an intention to purchase.

[0581] Once the user has finished selecting items, the terminal initiates the purchase process using the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After the user confirms, the server performs a secure payment process and completes the transaction. The server then sends the user a purchase completion notification and updates the purchase history.

[0582] As a concrete example, suppose a user is watching a cooking show and becomes interested in a pot used in it. The server analyzes the video data, identifies the pot, and sends related information to the user's terminal. The user then looks at the pot and makes an "OK!" gesture to begin the purchase process, easily completing the purchase. In this way, the system of the present invention makes user interaction almost unconscious, significantly improving the shopping experience.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] The server receives video data from television programs in real time and uses image processing algorithms to identify products. Once a product is identified, the information is matched against a database to retrieve relevant product identification information and detailed information.

[0586] Step 2:

[0587] The server uses AI generation based on acquired product information to create product recommendations tailored to the user. Based on past viewing and purchase history, it scores and prioritizes highly relevant products for presentation.

[0588] Step 3:

[0589] The device receives data from an eye-tracking device to track the user's gaze. The eye-tracking algorithm analyzes the position of the gaze and identifies which part of the image the user is focusing on.

[0590] Step 4:

[0591] The device transmits gaze information about the product area that it has visually identified to the server. This includes information such as how long the user's gaze remained in a particular location.

[0592] Step 5:

[0593] The device detects user gestures using high-sensitivity sensors and cameras. When the motion recognition algorithm detects an "OK!" gesture, it interprets the user's intention as a purchase and notifies the server.

[0594] Step 6:

[0595] Once a user indicates their intention to purchase, the server sends detailed information about the potential purchase items and a purchase confirmation screen to the user's device. Here, the user can make a final confirmation of their purchase.

[0596] Step 7:

[0597] After the user makes a final confirmation of their purchase, the server initiates payment processing via the payment gateway. The user's secure payment information is used during this process.

[0598] Step 8:

[0599] Once a transaction is complete, the server sends a purchase confirmation to the user and updates the purchase history database. This information is used for future recommendations.

[0600] (Example 1)

[0601] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0602] A challenge with traditional online shopping systems is that users have to go through a lot of trouble and time to obtain product information and make a purchase. Specifically, the process of identifying products of interest, checking detailed information, and completing the purchase procedure is cumbersome, resulting in a poor user experience.

[0603] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0604] In this invention, the server includes an image analysis means for analyzing visual information and recognizing items from the visual data; a recommendation generation means for generating recommendation information about the items; an eye-tracking device for tracking the user's gaze and acquiring gaze data; an action detection means for detecting the user's actions and determining their intentions; and a transaction initiation processing means for initiating a transaction based on the user's selection. This makes it possible for users to instantly identify products of interest from the video they are watching and to proceed with the purchase process intuitively.

[0605] "Visual information" refers to video and image data acquired by cameras and sensors.

[0606] "Image analysis means" refers to a part of the function that constitutes a system that recognizes objects from visual data and extracts their characteristics.

[0607] A "recommendation generation method" has the function of presenting relevant information and alternatives suitable for the user based on the recognized items.

[0608] An "eye-tracking device" is a device that detects the user's eye movements and measures and analyzes where their gaze is directed on the screen.

[0609] A "motion detection means" is a component that analyzes the user's body movements and determines their intentions.

[0610] A "transaction initiation processing mechanism" is a part of a system that initiates the purchase procedure for goods based on the user's selection.

[0611] A "gaze focus recognition means" is a function that detects when a user's gaze data is focused on a specific screen area and transmits that information to a server.

[0612] A "means of conveying intent" refers to a system element that senses the user's gestures and accurately transmits their intent to the server.

[0613] In this embodiment of the invention, a server plays a crucial role. The server continuously receives video signals from a television receiver and processes the visual information. Specifically, it recognizes objects from the visual data using an image analysis means employing a machine learning algorithm. In this process, deep learning technology and database matching are combined to identify objects and extract their features. Regarding the recognized objects, the server uses a recommendation generation means to generate and present relevant information and alternative product information suitable for the user.

[0614] The terminal acts as the interface with the user. The terminal includes an eye-tracking device that collects the user's gaze data in real time. This device can identify which part of the screen the user is focusing on. The terminal also uses a camera and motion sensors to detect user movements. Utilizing the motion detection means, when it receives a gesture from the user, such as a hand signal, it notifies the server of this intent and prepares to begin the purchase process.

[0615] When a user selects a product they are interested in within a video they are watching, the device transmits this information to the server through the user's gaze and gestures towards that product. The server then uses a transaction initiation process to quickly proceed with the purchase. Advanced image recognition technology allows users to easily select the desired product and experience the purchase process intuitively.

[0616] For example, if a user becomes interested in a cooking utensil while watching a cooking show, the device detects the user's gaze towards the utensil and checks their gesture. Based on this information, the server identifies the utensil and displays related purchase information. The user signals their intention to purchase to the server with an "OK!" gesture, and the system completes the purchase process. This series of operations allows the user to enjoy an efficient and seamless shopping experience.

[0617] An example of a prompt using a generative AI model would be an instruction such as, "Please describe a system that visually recognizes products featured on a television program and assists the user in the purchase process through their gaze and gestures."

[0618] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0619] Step 1:

[0620] The server receives visual information in real time from the television receiver. It takes this visual information as input and uses image analysis to recognize objects. In this process, machine learning algorithms scan each frame of the visual data and extract the features of the objects. As output, a list of identified objects is generated. For example, cooking utensils shown in a program are identified as pots and pans.

[0621] Step 2:

[0622] The server matches the characteristics of the items recognized in step 1 against a database. This database contains detailed product information, from which the server obtains input to generate relevant recommendation information. Based on the matching results from the database, it outputs recommendation information to present to the user. Specifically, this includes the price of the cookware, the manufacturer, and information on online stores where it can be purchased.

[0623] Step 3:

[0624] The device collects user gaze data using an eye-tracking device. The eye-tracking device receives the user's eye movements as input and performs data calculations to detect which part of the screen the gaze is directed towards. The output provides the gaze position and focus. This allows for the identification of objects the user is particularly interested in.

[0625] Step 4:

[0626] The device records user movements using a camera and motion sensors. The user's movements are used as input, and data processing is performed by a motion detection system to identify specific gestures. The output then identifies clear gestures indicating purchase intent. For example, if a user makes an "OK!" gesture, this is converted into a signal that is transmitted to the server indicating their purchase intent.

[0627] Step 5:

[0628] The user confirms the items they wish to purchase through their gaze and gestures. The terminal instructs the server to initiate the transaction based on these inputs. The server retrieves this information, generates a prompt message on the screen displaying the purchase details of the items, and asks the user for confirmation. Upon user confirmation, the purchase process begins, and a secure payment process is executed.

[0629] (Application Example 1)

[0630] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0631] Currently, in many physical stores, customers need to spend time individually obtaining product information, which often makes the purchasing process cumbersome. Furthermore, manual verification and waiting times at the checkout are unavoidable when purchasing specific items. These factors cause stress for consumers and degrade the quality of the shopping experience. Therefore, innovative methods are needed to make the in-store purchasing process more efficient and intuitive.

[0632] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0633] In this invention, the server includes image recognition means for analyzing visual information and recognizing objects from the visual data, generation means for generating presentation information about the objects, and eye-tracking means for tracking the user's gaze and acquiring gaze data. This enables the user to intuitively select products in a physical store and complete the purchase with minimal effort.

[0634] "Visual information" refers to image and video data acquired using digital cameras or sensors.

[0635] "Image recognition means" refers to algorithms and devices that use computer vision technology to identify objects and scenes from visual information.

[0636] "Generation means" refers to devices or software that perform a process of generating relevant information and recommendations based on recognized objects.

[0637] "Eye-tracking means" refers to technologies and devices that measure the direction of a user's gaze and acquire that data.

[0638] "Gesture recognition means" refers to technologies and devices that use sensors or cameras to detect the movements of a user's hands or body and interpret them as specific intentions or commands.

[0639] A "transaction initiation mechanism" is a system that automatically or semi-automatically initiates the purchase process based on the selected object.

[0640] "Augmented reality display means" refers to devices and technologies for overlaying and displaying digital information onto the real world.

[0641] To realize this application, the system primarily uses a server, terminals, eye-tracking devices, and gesture recognition technology. The server first acquires visual information through a digital camera, uses image recognition to identify products, and generates presentation information about those products. Machine learning frameworks such as TensorFlow and PyTorch are used for image recognition. The server then performs object identification and information generation in physical stores.

[0642] Next, the device tracks the user's gaze. Using a Tobii eye-tracking device, it collects gaze data in real time. This data is sent to a server for processing to determine which objects the user is interested in. If the gaze remains on a specific object for a certain period of time, information about that object is presented by the augmented reality display system.

[0643] Furthermore, the server uses gesture recognition to detect the user's hand and body movements. Using OpenCV and MediaPipe, it interprets the user's gestures and determines their purchase intent. For example, if an "OK!" gesture is detected, the transaction process to purchase that item is initiated.

[0644] To give a concrete example, if a user finds a smart toy in a physical store and their intention to purchase is confirmed by gesture recognition while they are looking at the toy, the transaction process will proceed immediately, improving the user experience. Throughout this entire process, augmented reality information is presented via devices such as HMDs, providing the user with intuitive product information and purchase options.

[0645] Examples of prompt statements for generative AI models include the following:

[0646] "Propose a prototype of a system that recognizes products based on image data, identifies user interests using eye-tracking information, and allows users to decide on the purchase of a specific product through gestures."

[0647] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0648] Step 1:

[0649] The server receives visual information from a digital camera transmitted from a terminal. Using this visual information as input, it utilizes image recognition and a generative AI model to identify products and analyze their characteristics. After data processing, detailed information and related data of the identified products are output.

[0650] Step 2:

[0651] The device acquires the user's gaze data in real time using a Tobii eye-tracking device. This gaze information is sent to a server, which uses the gaze information to perform data calculations to identify products of interest to the user. When the gaze is focused on a specific object, that information is output, and details of the corresponding product are displayed.

[0652] Step 3:

[0653] The user makes a gesture indicating their intention to purchase after reviewing the product. The terminal recognizes this gesture using OpenCV or MediaPipe. This gesture data is sent to the server as input, and the server processes the data to determine the intention. If the judgment results in a gesture that is interpreted as an intention to purchase, the purchase process is initiated.

[0654] Step 4:

[0655] The server executes the purchase process. Using the transaction initiation method, it generates a purchase screen based on the previously obtained product information and presents it to the user via the terminal. After final confirmation, the server securely executes the payment process and completes the purchase. As output, a transaction completion notification is sent to the user.

[0656] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0657] The system of the present invention consists of a server that performs image processing connected to a television receiver, a terminal for recognizing the user's actions and emotions, and an eye-tracking device and an emotion recognition engine.

[0658] First, the server receives video data from television programs in real time and uses image processing algorithms to identify products. The server generates information about the identified products and related recommendation information. The recommendation system suggests products that are highly relevant to the user based on the user's past viewing and purchase history, as well as their emotional state.

[0659] The device collects user gaze data using an eye-tracking device. The eye-tracking means identifies which part of the screen the user is fixating on and sends that information to a server. Furthermore, the device is equipped with an emotion recognition engine that obtains emotion information by analyzing changes in the user's facial expressions. This emotion information is taken into consideration by the recommendation system and used to improve the accuracy of product recommendations.

[0660] Furthermore, the device has a motion recognition function that identifies gestures made by the user. The motion recognition means recognizes the "OK!" gesture and sends the intention to the server as a purchase intent.

[0661] Once the user has finished selecting products, the terminal initiates the purchase process through the transaction initiation method. The server displays the purchase details on the screen and prompts the user for confirmation. After confirmation, the server performs a secure payment process. Upon completion of the transaction, the server sends the user a purchase completion notification, records the purchase history and sentiment information in a database, and uses it for future recommendations.

[0662] As a concrete example, consider a scenario where a user becomes interested in an outfit that appears in a movie. The server identifies the outfit in the video and provides relevant information. In addition, an emotion recognition engine analyzes the user's facial expressions, and if it detects positive emotions, it uses that information to provide even more appropriate product recommendations. This invention allows users to have a more personalized shopping experience.

[0663] The following describes the processing flow.

[0664] Step 1:

[0665] The server receives video data from television programs in real time and uses machine learning algorithms to identify products within the video. Once a product is identified, its detailed information is retrieved from a database.

[0666] Step 2:

[0667] The server uses AI to generate personalized recommendations based on the acquired product information. Specifically, it lists relevant products by taking into account the user's purchase history, viewing history, and real-time sentiment information.

[0668] Step 3:

[0669] The device uses an eye-tracking device to receive the user's gaze data and identify where on the screen the user is fixating. The gaze information is immediately sent to the server.

[0670] Step 4:

[0671] The device analyzes the user's facial expressions in real time via a facial recognition camera and extracts emotional information using an emotion recognition engine. This emotional information quantifies the user's current mood and level of interest.

[0672] Step 5:

[0673] The server integrates gaze and emotion information transmitted from the device to further optimize recommendations and provides the results to the user. This results in personalized recommendations that focus on products the user has looked at or products that have elicited positive emotions.

[0674] Step 6:

[0675] The device uses sensors to detect the user's hand gestures and a motion recognition algorithm to recognize the "OK!" gesture. Once this action is recognized, the selected product is confirmed.

[0676] Step 7:

[0677] The server initiates the transaction start step and displays a purchase confirmation dialog on the screen. The user can then make a final confirmation of the purchase.

[0678] Step 8:

[0679] Once the user finalizes the purchase, the server proceeds with the payment process, ensuring that the transaction is securely verified. After the transaction is complete, the server sends a purchase completion notification and updates the user's purchase history and associated sentiment information.

[0680] (Example 2)

[0681] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0682] Traditional online shopping systems have limited the user experience due to insufficient personalized product recommendations based on user interests and emotions. Furthermore, a lack of intuitive controls for users to smoothly select and purchase products remains a challenge.

[0683] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0684] In this invention, the server includes image processing means for analyzing visual information and recognizing products from the visual data, information generation means for generating recommendation information about products based on past history and emotional state, and gaze detection means for tracking the user's gaze and acquiring gaze information. This enables personalized product recommendations that are tailored to the user's interests and emotions.

[0685] "Analyzing visual information" refers to the process of detecting specific objects or features from image or video data and performing data processing to identify them.

[0686] "Recognizing a product" means analyzing the characteristics of a product and comparing them with information in a database to identify its specific product name and attributes.

[0687] "Information generation means" refers to a device or program that has the function of creating appropriate recommendation information based on past historical data and the user's current emotional state.

[0688] "Eye-gaze detection means" refers to a device or program that analyzes the movement of the user's eyeballs and the point of fixation to determine where they are looking.

[0689] An "emotion analysis tool" is a device or program that analyzes the user's facial expressions and infers the type and intensity of emotions from them.

[0690] "Motion detection means" refers to a device or program that analyzes the user's body movements and gestures to determine a specific intention or command.

[0691] "Means of performing a procedure" refers to a device or program that controls a series of actions necessary to initiate a transaction and executes payment processing and verification steps.

[0692] To implement this invention, a system including a server, terminals, and various devices is constructed. The server receives video data in real time via a television receiver and identifies products in the visual data using an image processing library. This process uses OpenCV, a common image recognition library, to extract features of products shown in the video and match them with a database.

[0693] Next, the device uses an eye-tracking device to track the user's gaze. This device utilizes a common eye-tracking technology to identify where the user is looking on the screen. Based on this result, the user's interests are measured.

[0694] Furthermore, the device is equipped with an emotion analysis engine that monitors the user's facial expressions via a camera. Using general emotion recognition software, it analyzes changes in the user's facial expressions and determines their emotional state. This information is used by the server to improve the accuracy of product recommendations.

[0695] The terminal also has motion detection capabilities, recognizing the user's hand gestures with its camera. Motion recognition uses a machine learning model to interpret the gestures; for example, an "OK!" command is interpreted as an intention to purchase. This information is transmitted to a server and used as a means to initiate a transaction.

[0696] For example, if a user becomes interested in an outfit while watching a movie, the server analyzes the video of that scene and extracts detailed information about the outfit. The emotion recognition engine reads the user's facial expressions, and if it detects a positive emotion, it suggests related products based on that.

[0697] An example of a prompt to input into a generative AI model would be: "Please provide detailed information about the costumes the user showed interest in while watching the movie. Based on the user's emotional state, please also recommend related products."

[0698] In this way, users can receive personalized product recommendations based on their viewing experience and enjoy a more fulfilling shopping experience.

[0699] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0700] Step 1:

[0701] The server receives video data in real time from the television receiver. Using this video data as input, it identifies products using an image processing algorithm. Specifically, it uses OpenCV to convert the images in the video to grayscale and performs edge detection to recognize the contours of the products. This data processing outputs characteristic data of the identified products.

[0702] Step 2:

[0703] The device collects user gaze information using an eye-tracking device. This gaze data is used as input to identify where the user is fixating on the screen. Specifically, an eye-tracking algorithm analyzes the user's eye movements and outputs the coordinates of the point of fixation. This output is sent to the server as information indicating the user's area of ​​interest.

[0704] Step 3:

[0705] The device uses an emotion recognition engine to analyze the user's facial expressions and obtain emotional information. This facial data is then used as input to estimate the emotional category (e.g., joy, surprise) using a deep learning model. The model extracts facial features and outputs an emotional label based on them. This emotional information is also sent to the server and used as a basis for product recommendation decisions.

[0706] Step 4:

[0707] The server uses a generative AI model to recommend products based on product identification results, user gaze data, and sentiment information. Using this information as input, a machine learning model, which also considers historical data, generates an optimal product list. As a result of this data processing, product recommendations are output to the user.

[0708] Step 5:

[0709] The terminal uses motion detection to recognize the user's gestures. A motion analysis algorithm takes the gesture video as input, identifies gestures such as "OK!", and outputs their intent to the server. This confirms the user's purchase intention.

[0710] Step 6:

[0711] The server initiates a transaction based on user gesture recognition. Using product information and screen display data for purchase confirmation as input, it calls the payment processing system to securely complete the transaction. As an output of this process, a purchase completion notification is sent to the user, and the purchase history is recorded in the database.

[0712] (Application Example 2)

[0713] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0714] Traditional e-commerce systems present challenges such as a cumbersome process from product selection to purchase, making it difficult to provide personalized recommendations. Furthermore, mechanical recommendations often fail to consider the user's emotional state, hindering the improvement of the user experience. The lack of a payment process that quickly and naturally reflects purchase intent is also a significant issue.

[0715] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0716] In this invention, the server includes image recognition means for analyzing visual information and recognizing products from visual data, recommendation means for generating recommendation information about products, eye-tracking means for tracking the user's gaze and acquiring eye-tracking information, emotion recognition means for analyzing the user's facial expressions and recognizing emotions, and action recognition means for recognizing the user's actions and determining their intentions. This enables highly accurate product recommendations based on the user's interests and emotional state, and a smooth purchase process through intuitive actions.

[0717] "Image recognition means" refers to a technology or device for analyzing visual information to recognize products from visual data.

[0718] "Recommendation methods" refer to technologies or devices for generating highly relevant information about a product and suggesting it to the user.

[0719] "Eye-tracking means" refers to a technology or device that tracks the movement of a user's eyes and identifies which part they are fixating on.

[0720] "Emotion recognition means" refers to technology or devices for identifying an emotional state by analyzing the user's facial expressions.

[0721] "Motion recognition means" refers to a technology or device for analyzing the user's body movements and determining the user's intentions from those movements.

[0722] "Transaction initiation means" refers to technology or equipment for initiating a transaction, such as a purchase, based on the user's choice.

[0723] The system for implementing this invention provides users with a personalized purchasing experience by utilizing various devices and software. The system mainly consists of a server, terminals, eye-tracking devices, and an emotion recognition engine.

[0724] The server is the central hub for calculations and processing, using image recognition algorithms to analyze product information from video footage. The server also generates relevant recommendations based on this analysis. These recommendations are customized based on the user's viewing history, purchase history, and even their emotional state, which is captured in real time.

[0725] The user's device uses an eye-tracking device to collect eye-tracking information and accurately measure the user's eye movements. This data is used to identify which part of the screen the user is fixating on, and the identified eye-tracking information is sent to a server. The device also has an emotion recognition engine that analyzes the user's facial expressions in real time, allowing it to understand the user's emotional state.

[0726] The system combines user gaze and emotion data to improve the accuracy of product recommendations. Furthermore, it can initiate a transaction by recognizing specific gestures made by the user (e.g., a thumbs-up "OK!" gesture) and interpreting them as a purchase intention. The server performs secure payment processing and notifies the user when the transaction is complete. The recorded purchase history and emotion information are stored in a database and used for future recommendations.

[0727] For example, when a user becomes interested in an outfit they see while watching a movie or TV show, the eye-tracking device and emotion recognition engine can work together to determine whether the outfit is being viewed favorably. By integrating eye-tracking and emotion information in this way, the system can recommend the most suitable product for the user and facilitate a smooth purchase process.

[0728] An example of a prompt message is: "The user found a product they liked in the video they were watching. We want to confirm their interest in the product using eye-tracking and simplify the purchase process."

[0729] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0730] Step 1:

[0731] The server receives video data from television programs in real time and identifies products using an image recognition algorithm. The input is video data, and the output is information about the identified products. Products are identified by analyzing the pixels of the image data and extracting patterns and shapes characteristic of the product.

[0732] Step 2:

[0733] The server generates recommendation information related to the identified product. Inputs include past viewing and purchase history, as well as real-time sentiment information. The output is personalized recommendations used to present the user with highly relevant products. Recommendations are prioritized based on relevance, matching historical and sentiment data.

[0734] Step 3:

[0735] The device uses an eye-tracking device to collect user gaze data. The input is the user's visual gaze information, and the output is the specific location on the screen where the gaze is directed. The gaze position is determined by analyzing eye movements in real time via the camera and calculating the point of fixation.

[0736] Step 4:

[0737] The device uses an emotion recognition engine to acquire emotional information from the user's facial expressions. The input is image data of the user's face, and the output is the detected emotional state. Through image analysis, features related to facial expressions are extracted, and the emotional state is identified. This emotional information is used by recommendation systems to improve the accuracy of product recommendations.

[0738] Step 5:

[0739] The device recognizes the user's gestures to determine their purchase intent. The input is the user's gesture actions, and the output is confirmation information regarding the user's intention. A motion recognition algorithm is used to analyze the state of the gestures and identify their intent.

[0740] Step 6:

[0741] The server initiates the purchase process through the transaction initiation method and performs secure payment processing. Input is user verification information, and output is a transaction completion notification. Payment processing utilizes a payment API to integrate with external payment systems, ensuring a secure transaction.

[0742] 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.

[0743] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0744] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0745] 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.

[0746] Figure 9 shows an 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.

[0747] 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.

[0748] 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.

[0749] 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, motorcycles, etc., 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, for example, based 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.

[0750] 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."

[0751] 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.

[0752] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0753] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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 the like 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.

[0762] 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.

[0763] The following is further disclosed regarding the embodiments described above.

[0764] (Claim 1)

[0765] An image recognition means that analyzes visual information to recognize products from visual data,

[0766] A recommendation method for generating recommendation information about products,

[0767] A gaze tracking means that tracks the user's gaze and acquires gaze information,

[0768] Action recognition means that recognizes the user's actions and determines their intention,

[0769] A system that includes a means for initiating a transaction based on the user's selection.

[0770] (Claim 2)

[0771] The system according to claim 1, wherein the transaction initiation means prompts the user to confirm the purchase by controlling the display of information shown on the screen.

[0772] (Claim 3)

[0773] The system according to claim 1, wherein the image recognition means identifies the boundaries of products in visual data using a predetermined algorithm.

[0774] "Example 1"

[0775] (Claim 1)

[0776] An image analysis means that analyzes visual information and recognizes an object from the visual data,

[0777] A recommendation generation means for generating recommendation information about goods,

[0778] An eye-tracking device that tracks the user's gaze and acquires eye-tracking data,

[0779] Action detection means that detects the user's actions and determines their intention,

[0780] A transaction initiation processing means that initiates a transaction based on the user's selection,

[0781] A gaze focus recognition means that recognizes when acquired gaze information is concentrated on a specific part of the screen and transmits the information to a server,

[0782] A system including an intent communication mechanism that transmits purchase intent to a server based on gestures.

[0783] (Claim 2)

[0784] The system according to claim 1, wherein the transaction initiation processing means controls the information displayed on the screen to prompt the user to confirm the purchase.

[0785] (Claim 3)

[0786] The system according to claim 1, wherein the image analysis means identifies the contour of an article in visual data using a predetermined algorithm.

[0787] "Application Example 1"

[0788] (Claim 1)

[0789] An image recognition means that analyzes visual information and recognizes objects from visual data,

[0790] A generation means for generating presentation information about an object,

[0791] A gaze tracking means that tracks the user's gaze and acquires gaze data,

[0792] A gesture recognition means that recognizes the user's actions and determines their purchase intent,

[0793] A transaction initiation means that initiates a transaction based on the selected object,

[0794] A system including augmented reality display means for displaying visual data.

[0795] (Claim 2)

[0796] The system according to claim 1, wherein the transaction initiation means prompts the user to confirm the transaction by controlling the displayed information via a display device.

[0797] (Claim 3)

[0798] The system according to claim 1, wherein the image recognition means uses a machine learning algorithm to identify features of an object in visual data.

[0799] "Example 2 of combining an emotion engine"

[0800] (Claim 1)

[0801] An image processing means that analyzes visual information and recognizes products from the visual data,

[0802] Information generation means for generating recommendation information about products based on past history and emotional state,

[0803] A gaze detection means that tracks the user's gaze and acquires gaze information,

[0804] An emotion analysis method that analyzes the user's facial expressions to obtain emotional information,

[0805] Action detection means that recognizes the user's actions and determines their intention,

[0806] A system that includes means for initiating a transaction based on the user's choice.

[0807] (Claim 2)

[0808] The system according to claim 1, which displays and controls information to prompt the user to confirm the purchase in order to initiate a transaction.

[0809] (Claim 3)

[0810] The system according to claim 1, wherein the image processing means identifies the boundaries of products in visual data using predetermined arithmetic processing.

[0811] "Application example 2 when combining with an emotional engine"

[0812] (Claim 1)

[0813] An image recognition means that analyzes visual information to recognize products from visual data,

[0814] A recommendation method for generating recommendation information about products,

[0815] A gaze tracking means that tracks the user's gaze and acquires gaze information,

[0816] An emotion recognition method that analyzes the user's facial expressions to recognize emotions,

[0817] Action recognition means that recognizes the user's actions and determines their intention,

[0818] A system that includes a means for initiating a transaction based on the user's selection.

[0819] (Claim 2)

[0820] The system according to claim 1, wherein the transaction initiation means prompts the user to confirm the purchase by controlling the display of information shown on the screen and performs a secure payment process.

[0821] (Claim 3)

[0822] The system according to claim 1, wherein the image recognition means identifies the boundaries of products in visual data using a predetermined algorithm and recommends products taking into account the user's emotional information. [Explanation of symbols]

[0823] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An image recognition means that analyzes visual information to recognize products from visual data, A recommendation method for generating recommendation information about products, A gaze tracking means that tracks the user's gaze and acquires gaze information, Action recognition means that recognizes the user's actions and determines their intention, A system that includes a means for initiating a transaction based on the user's selection.

2. The system according to claim 1, wherein the transaction initiation means prompts the user to confirm the purchase by controlling the display of information shown on the screen.

3. The system according to claim 1, wherein the image recognition means identifies the boundaries of products in visual data using a predetermined algorithm.

Images