system

Abstract

The system according to this embodiment aims to freely replace and display real-world objects according to the user's preferences. [Solution] The system according to the embodiment comprises an object recognition unit, a posture estimation unit, a tracking unit, a replacement display unit, and an agent unit. The object recognition unit recognizes an object. The posture estimation unit estimates the posture of the object recognized by the object recognition unit. The tracking unit tracks the object estimated by the posture estimation unit. The replacement display unit replaces and displays the object tracked by the tracking unit. The agent unit receives instructions from the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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] In the conventional technology, it is difficult to freely replace and display real objects, and there is a problem that customization according to the user's preference is not sufficiently performed.

[0005] The system according to the embodiment aims to freely replace and display real objects according to the user's preference.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an object recognition unit, a posture estimation unit, a tracking unit, a replacement display unit, and an agent unit. The object recognition unit recognizes an object. The posture estimation unit estimates the posture of the object recognized by the object recognition unit. The tracking unit tracks the object estimated by the posture estimation unit. The replacement display unit replaces and displays the object tracked by the tracking unit. The agent unit receives instructions from the user. [Effects of the Invention]

[0007] The system according to this embodiment can freely replace and display real-world objects according to the user's preferences. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a 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.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AR display system according to an embodiment of the present invention is a system that replaces pedestrians and vehicles in a city with celebrities or favorite characters and displays them in AR. This AR display system uses object recognition and posture estimation technology to track and replace objects. In addition, the appearance of furniture and interior design in a room can be changed to suit the user's preference, and the view from the window can be freely specified. Furthermore, it is compatible not only with AR glasses but also with AR contact lenses that are expected to be developed in the future. Settings can be changed at any time by calling on the agent. For example, the user can call on the agent to change the settings. For example, the user might say, "Change the interior to a Swiss lakeside lodge. Change the window too, please." Based on this instruction, the camera in the AR glasses recognizes objects, and the appearance of furniture, etc., is replaced with something suitable for the lodge's interior and displayed. At the same time, the view from the window is set to show a Swiss lakeside. Next, when the user goes outside to commute, they can instruct the agent to "Make all the people and vehicles in the city look like a specific character." Based on this instruction, the camera in the AR glasses recognizes objects and people's postures, and people and vehicles in the city are replaced with characters or carriages that look like the specific character and displayed. This system combines image recognition-based tracking and pose estimation with augmented reality (AR) to replace and display objects in the city. It targets people who want to feel more cheerful while at home or commuting, aiming to boost their mood. The market size is projected to be several trillion yen, comparable to that of smartwatches. With advancements in image recognition, speech recognition, and large-scale language models, the technology is now catching up, making it the ideal time to enter the market. This allows the AR display system to replace pedestrians and vehicles in the city with celebrities or favorite characters in augmented reality.

[0029] The AR display system according to this embodiment comprises an object recognition unit, a pose estimation unit, a tracking unit, a replacement display unit, and an agent unit. The object recognition unit recognizes objects. The object recognition unit recognizes objects using, for example, image processing technology. The object recognition unit can also recognize objects using machine learning algorithms. Furthermore, the object recognition unit can also recognize objects using deep learning technology. For example, the object recognition unit uses image processing technology to detect objects from images captured by a camera and recognizes those objects. Machine learning algorithms build models for recognizing objects based on past data and recognize objects with high accuracy even with new data. Deep learning technology uses multi-layer neural networks to recognize objects and detect complex patterns with high accuracy. The pose estimation unit estimates the pose of the object recognized by the object recognition unit. The pose estimation unit estimates the pose of the object using, for example, a 3D model. Furthermore, the pose estimation unit can also estimate the pose of the object using a method for calculating joint angles. Furthermore, the pose estimation unit can also estimate the pose of the object using a skeletal model. For example, the posture estimation unit estimates the position and orientation of an object using a 3D model. The joint angle calculation method calculates the angles of the object's joints and estimates the posture based on those angles. The skeletal model estimates the posture based on the object's skeletal structure and reproduces complex movements with high accuracy. The tracking unit tracks the object estimated by the posture estimation unit. The tracking unit tracks the object using, for example, a camera. The tracking unit can also track the object using sensors. Furthermore, the tracking unit can also track the object using algorithms. For example, the tracking unit tracks the position and movement of an object in real time using a camera. Sensors detect the movement of an object and track the object based on that data. Algorithms analyze the movement patterns of an object and track the object based on those patterns. The replacement display unit replaces and displays the object tracked by the tracking unit. The replacement display unit replaces and displays the object using, for example, AR technology. The replacement display unit can also replace and display the object using a 3D model.Furthermore, the replacement display unit can also replace objects using video. For example, the replacement display unit can use AR technology to replace real-world objects with virtual characters or landscapes. 3D models overlay virtual objects onto real-world objects to provide a realistic experience. Videos overlay virtual landscapes or characters onto real-world landscapes to provide visual enjoyment. The agent unit receives instructions from the user. The agent unit receives user instructions using, for example, speech recognition technology. The agent unit can also receive user instructions using touch operations. Furthermore, the agent unit can also receive user instructions using gesture recognition technology. For example, the agent unit uses speech recognition technology to analyze the user's voice instructions and control the system based on those instructions. Touch operations allow the user to input instructions by touching the screen and control the system based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements. As a result, the AR display system according to the embodiment is capable of object recognition, posture estimation, tracking, replacement display, and receiving instructions from the user.

[0030] The object recognition unit recognizes objects. For example, the object recognition unit recognizes objects using image processing techniques. Furthermore, the object recognition unit can also recognize objects using machine learning algorithms. In addition, the object recognition unit can recognize objects using deep learning techniques. For example, the object recognition unit uses image processing techniques to detect and recognize objects from images captured by a camera. Machine learning algorithms build object recognition models based on past data and recognize objects with high accuracy even with new data. Deep learning techniques use multi-layered neural networks to recognize objects and detect complex patterns with high accuracy. By combining these techniques, the object recognition unit can maintain high recognition accuracy even in various environments and conditions. For example, image processing techniques extract object features using methods such as edge detection and contour extraction, and machine learning algorithms classify the type and attributes of objects based on those features. Deep learning techniques perform more advanced feature extraction, enabling accurate object recognition from complex objects and backgrounds. The object recognition unit utilizes these techniques to recognize objects in real time, improving the overall accuracy and efficiency of the system. Furthermore, the object recognition unit can share recognition results with other units, strengthening the overall system coordination. For example, information on recognized objects can be transmitted to the pose estimation unit and tracking unit, where it is used as foundational data for more accurate processing. This allows the object recognition unit to improve the overall system performance and provide users with a higher quality AR experience.

[0031] The posture estimation unit estimates the posture of an object recognized by the object recognition unit. The posture estimation unit can estimate the posture of an object using, for example, a 3D model. It can also estimate the posture of an object using a joint angle calculation method. Furthermore, it can estimate the posture of an object using a skeletal model. For example, the posture estimation unit uses a 3D model to estimate the position and orientation of an object. The joint angle calculation method calculates the angles of the object's joints and estimates the posture based on those angles. The skeletal model estimates the posture based on the object's skeletal structure and reproduces complex movements with high accuracy. By combining these technologies, the posture estimation unit can estimate the posture of various objects with high accuracy. For example, a 3D model represents the shape and structure of an object in detail and accurately estimates the object's position and orientation based on that information. The joint angle calculation method analyzes the movement of the object's joints and estimates the posture based on that movement. The skeletal model can analyze the object's skeletal structure in detail and reproduce complex movements with high accuracy. The pose estimation unit utilizes these technologies to estimate the object's pose in real time, improving the overall accuracy and efficiency of the system. Furthermore, the pose estimation unit can share the estimation results with other units, strengthening the overall system coordination. For example, the estimated object's pose information can be transmitted to the tracking unit and the replacement display unit, where it is used as foundational data for more accurate processing. This allows the pose estimation unit to improve the overall system performance and provide users with a higher quality AR experience.

[0032] The tracking unit tracks the object estimated by the attitude estimation unit. The tracking unit can track the object using, for example, a camera. It can also track the object using sensors. Furthermore, the tracking unit can track the object using algorithms. For example, the tracking unit uses a camera to track the object's position and movement in real time. Sensors detect the object's movement and track it based on that data. Algorithms analyze the object's movement patterns and track it based on those patterns. By combining these technologies, the tracking unit can maintain high tracking accuracy even in various environments and conditions. For example, a camera captures the object's position and movement in detail and tracks it in real time based on that information. Sensors detect the object's movement and track it based on that data. Algorithms analyze the object's movement patterns and track it based on those patterns. The tracking unit utilizes these technologies to track objects in real time, improving the overall accuracy and efficiency of the system. Furthermore, the tracking unit can share tracking results with other departments, strengthening overall system collaboration. For example, information about tracked objects is transmitted to the replacement display unit and agent unit, where it is used as foundational data for more accurate processing. This allows the tracking unit to improve the overall system performance and provide users with a higher quality AR experience.

[0033] The replacement display unit replaces and displays objects tracked by the tracking unit. The replacement display unit can replace and display objects using, for example, AR technology. It can also replace and display objects using 3D models. Furthermore, it can replace and display objects using video. For example, the replacement display unit uses AR technology to replace real-world objects with virtual characters or landscapes. 3D models overlay virtual objects onto real-world objects, providing a realistic experience. Video overlays virtual landscapes or characters onto real-world landscapes, providing visual enjoyment. By combining these technologies, the replacement display unit can maintain high display accuracy even in various environments and conditions. For example, AR technology replaces real-world objects with virtual characters or landscapes, providing users with a new experience. 3D models overlay virtual objects onto real-world objects, providing a realistic experience. Video overlays virtual landscapes or characters onto real-world landscapes, providing visual enjoyment. The replacement display unit utilizes these technologies to replace and display objects in real time, improving the overall accuracy and efficiency of the system. Furthermore, the replacement display unit can share display results with other departments, strengthening the overall system collaboration. For example, information on the replaced and displayed objects is transmitted to the agent unit and used as basic data for the agent unit to perform more accurate processing. As a result, the replacement display unit can improve the overall system performance and provide users with a higher quality AR experience.

[0034] The agent unit receives instructions from the user. For example, the agent unit can receive user instructions using speech recognition technology. It can also receive user instructions using touch operations. Furthermore, the agent unit can receive user instructions using gesture recognition technology. For example, the agent unit uses speech recognition technology to analyze the user's voice instructions and control the system based on those instructions. Touch operations allow the user to input instructions by touching the screen, and the system controls based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements. By combining these technologies, the agent unit can maintain high instruction reception accuracy even in various environments and conditions. For example, speech recognition technology analyzes the user's voice instructions and controls the system based on those instructions. Touch operations allow the user to input instructions by touching the screen, and the system controls based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements. The agent unit utilizes these technologies to receive user instructions in real time and improve the overall accuracy and efficiency of the system. Furthermore, the agent unit can share instruction results with other units, strengthening the overall system coordination. For example, received user instructions can be transmitted to the object recognition unit and the pose estimation unit, where they are used as foundational data for more accurate processing. This allows the agent unit to improve the overall system performance and provide users with a higher quality AR experience.

[0035] The replacement display unit can change the appearance and interior of a room's furniture. For example, it can use AR technology to change the appearance of a room's furniture. It can also change the interior of a room using 3D models. Furthermore, it can change the atmosphere of a room using video. For example, it can use AR technology to replace real furniture with virtual furniture. 3D models overlay virtual furniture and interiors onto a real room, providing a realistic experience. Videos overlay virtual scenery and interiors onto a real room, providing visual enjoyment. This allows for changes to the appearance and interior of a room's furniture.

[0036] The replacement display unit can change the view from the window. For example, the replacement display unit can change the view from the window using AR technology. It can also change the view from the window using video. Furthermore, it can change the view from the window using 3D models. For example, the replacement display unit uses AR technology to replace the real-world view with a virtual one. Video overlays a virtual landscape onto the real window, providing visual enjoyment. 3D models overlay a virtual landscape onto the real window, providing a realistic experience. This allows the view from the window to be changed.

[0037] The agent unit can support AR glasses and AR contact lenses. For example, the agent unit supports AR glasses by ensuring device compatibility. It can also support AR contact lenses by applying a communication protocol. Furthermore, the agent unit can support new devices through software updates. For instance, to ensure compatibility with AR glasses, the agent unit configures itself to match the device's specifications. The communication protocol is a set of rules for exchanging data between the AR contact lens and the agent unit, enabling smooth communication. Software updates allow the agent unit to support new devices as they emerge. This enables support for both AR glasses and AR contact lenses.

[0038] The agent unit can change settings based on user instructions. For example, the agent unit can receive user instructions using speech recognition technology and change settings based on those instructions. The agent unit can also receive user instructions using touch operation and change settings based on those instructions. Furthermore, the agent unit can receive user instructions using gesture recognition technology and change settings based on those instructions. For example, the agent unit can use speech recognition technology to analyze the user's voice instructions and change system settings based on those instructions. Touch operation allows the user to input instructions by touching the screen, and the system settings are changed based on those instructions. Gesture recognition technology detects the user's hand movements and changes system settings based on those movements. This allows the system to change settings based on user instructions.

[0039] The object recognition unit can recognize objects using the camera built into the AR glasses. For example, the object recognition unit can photograph an object using the camera built into the AR glasses, analyze the image data, and recognize the object. Furthermore, the object recognition unit can perform more detailed object recognition by increasing the camera resolution. In addition, the object recognition unit can improve the accuracy of object recognition by optimizing the recognition algorithm. For example, the object recognition unit can photograph pedestrians and vehicles in a city using the camera built into the AR glasses, analyze the image data, and recognize the objects. By increasing the camera resolution, distant objects and small objects can be recognized with high accuracy. The recognition algorithm extracts the features of an object and identifies the object based on those features. This allows objects to be recognized using the camera built into the AR glasses.

[0040] The posture estimation unit can estimate the posture of an object using the camera mounted on the AR glasses. For example, the posture estimation unit takes a picture of an object using the camera mounted on the AR glasses, analyzes the image data, and estimates the object's posture. Furthermore, the posture estimation unit can perform more detailed posture estimation by increasing the camera resolution. In addition, the posture estimation unit can improve the accuracy of posture estimation by optimizing the posture estimation algorithm. For example, the posture estimation unit takes a picture of pedestrians or vehicles in a city using the camera mounted on the AR glasses, analyzes the image data, and estimates the object's posture. By increasing the camera resolution, the posture of distant or small objects can also be estimated with high accuracy. The posture estimation algorithm calculates the joint angles and positions of the object and estimates the posture based on that data. This allows the posture of an object to be estimated using the camera mounted on the AR glasses.

[0041] The object recognition unit can optimize its recognition algorithm by referring to the user's past recognition history during object recognition. For example, the object recognition unit can store the user's past recognition history in a database and optimize the recognition algorithm based on that data. Furthermore, the object recognition unit can construct an algorithm that prioritizes the recognition of specific objects based on past recognition history. In addition, the object recognition unit can analyze past recognition history and extract patterns to improve recognition accuracy. For example, the object recognition unit optimizes its recognition algorithm based on data of objects the user has recognized in the past. It constructs an algorithm that prioritizes the recognition of specific objects based on the user's past recognition history. It analyzes the user's past recognition history and extracts patterns to improve recognition accuracy. This allows the recognition algorithm to be optimized by referring to the user's past recognition history.

[0042] The object recognition unit can improve recognition accuracy by analyzing the movement patterns of objects during object recognition. For example, the object recognition unit can analyze the movement patterns of objects in real time and improve recognition accuracy based on that data. Furthermore, the object recognition unit can optimize its recognition algorithm based on past movement pattern data. In addition, the object recognition unit can learn the movement patterns of objects and build models to improve recognition accuracy. For example, the object recognition unit analyzes the movement patterns of objects in real time and improves recognition accuracy based on that data. It optimizes its recognition algorithm based on past movement pattern data. It learns the movement patterns of objects and builds models to improve recognition accuracy. This allows it to analyze the movement patterns of objects and improve recognition accuracy.

[0043] The object recognition unit can prioritize the recognition of highly relevant objects based on the user's geographical location information during object recognition. For example, the object recognition unit acquires the user's geographical location information and prioritizes the recognition of highly relevant objects based on that information. The object recognition unit can also improve recognition accuracy by optimizing the method of acquiring location information. Furthermore, the object recognition unit can determine which objects to prioritize for recognition by setting criteria for evaluating relevance. For example, if the user is in a specific region, the object recognition unit will prioritize the recognition of objects related to that region. If the user is in a tourist area, it will prioritize the recognition of tourist attractions. If the user is at home, it will prioritize the recognition of objects within the home. This allows the object recognition unit to prioritize the recognition of highly relevant objects based on the user's geographical location information.

[0044] The object recognition unit can analyze the user's social media activity and recognize related objects during object recognition. For example, the object recognition unit can store the user's social media activity in a database and recognize related objects based on that data. The object recognition unit can also improve recognition accuracy by optimizing the method of collecting social media data. Furthermore, the object recognition unit can determine which objects to recognize preferentially by setting criteria for evaluating relevance. For example, the object recognition unit may preferentially recognize objects that the user has shown interest in on social media. It can analyze the content of the user's social media posts and recognize related objects. It can recognize objects that the user's social media followers are interested in. In this way, it can analyze the user's social media activity and recognize related objects.

[0045] The pose estimation unit can optimize its estimation algorithm by referring to the object's past pose data during pose estimation. For example, the pose estimation unit can store the object's past pose data in a database and optimize the estimation algorithm based on that data. The pose estimation unit can also construct an algorithm that prioritizes the estimation of specific poses from past pose data. Furthermore, the pose estimation unit can analyze past pose data and extract patterns to improve estimation accuracy. For example, the pose estimation unit optimizes the estimation algorithm based on the object's past pose data. It constructs an algorithm that prioritizes the estimation of specific poses from the object's past pose data. It analyzes the object's past pose data and extracts patterns to improve estimation accuracy. This allows the estimation algorithm to be optimized by referring to the object's past pose data.

[0046] The pose estimation unit can improve estimation accuracy by analyzing the movement patterns of an object during pose estimation. For example, the pose estimation unit can analyze the movement patterns of an object in real time and improve estimation accuracy based on that data. Furthermore, the pose estimation unit can optimize the estimation algorithm based on past movement pattern data. In addition, the pose estimation unit can learn the movement patterns of an object and build a model to improve estimation accuracy. For example, the pose estimation unit can analyze the movement patterns of an object in real time and improve estimation accuracy based on that data. It can optimize the estimation algorithm based on past movement pattern data. It can learn the movement patterns of an object and build a model to improve estimation accuracy. This allows for improved estimation accuracy by analyzing the movement patterns of an object.

[0047] The posture estimation unit can prioritize estimating postures that are highly relevant to an object based on its geographical location information. For example, the posture estimation unit acquires the object's geographical location information and prioritizes estimating postures that are highly relevant based on that information. The posture estimation unit can also improve estimation accuracy by optimizing the method of acquiring location information. Furthermore, the posture estimation unit can determine which postures to prioritize by setting criteria for evaluating relevance. For example, if an object is in a specific region, the posture estimation unit will prioritize estimating postures related to that region. If an object is in a tourist area, it will prioritize estimating postures at tourist attractions. If an object is at home, it will prioritize estimating postures within the home. This allows the posture estimation unit to prioritize estimating postures that are highly relevant based on the object's geographical location information.

[0048] The pose estimation unit can improve estimation accuracy by referring to relevant literature on the object during pose estimation. For example, the pose estimation unit can store relevant literature on the object in a database and optimize the estimation algorithm based on that data. The pose estimation unit can also construct an algorithm that prioritizes the estimation of a specific pose from the relevant literature. Furthermore, the pose estimation unit can analyze the relevant literature and extract patterns to improve estimation accuracy. For example, the pose estimation unit optimizes the estimation algorithm based on relevant literature on the object. It constructs an algorithm that prioritizes the estimation of a specific pose from the relevant literature on the object. It analyzes the relevant literature on the object and extracts patterns to improve estimation accuracy. This allows the pose estimation accuracy to be improved by referring to relevant literature on the object.

[0049] The tracking unit can optimize the tracking algorithm by referring to the object's past tracking data during tracking. For example, the tracking unit can store the object's past tracking data in a database and optimize the tracking algorithm based on that data. Furthermore, the tracking unit can construct an algorithm that prioritizes tracking specific objects based on past tracking data. In addition, the tracking unit can analyze past tracking data and extract patterns to improve tracking accuracy. For example, the tracking unit optimizes the tracking algorithm based on the object's past tracking data. It constructs an algorithm that prioritizes tracking specific objects based on the object's past tracking data. It analyzes the object's past tracking data and extracts patterns to improve tracking accuracy. This allows the tracking algorithm to be optimized by referring to the object's past tracking data.

[0050] The tracking unit can improve tracking accuracy by analyzing the movement patterns of objects during tracking. For example, the tracking unit can analyze the movement patterns of objects in real time and improve tracking accuracy based on that data. Furthermore, the tracking unit can optimize the tracking algorithm based on past movement pattern data. In addition, the tracking unit can learn the movement patterns of objects and build models to improve tracking accuracy. For example, the tracking unit can analyze the movement patterns of objects in real time and improve tracking accuracy based on that data. It can optimize the tracking algorithm based on past movement pattern data. It can learn the movement patterns of objects and build models to improve tracking accuracy. This allows for improved tracking accuracy by analyzing the movement patterns of objects.

[0051] The tracking unit can prioritize tracking highly relevant objects based on the object's geographical location information during tracking. For example, the tracking unit acquires the object's geographical location information and uses that information to prioritize tracking highly relevant objects. The tracking unit can also improve tracking accuracy by optimizing the method of acquiring location information. Furthermore, the tracking unit can determine which objects to prioritize tracking by setting criteria for evaluating relevance. For example, if the object is in a specific region, the tracking unit will prioritize tracking objects related to that region. If the object is in a tourist area, it will prioritize tracking objects related to tourist attractions. If the object is at home, it will prioritize tracking objects within the home. This allows for the priority tracking of highly relevant objects based on the object's geographical location information.

[0052] The tracking unit can improve tracking accuracy by referring to relevant literature for objects during tracking. For example, the tracking unit can store relevant literature for objects in a database and optimize the tracking algorithm based on that data. The tracking unit can also construct an algorithm that prioritizes tracking specific objects based on the relevant literature. Furthermore, the tracking unit can analyze the relevant literature and extract patterns to improve tracking accuracy. For example, the tracking unit optimizes the tracking algorithm based on relevant literature for objects. It constructs an algorithm that prioritizes tracking specific objects based on relevant literature. It analyzes the relevant literature for objects and extracts patterns to improve tracking accuracy. This allows for improved tracking accuracy by referring to relevant literature for objects.

[0053] The replacement display unit can optimize its display algorithm by referring to the object's past display data during replacement display. For example, the replacement display unit can store the object's past display data in a database and optimize the display algorithm based on that data. Furthermore, the replacement display unit can construct an algorithm that prioritizes the display of specific display patterns from past display data. In addition, the replacement display unit can analyze past display data and extract patterns to improve display accuracy. For example, the replacement display unit optimizes the display algorithm based on the object's past display data. It constructs an algorithm that prioritizes the display of specific display patterns from the object's past display data. It analyzes the object's past display data and extracts patterns to improve display accuracy. This allows the display algorithm to be optimized by referring to the object's past display data.

[0054] The replacement display unit can improve display accuracy by analyzing the movement patterns of objects during replacement display. For example, the replacement display unit can analyze the movement patterns of objects in real time and improve display accuracy based on that data. Furthermore, the replacement display unit can optimize the display algorithm based on past movement pattern data. In addition, the replacement display unit can learn the movement patterns of objects and build models to improve display accuracy. For example, the replacement display unit can analyze the movement patterns of objects in real time and improve display accuracy based on that data. It can optimize the display algorithm based on past movement pattern data. It can learn the movement patterns of objects and build models to improve display accuracy. This allows for the analysis of object movement patterns and improvement of display accuracy.

[0055] The replacement display unit can prioritize the display of highly relevant objects based on the geographical location information of the object during replacement display. For example, the replacement display unit acquires the geographical location information of an object and prioritizes the display of highly relevant objects based on that information. The replacement display unit can also improve display accuracy by optimizing the method of acquiring location information. Furthermore, the replacement display unit can determine which objects to prioritize by setting relevance evaluation criteria. For example, if an object is in a specific region, the replacement display unit will prioritize the display of objects related to that region. If an object is in a tourist area, it will prioritize the display of objects related to tourist attractions. If an object is at home, it will prioritize the display of objects within the home. In this way, highly relevant objects can be prioritized based on the geographical location information of the object.

[0056] The replacement display unit can improve display accuracy by referring to related literature for objects during replacement display. For example, the replacement display unit can store related literature for objects in a database and optimize the display algorithm based on that data. Furthermore, the replacement display unit can construct an algorithm that prioritizes the display of specific display patterns from related literature. In addition, the replacement display unit can analyze related literature and extract patterns to improve display accuracy. For example, the replacement display unit optimizes the display algorithm based on related literature for objects. It constructs an algorithm that prioritizes the display of specific display patterns from related literature for objects. It analyzes related literature for objects and extracts patterns to improve display accuracy. This allows for improved display accuracy by referring to related literature for objects.

[0057] The agent unit can optimize its response algorithm by referring to the user's past instruction history when the agent responds. For example, the agent unit can store the user's past instruction history in a database and optimize the response algorithm based on that data. The agent unit can also build an algorithm that prioritizes responding with specific response patterns from the past instruction history. Furthermore, the agent unit can analyze the past instruction history and extract patterns to improve response accuracy. For example, the agent unit optimizes the response algorithm based on the user's past instruction history. It builds an algorithm that prioritizes responding with specific response patterns from the user's past instruction history. It analyzes the user's past instruction history and extracts patterns to improve response accuracy. This allows the agent unit to optimize the response algorithm by referring to the user's past instruction history.

[0058] The agent unit can improve response accuracy by analyzing patterns in user instructions during agent responses. For example, the agent unit can analyze user instruction patterns in real time and improve response accuracy based on that data. Furthermore, the agent unit can optimize response algorithms based on past instruction pattern data. In addition, the agent unit can learn user instruction patterns and build models to improve response accuracy. For example, the agent unit can analyze user instruction patterns in real time and improve response accuracy based on that data. It can optimize response algorithms based on past instruction pattern data. It can learn user instruction patterns and build models to improve response accuracy. This allows the agent unit to analyze user instruction patterns and improve response accuracy.

[0059] The agent unit can prioritize highly relevant responses based on the user's geographical location when responding to an agent. For example, the agent unit can acquire the user's geographical location and prioritize highly relevant responses based on that information. The agent unit can also improve response accuracy by optimizing the method of acquiring location information. Furthermore, the agent unit can determine which responses to prioritize by setting criteria for evaluating relevance. For example, if the user is in a specific region, the agent unit will prioritize responses related to that region. If the user is in a tourist area, it will prioritize responses related to tourist attractions. If the user is at home, it will prioritize responses related to the home. This allows the agent unit to prioritize highly relevant responses based on the user's geographical location.

[0060] The agent unit can analyze a user's social media activity and provide relevant responses when an agent responds. For example, the agent unit can store a user's social media activity in a database and provide relevant responses based on that data. The agent unit can also improve response accuracy by optimizing the method of collecting social media data. Furthermore, the agent unit can determine which responses to prioritize by setting criteria for evaluating relevance. For example, the agent unit can provide responses related to content the user has shown interest in on social media. It can analyze the content of the user's social media posts and provide relevant responses. It can provide responses related to content that the user's social media followers are interested in. In this way, the agent can analyze the user's social media activity and provide relevant responses.

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

[0062] AR display systems can personalize the displayed content by referencing the user's past behavior history. For example, if a user has previously preferred to display a particular character, the system can prioritize displaying that character. Similarly, if a user has preferred to display a particular landscape in a specific location, the system can prioritize displaying that landscape when the user is in that location. Furthermore, by analyzing the user's past behavior history, the system can provide new suggestions based on the user's preferences. This allows for a more personalized AR experience for the user.

[0063] The AR display system can dynamically change its displayed content based on the user's geographical location. For example, if the user is in a tourist destination, the system can display scenery and characters related to that destination. If the user is at home, the system can display scenery and characters related to the home environment. Furthermore, if the user is participating in a specific event, the system can display scenery and characters related to that event. This allows for the provision of an optimal AR experience tailored to the user's current location.

[0064] AR display systems can analyze a user's social media activity and provide relevant content. For example, if a user shows interest in a particular character or landscape on social media, the system can prioritize displaying that character or landscape. It can also display content related to the interests of the user's social media followers. Furthermore, it can analyze the user's social media posts and provide new suggestions based on the user's interests. This allows for the provision of a personalized AR experience based on the user's social media activity.

[0065] The AR display system can optimize the agent's response algorithm by referring to the user's past instruction history. For example, if a user has frequently given a particular instruction in the past, the agent can prioritize responses to that instruction. It can also analyze the user's past instruction history and make new suggestions based on the user's preferences. Furthermore, it can extract patterns to improve the agent's response accuracy based on the user's past instruction history. This allows the system to provide optimal agent responses based on the user's past instruction history.

[0066] The AR display system can analyze user instruction patterns in real time and improve the agent's response accuracy based on that data. For example, when a user gives a specific instruction, the system can analyze the instruction pattern in real time and provide the optimal response. It can also optimize the agent's response algorithm based on past instruction pattern data. Furthermore, it can build a model to learn user instruction patterns and improve response accuracy. This allows the system to provide the optimal agent response based on the user's instruction patterns.

[0067] The AR display system can dynamically change the agent's response based on the user's geographical location. For example, if the user is in a tourist destination, the agent can prioritize providing information related to that destination. If the user is at home, the agent can prioritize providing information related to the home. Furthermore, if the user is participating in a specific event, the agent can prioritize providing information related to that event. This allows for the provision of the most appropriate agent response based on the user's current location.

[0068] The AR display system can analyze a user's social media activity and dynamically change the agent's response. For example, if a user shows interest in a particular topic on social media, the agent can prioritize providing information related to that topic. It can also provide information related to what the user's social media followers are interested in. Furthermore, it can analyze the user's social media posts and make new suggestions based on the user's interests. This allows for the provision of optimal agent responses based on the user's social media activity.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The object recognition unit recognizes objects. The object recognition unit recognizes objects using, for example, image processing technology, machine learning algorithms, and deep learning technology. Image processing technology is used to detect and recognize objects from images captured by a camera. Machine learning algorithms build models for recognizing objects based on past data and recognize objects with high accuracy even with new data. Deep learning technology uses multi-layered neural networks to recognize objects and detect complex patterns with high accuracy. Step 2: The posture estimation unit estimates the posture of the object recognized by the object recognition unit. The posture estimation unit estimates the posture of the object using, for example, a 3D model, a method for calculating joint angles, or a skeletal model. The 3D model is used to estimate the position and orientation of the object. The method for calculating joint angles calculates the angles of the object's joints and estimates the posture based on those angles. The skeletal model estimates the posture based on the object's skeletal structure and reproduces complex movements with high accuracy. Step 3: The tracking unit tracks the object estimated by the attitude estimation unit. The tracking unit tracks the object using, for example, a camera, sensors, and an algorithm. The camera tracks the object's position and movement in real time. The sensors detect the object's movement and track the object based on that data. The algorithm analyzes the object's movement pattern and tracks the object based on that pattern. Step 4: The replacement display unit replaces and displays the object tracked by the tracking unit. The replacement display unit replaces and displays the object using, for example, AR technology, 3D models, or video. Using AR technology, real-world objects are replaced and displayed with virtual characters or landscapes. 3D models overlay virtual objects onto real-world objects to provide a realistic experience. Videos overlay virtual landscapes or characters onto real-world landscapes to provide visual enjoyment. Step 5: The agent unit receives instructions from the user. The agent unit receives user instructions using, for example, voice recognition technology, touch operation, and gesture recognition technology. Voice recognition technology analyzes the user's voice instructions and controls the system based on those instructions. Touch operation allows the user to input instructions by touching the screen, and controls the system based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements.

[0071] (Example of form 2) An AR display system according to an embodiment of the present invention is a system that replaces pedestrians and vehicles in a city with celebrities or favorite characters and displays them in AR. This AR display system uses object recognition and posture estimation technology to track and replace objects. In addition, the appearance of furniture and interior design in a room can be changed to suit the user's preference, and the view from the window can be freely specified. Furthermore, it is compatible not only with AR glasses but also with AR contact lenses that are expected to be developed in the future. Settings can be changed at any time by calling on the agent. For example, the user can call on the agent to change the settings. For example, the user might say, "Change the interior to a Swiss lakeside lodge. Change the window too, please." Based on this instruction, the camera in the AR glasses recognizes objects, and the appearance of furniture, etc., is replaced with something suitable for the lodge's interior and displayed. At the same time, the view from the window is set to show a Swiss lakeside. Next, when the user goes outside to commute, they can instruct the agent to "Make all the people and vehicles in the city look like a specific character." Based on this instruction, the camera in the AR glasses recognizes objects and people's postures, and people and vehicles in the city are replaced with characters or carriages that look like the specific character and displayed. This system combines image recognition-based tracking and pose estimation with augmented reality (AR) to replace and display objects in the city. It targets people who want to feel more cheerful while at home or commuting, aiming to boost their mood. The market size is projected to be several trillion yen, comparable to that of smartwatches. With advancements in image recognition, speech recognition, and large-scale language models, the technology is now catching up, making it the ideal time to enter the market. This allows the AR display system to replace pedestrians and vehicles in the city with celebrities or favorite characters in augmented reality.

[0072] The AR display system according to this embodiment comprises an object recognition unit, a pose estimation unit, a tracking unit, a replacement display unit, and an agent unit. The object recognition unit recognizes objects. The object recognition unit recognizes objects using, for example, image processing technology. The object recognition unit can also recognize objects using machine learning algorithms. Furthermore, the object recognition unit can also recognize objects using deep learning technology. For example, the object recognition unit uses image processing technology to detect objects from images captured by a camera and recognizes those objects. Machine learning algorithms build models for recognizing objects based on past data and recognize objects with high accuracy even with new data. Deep learning technology uses multi-layer neural networks to recognize objects and detect complex patterns with high accuracy. The pose estimation unit estimates the pose of the object recognized by the object recognition unit. The pose estimation unit estimates the pose of the object using, for example, a 3D model. Furthermore, the pose estimation unit can also estimate the pose of the object using a method for calculating joint angles. Furthermore, the pose estimation unit can also estimate the pose of the object using a skeletal model. For example, the posture estimation unit estimates the position and orientation of an object using a 3D model. The joint angle calculation method calculates the angles of the object's joints and estimates the posture based on those angles. The skeletal model estimates the posture based on the object's skeletal structure and reproduces complex movements with high accuracy. The tracking unit tracks the object estimated by the posture estimation unit. The tracking unit tracks the object using, for example, a camera. The tracking unit can also track the object using sensors. Furthermore, the tracking unit can also track the object using algorithms. For example, the tracking unit tracks the position and movement of an object in real time using a camera. Sensors detect the movement of an object and track the object based on that data. Algorithms analyze the movement patterns of an object and track the object based on those patterns. The replacement display unit replaces and displays the object tracked by the tracking unit. The replacement display unit replaces and displays the object using, for example, AR technology. The replacement display unit can also replace and display the object using a 3D model.Furthermore, the replacement display unit can also replace objects using video. For example, the replacement display unit can use AR technology to replace real-world objects with virtual characters or landscapes. 3D models overlay virtual objects onto real-world objects to provide a realistic experience. Videos overlay virtual landscapes or characters onto real-world landscapes to provide visual enjoyment. The agent unit receives instructions from the user. The agent unit receives user instructions using, for example, speech recognition technology. The agent unit can also receive user instructions using touch operations. Furthermore, the agent unit can also receive user instructions using gesture recognition technology. For example, the agent unit uses speech recognition technology to analyze the user's voice instructions and control the system based on those instructions. Touch operations allow the user to input instructions by touching the screen and control the system based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements. As a result, the AR display system according to the embodiment is capable of object recognition, posture estimation, tracking, replacement display, and receiving instructions from the user.

[0073] The object recognition unit recognizes objects. For example, the object recognition unit recognizes objects using image processing techniques. Furthermore, the object recognition unit can also recognize objects using machine learning algorithms. In addition, the object recognition unit can recognize objects using deep learning techniques. For example, the object recognition unit uses image processing techniques to detect and recognize objects from images captured by a camera. Machine learning algorithms build object recognition models based on past data and recognize objects with high accuracy even with new data. Deep learning techniques use multi-layered neural networks to recognize objects and detect complex patterns with high accuracy. By combining these techniques, the object recognition unit can maintain high recognition accuracy even in various environments and conditions. For example, image processing techniques extract object features using methods such as edge detection and contour extraction, and machine learning algorithms classify the type and attributes of objects based on those features. Deep learning techniques perform more advanced feature extraction, enabling accurate object recognition from complex objects and backgrounds. The object recognition unit utilizes these techniques to recognize objects in real time, improving the overall accuracy and efficiency of the system. Furthermore, the object recognition unit can share recognition results with other units, strengthening the overall system coordination. For example, information on recognized objects can be transmitted to the pose estimation unit and tracking unit, where it is used as foundational data for more accurate processing. This allows the object recognition unit to improve the overall system performance and provide users with a higher quality AR experience.

[0074] The posture estimation unit estimates the posture of an object recognized by the object recognition unit. The posture estimation unit can estimate the posture of an object using, for example, a 3D model. It can also estimate the posture of an object using a joint angle calculation method. Furthermore, it can estimate the posture of an object using a skeletal model. For example, the posture estimation unit uses a 3D model to estimate the position and orientation of an object. The joint angle calculation method calculates the angles of the object's joints and estimates the posture based on those angles. The skeletal model estimates the posture based on the object's skeletal structure and reproduces complex movements with high accuracy. By combining these technologies, the posture estimation unit can estimate the posture of various objects with high accuracy. For example, a 3D model represents the shape and structure of an object in detail and accurately estimates the object's position and orientation based on that information. The joint angle calculation method analyzes the movement of the object's joints and estimates the posture based on that movement. The skeletal model can analyze the object's skeletal structure in detail and reproduce complex movements with high accuracy. The pose estimation unit utilizes these technologies to estimate the object's pose in real time, improving the overall accuracy and efficiency of the system. Furthermore, the pose estimation unit can share the estimation results with other units, strengthening the overall system coordination. For example, the estimated object's pose information can be transmitted to the tracking unit and the replacement display unit, where it is used as foundational data for more accurate processing. This allows the pose estimation unit to improve the overall system performance and provide users with a higher quality AR experience.

[0075] The tracking unit tracks the object estimated by the attitude estimation unit. The tracking unit can track the object using, for example, a camera. It can also track the object using sensors. Furthermore, the tracking unit can track the object using algorithms. For example, the tracking unit uses a camera to track the object's position and movement in real time. Sensors detect the object's movement and track it based on that data. Algorithms analyze the object's movement patterns and track it based on those patterns. By combining these technologies, the tracking unit can maintain high tracking accuracy even in various environments and conditions. For example, a camera captures the object's position and movement in detail and tracks it in real time based on that information. Sensors detect the object's movement and track it based on that data. Algorithms analyze the object's movement patterns and track it based on those patterns. The tracking unit utilizes these technologies to track objects in real time, improving the overall accuracy and efficiency of the system. Furthermore, the tracking unit can share tracking results with other departments, strengthening overall system collaboration. For example, information about tracked objects is transmitted to the replacement display unit and agent unit, where it is used as foundational data for more accurate processing. This allows the tracking unit to improve the overall system performance and provide users with a higher quality AR experience.

[0076] The replacement display unit replaces and displays objects tracked by the tracking unit. The replacement display unit can replace and display objects using, for example, AR technology. It can also replace and display objects using 3D models. Furthermore, it can replace and display objects using video. For example, the replacement display unit uses AR technology to replace real-world objects with virtual characters or landscapes. 3D models overlay virtual objects onto real-world objects, providing a realistic experience. Video overlays virtual landscapes or characters onto real-world landscapes, providing visual enjoyment. By combining these technologies, the replacement display unit can maintain high display accuracy even in various environments and conditions. For example, AR technology replaces real-world objects with virtual characters or landscapes, providing users with a new experience. 3D models overlay virtual objects onto real-world objects, providing a realistic experience. Video overlays virtual landscapes or characters onto real-world landscapes, providing visual enjoyment. The replacement display unit utilizes these technologies to replace and display objects in real time, improving the overall accuracy and efficiency of the system. Furthermore, the replacement display unit can share display results with other departments, strengthening the overall system collaboration. For example, information on the replaced and displayed objects is transmitted to the agent unit and used as basic data for the agent unit to perform more accurate processing. As a result, the replacement display unit can improve the overall system performance and provide users with a higher quality AR experience.

[0077] The agent unit receives instructions from the user. For example, the agent unit can receive user instructions using speech recognition technology. It can also receive user instructions using touch operations. Furthermore, the agent unit can receive user instructions using gesture recognition technology. For example, the agent unit uses speech recognition technology to analyze the user's voice instructions and control the system based on those instructions. Touch operations allow the user to input instructions by touching the screen, and the system controls based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements. By combining these technologies, the agent unit can maintain high instruction reception accuracy even in various environments and conditions. For example, speech recognition technology analyzes the user's voice instructions and controls the system based on those instructions. Touch operations allow the user to input instructions by touching the screen, and the system controls based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements. The agent unit utilizes these technologies to receive user instructions in real time and improve the overall accuracy and efficiency of the system. Furthermore, the agent unit can share instruction results with other units, strengthening the overall system coordination. For example, received user instructions can be transmitted to the object recognition unit and the pose estimation unit, where they are used as foundational data for more accurate processing. This allows the agent unit to improve the overall system performance and provide users with a higher quality AR experience.

[0078] The replacement display unit can change the appearance and interior of a room's furniture. For example, it can use AR technology to change the appearance of a room's furniture. It can also change the interior of a room using 3D models. Furthermore, it can change the atmosphere of a room using video. For example, it can use AR technology to replace real furniture with virtual furniture. 3D models overlay virtual furniture and interiors onto a real room, providing a realistic experience. Videos overlay virtual scenery and interiors onto a real room, providing visual enjoyment. This allows for changes to the appearance and interior of a room's furniture.

[0079] The replacement display unit can change the view from the window. For example, the replacement display unit can change the view from the window using AR technology. It can also change the view from the window using video. Furthermore, it can change the view from the window using 3D models. For example, the replacement display unit uses AR technology to replace the real-world view with a virtual one. Video overlays a virtual landscape onto the real window, providing visual enjoyment. 3D models overlay a virtual landscape onto the real window, providing a realistic experience. This allows the view from the window to be changed.

[0080] The agent unit can support AR glasses and AR contact lenses. For example, the agent unit supports AR glasses by ensuring device compatibility. It can also support AR contact lenses by applying a communication protocol. Furthermore, the agent unit can support new devices through software updates. For instance, to ensure compatibility with AR glasses, the agent unit configures itself to match the device's specifications. The communication protocol is a set of rules for exchanging data between the AR contact lens and the agent unit, enabling smooth communication. Software updates allow the agent unit to support new devices as they emerge. This enables support for both AR glasses and AR contact lenses.

[0081] The agent unit can change settings based on user instructions. For example, the agent unit can receive user instructions using speech recognition technology and change settings based on those instructions. The agent unit can also receive user instructions using touch operation and change settings based on those instructions. Furthermore, the agent unit can receive user instructions using gesture recognition technology and change settings based on those instructions. For example, the agent unit can use speech recognition technology to analyze the user's voice instructions and change system settings based on those instructions. Touch operation allows the user to input instructions by touching the screen, and the system settings are changed based on those instructions. Gesture recognition technology detects the user's hand movements and changes system settings based on those movements. This allows the system to change settings based on user instructions.

[0082] The object recognition unit can recognize objects using the camera built into the AR glasses. For example, the object recognition unit can photograph an object using the camera built into the AR glasses, analyze the image data, and recognize the object. Furthermore, the object recognition unit can perform more detailed object recognition by increasing the camera resolution. In addition, the object recognition unit can improve the accuracy of object recognition by optimizing the recognition algorithm. For example, the object recognition unit can photograph pedestrians and vehicles in a city using the camera built into the AR glasses, analyze the image data, and recognize the objects. By increasing the camera resolution, distant objects and small objects can be recognized with high accuracy. The recognition algorithm extracts the features of an object and identifies the object based on those features. This allows objects to be recognized using the camera built into the AR glasses.

[0083] The posture estimation unit can estimate the posture of an object using the camera mounted on the AR glasses. For example, the posture estimation unit takes a picture of an object using the camera mounted on the AR glasses, analyzes the image data, and estimates the object's posture. Furthermore, the posture estimation unit can perform more detailed posture estimation by increasing the camera resolution. In addition, the posture estimation unit can improve the accuracy of posture estimation by optimizing the posture estimation algorithm. For example, the posture estimation unit takes a picture of pedestrians or vehicles in a city using the camera mounted on the AR glasses, analyzes the image data, and estimates the object's posture. By increasing the camera resolution, the posture of distant or small objects can also be estimated with high accuracy. The posture estimation algorithm calculates the joint angles and positions of the object and estimates the posture based on that data. This allows the posture of an object to be estimated using the camera mounted on the AR glasses.

[0084] The object recognition unit can estimate the user's emotions and adjust the accuracy of object recognition based on the estimated emotions. For example, the object recognition unit estimates the user's emotions using an emotion estimation algorithm. Furthermore, the object recognition unit can adjust the accuracy of object recognition based on the estimated emotions. In addition, the object recognition unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the object recognition unit increases the accuracy of object recognition and provides detailed information. If the user is stressed, it decreases the accuracy of object recognition and provides simplified information. If the user is excited, it adjusts the accuracy of object recognition to a moderate level and provides appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows the accuracy of object recognition to be adjusted based on the user's emotions.

[0085] The object recognition unit can optimize its recognition algorithm by referring to the user's past recognition history during object recognition. For example, the object recognition unit can store the user's past recognition history in a database and optimize the recognition algorithm based on that data. Furthermore, the object recognition unit can construct an algorithm that prioritizes the recognition of specific objects based on past recognition history. In addition, the object recognition unit can analyze past recognition history and extract patterns to improve recognition accuracy. For example, the object recognition unit optimizes its recognition algorithm based on data of objects the user has recognized in the past. It constructs an algorithm that prioritizes the recognition of specific objects based on the user's past recognition history. It analyzes the user's past recognition history and extracts patterns to improve recognition accuracy. This allows the recognition algorithm to be optimized by referring to the user's past recognition history.

[0086] The object recognition unit can improve recognition accuracy by analyzing the movement patterns of objects during object recognition. For example, the object recognition unit can analyze the movement patterns of objects in real time and improve recognition accuracy based on that data. Furthermore, the object recognition unit can optimize its recognition algorithm based on past movement pattern data. In addition, the object recognition unit can learn the movement patterns of objects and build models to improve recognition accuracy. For example, the object recognition unit analyzes the movement patterns of objects in real time and improves recognition accuracy based on that data. It optimizes its recognition algorithm based on past movement pattern data. It learns the movement patterns of objects and builds models to improve recognition accuracy. This allows it to analyze the movement patterns of objects and improve recognition accuracy.

[0087] The object recognition unit can estimate the user's emotions and determine the priority of objects to recognize based on the estimated emotions. For example, the object recognition unit estimates the user's emotions using an emotion estimation algorithm. It can also determine the priority of objects to recognize based on the estimated emotions. Furthermore, the object recognition unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the object recognition unit will prioritize recognizing objects of interest. If the user is stressed, it will prioritize recognizing important objects. If the user is excited, it will prioritize recognizing visually stimulating objects. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the determination of the priority of objects to recognize based on the user's emotions.

[0088] The object recognition unit can prioritize the recognition of highly relevant objects based on the user's geographical location information during object recognition. For example, the object recognition unit acquires the user's geographical location information and prioritizes the recognition of highly relevant objects based on that information. The object recognition unit can also improve recognition accuracy by optimizing the method of acquiring location information. Furthermore, the object recognition unit can determine which objects to prioritize for recognition by setting criteria for evaluating relevance. For example, if the user is in a specific region, the object recognition unit will prioritize the recognition of objects related to that region. If the user is in a tourist area, it will prioritize the recognition of tourist attractions. If the user is at home, it will prioritize the recognition of objects within the home. This allows the object recognition unit to prioritize the recognition of highly relevant objects based on the user's geographical location information.

[0089] The object recognition unit can analyze the user's social media activity and recognize related objects during object recognition. For example, the object recognition unit can store the user's social media activity in a database and recognize related objects based on that data. The object recognition unit can also improve recognition accuracy by optimizing the method of collecting social media data. Furthermore, the object recognition unit can determine which objects to recognize preferentially by setting criteria for evaluating relevance. For example, the object recognition unit may preferentially recognize objects that the user has shown interest in on social media. It can analyze the content of the user's social media posts and recognize related objects. It can recognize objects that the user's social media followers are interested in. In this way, it can analyze the user's social media activity and recognize related objects.

[0090] The posture estimation unit can estimate the user's emotions and adjust the accuracy of posture estimation based on the estimated emotions. For example, the posture estimation unit estimates the user's emotions using an emotion estimation algorithm. Furthermore, the posture estimation unit can adjust the accuracy of posture estimation based on the estimated emotions. In addition, the posture estimation unit can accumulate user emotion data and analyze long-term emotional trends. For example, when the user is relaxed, the posture estimation unit increases the accuracy of posture estimation and provides detailed information. When the user is stressed, it decreases the accuracy of posture estimation and provides simplified information. When the user is excited, it adjusts the accuracy of posture estimation to a moderate level and provides appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows the accuracy of posture estimation to be adjusted based on the user's emotions.

[0091] The pose estimation unit can optimize its estimation algorithm by referring to the object's past pose data during pose estimation. For example, the pose estimation unit can store the object's past pose data in a database and optimize the estimation algorithm based on that data. The pose estimation unit can also construct an algorithm that prioritizes the estimation of specific poses from past pose data. Furthermore, the pose estimation unit can analyze past pose data and extract patterns to improve estimation accuracy. For example, the pose estimation unit optimizes the estimation algorithm based on the object's past pose data. It constructs an algorithm that prioritizes the estimation of specific poses from the object's past pose data. It analyzes the object's past pose data and extracts patterns to improve estimation accuracy. This allows the estimation algorithm to be optimized by referring to the object's past pose data.

[0092] The pose estimation unit can improve estimation accuracy by analyzing the movement patterns of an object during pose estimation. For example, the pose estimation unit can analyze the movement patterns of an object in real time and improve estimation accuracy based on that data. Furthermore, the pose estimation unit can optimize the estimation algorithm based on past movement pattern data. In addition, the pose estimation unit can learn the movement patterns of an object and build a model to improve estimation accuracy. For example, the pose estimation unit can analyze the movement patterns of an object in real time and improve estimation accuracy based on that data. It can optimize the estimation algorithm based on past movement pattern data. It can learn the movement patterns of an object and build a model to improve estimation accuracy. This allows for improved estimation accuracy by analyzing the movement patterns of an object.

[0093] The posture estimation unit can estimate the user's emotions and determine the priority of postures to estimate based on the estimated user emotions. For example, the posture estimation unit estimates the user's emotions using an emotion estimation algorithm. Furthermore, the posture estimation unit can also determine the priority of postures to estimate based on the estimated user emotions. In addition, the posture estimation unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the posture estimation unit prioritizes estimating postures of interest. If the user is stressed, it prioritizes estimating important postures. If the user is excited, it prioritizes estimating visually stimulating postures. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the determination of the priority of postures to estimate based on the user's emotions.

[0094] The posture estimation unit can prioritize estimating postures that are highly relevant to an object based on its geographical location information. For example, the posture estimation unit acquires the object's geographical location information and prioritizes estimating postures that are highly relevant based on that information. The posture estimation unit can also improve estimation accuracy by optimizing the method of acquiring location information. Furthermore, the posture estimation unit can determine which postures to prioritize by setting criteria for evaluating relevance. For example, if an object is in a specific region, the posture estimation unit will prioritize estimating postures related to that region. If an object is in a tourist area, it will prioritize estimating postures at tourist attractions. If an object is at home, it will prioritize estimating postures within the home. This allows the posture estimation unit to prioritize estimating postures that are highly relevant based on the object's geographical location information.

[0095] The pose estimation unit can improve estimation accuracy by referring to relevant literature on the object during pose estimation. For example, the pose estimation unit can store relevant literature on the object in a database and optimize the estimation algorithm based on that data. The pose estimation unit can also construct an algorithm that prioritizes the estimation of a specific pose from the relevant literature. Furthermore, the pose estimation unit can analyze the relevant literature and extract patterns to improve estimation accuracy. For example, the pose estimation unit optimizes the estimation algorithm based on relevant literature on the object. It constructs an algorithm that prioritizes the estimation of a specific pose from the relevant literature on the object. It analyzes the relevant literature on the object and extracts patterns to improve estimation accuracy. This allows the pose estimation accuracy to be improved by referring to relevant literature on the object.

[0096] The tracking unit can estimate the user's emotions and adjust the tracking accuracy based on the estimated emotions. For example, the tracking unit estimates the user's emotions using an emotion estimation algorithm. Furthermore, the tracking unit can adjust the tracking accuracy based on the estimated emotions. In addition, the tracking unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the tracking unit increases tracking accuracy and provides detailed information. If the user is stressed, it decreases tracking accuracy and provides simplified information. If the user is excited, it adjusts tracking accuracy to a moderate level and provides appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows the tracking accuracy to be adjusted based on the user's emotions.

[0097] The tracking unit can optimize the tracking algorithm by referring to the object's past tracking data during tracking. For example, the tracking unit can store the object's past tracking data in a database and optimize the tracking algorithm based on that data. Furthermore, the tracking unit can construct an algorithm that prioritizes tracking specific objects based on past tracking data. In addition, the tracking unit can analyze past tracking data and extract patterns to improve tracking accuracy. For example, the tracking unit optimizes the tracking algorithm based on the object's past tracking data. It constructs an algorithm that prioritizes tracking specific objects based on the object's past tracking data. It analyzes the object's past tracking data and extracts patterns to improve tracking accuracy. This allows the tracking algorithm to be optimized by referring to the object's past tracking data.

[0098] The tracking unit can improve tracking accuracy by analyzing the movement patterns of objects during tracking. For example, the tracking unit can analyze the movement patterns of objects in real time and improve tracking accuracy based on that data. Furthermore, the tracking unit can optimize the tracking algorithm based on past movement pattern data. In addition, the tracking unit can learn the movement patterns of objects and build models to improve tracking accuracy. For example, the tracking unit can analyze the movement patterns of objects in real time and improve tracking accuracy based on that data. It can optimize the tracking algorithm based on past movement pattern data. It can learn the movement patterns of objects and build models to improve tracking accuracy. This allows for improved tracking accuracy by analyzing the movement patterns of objects.

[0099] The tracking unit can estimate the user's emotions and determine the priority of objects to track based on the estimated emotions. For example, the tracking unit estimates the user's emotions using an emotion estimation algorithm. It can also determine the priority of objects to track based on the estimated emotions. Furthermore, the tracking unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the tracking unit prioritizes tracking objects of interest. If the user is stressed, it prioritizes tracking important objects. If the user is excited, it prioritizes tracking visually stimulating objects. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the determination of the priority of objects to track based on the user's emotions.

[0100] The tracking unit can prioritize tracking highly relevant objects based on the object's geographical location information during tracking. For example, the tracking unit acquires the object's geographical location information and uses that information to prioritize tracking highly relevant objects. The tracking unit can also improve tracking accuracy by optimizing the method of acquiring location information. Furthermore, the tracking unit can determine which objects to prioritize tracking by setting criteria for evaluating relevance. For example, if the object is in a specific region, the tracking unit will prioritize tracking objects related to that region. If the object is in a tourist area, it will prioritize tracking objects related to tourist attractions. If the object is at home, it will prioritize tracking objects within the home. This allows for the priority tracking of highly relevant objects based on the object's geographical location information.

[0101] The tracking unit can improve tracking accuracy by referring to relevant literature for objects during tracking. For example, the tracking unit can store relevant literature for objects in a database and optimize the tracking algorithm based on that data. The tracking unit can also construct an algorithm that prioritizes tracking specific objects based on the relevant literature. Furthermore, the tracking unit can analyze the relevant literature and extract patterns to improve tracking accuracy. For example, the tracking unit optimizes the tracking algorithm based on relevant literature for objects. It constructs an algorithm that prioritizes tracking specific objects based on relevant literature. It analyzes the relevant literature for objects and extracts patterns to improve tracking accuracy. This allows for improved tracking accuracy by referring to relevant literature for objects.

[0102] The replacement display unit can estimate the user's emotions and adjust the replacement display method based on the estimated user emotions. For example, the replacement display unit estimates the user's emotions using an emotion estimation algorithm. Furthermore, the replacement display unit can adjust the replacement display method based on the estimated user emotions. In addition, the replacement display unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the replacement display unit displays characters or scenery with a calming atmosphere. If the user is stressed, it displays characters or scenery with a calming effect. If the user is excited, it displays characters or scenery that are visually stimulating. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows the replacement display method to be adjusted based on the user's emotions.

[0103] The replacement display unit can optimize its display algorithm by referring to the object's past display data during replacement display. For example, the replacement display unit can store the object's past display data in a database and optimize the display algorithm based on that data. Furthermore, the replacement display unit can construct an algorithm that prioritizes the display of specific display patterns from past display data. In addition, the replacement display unit can analyze past display data and extract patterns to improve display accuracy. For example, the replacement display unit optimizes the display algorithm based on the object's past display data. It constructs an algorithm that prioritizes the display of specific display patterns from the object's past display data. It analyzes the object's past display data and extracts patterns to improve display accuracy. This allows the display algorithm to be optimized by referring to the object's past display data.

[0104] The replacement display unit can improve display accuracy by analyzing the movement patterns of objects during replacement display. For example, the replacement display unit can analyze the movement patterns of objects in real time and improve display accuracy based on that data. Furthermore, the replacement display unit can optimize the display algorithm based on past movement pattern data. In addition, the replacement display unit can learn the movement patterns of objects and build models to improve display accuracy. For example, the replacement display unit can analyze the movement patterns of objects in real time and improve display accuracy based on that data. It can optimize the display algorithm based on past movement pattern data. It can learn the movement patterns of objects and build models to improve display accuracy. This allows for the analysis of object movement patterns and improvement of display accuracy.

[0105] The replacement display unit can estimate the user's emotions and determine the priority of objects to display based on the estimated user emotions. For example, the replacement display unit estimates the user's emotions using an emotion estimation algorithm. It can also determine the priority of objects to display based on the estimated user emotions. Furthermore, the replacement display unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the replacement display unit will prioritize displaying objects of interest. If the user is stressed, it will prioritize displaying objects with a calming effect. If the user is excited, it will prioritize displaying visually stimulating objects. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows the priority of objects to be displayed based on the user's emotions.

[0106] The replacement display unit can prioritize the display of highly relevant objects based on the geographical location information of the object during replacement display. For example, the replacement display unit acquires the geographical location information of an object and prioritizes the display of highly relevant objects based on that information. The replacement display unit can also improve display accuracy by optimizing the method of acquiring location information. Furthermore, the replacement display unit can determine which objects to prioritize by setting relevance evaluation criteria. For example, if an object is in a specific region, the replacement display unit will prioritize the display of objects related to that region. If an object is in a tourist area, it will prioritize the display of objects related to tourist attractions. If an object is at home, it will prioritize the display of objects within the home. In this way, highly relevant objects can be prioritized based on the geographical location information of the object.

[0107] The replacement display unit can improve display accuracy by referring to related literature for objects during replacement display. For example, the replacement display unit can store related literature for objects in a database and optimize the display algorithm based on that data. Furthermore, the replacement display unit can construct an algorithm that prioritizes the display of specific display patterns from related literature. In addition, the replacement display unit can analyze related literature and extract patterns to improve display accuracy. For example, the replacement display unit optimizes the display algorithm based on related literature for objects. It constructs an algorithm that prioritizes the display of specific display patterns from related literature for objects. It analyzes related literature for objects and extracts patterns to improve display accuracy. This allows for improved display accuracy by referring to related literature for objects.

[0108] The agent unit can estimate the user's emotions and adjust its response method based on the estimated emotions. For example, the agent unit can estimate the user's emotions using an emotion estimation algorithm. Furthermore, the agent unit can adjust its response method based on the estimated emotions. In addition, the agent unit can accumulate user emotion data and analyze long-term emotional trends. For example, the agent unit will respond in a calm voice if the user is relaxed; in a soothing voice if the user is stressed; and in a cheerful voice if the user is excited. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows the agent's response method to be adjusted based on the user's emotions.

[0109] The agent unit can optimize its response algorithm by referring to the user's past instruction history when the agent responds. For example, the agent unit can store the user's past instruction history in a database and optimize the response algorithm based on that data. The agent unit can also build an algorithm that prioritizes responding with specific response patterns from the past instruction history. Furthermore, the agent unit can analyze the past instruction history and extract patterns to improve response accuracy. For example, the agent unit optimizes the response algorithm based on the user's past instruction history. It builds an algorithm that prioritizes responding with specific response patterns from the user's past instruction history. It analyzes the user's past instruction history and extracts patterns to improve response accuracy. This allows the agent unit to optimize the response algorithm by referring to the user's past instruction history.

[0110] The agent unit can improve response accuracy by analyzing patterns in user instructions during agent responses. For example, the agent unit can analyze user instruction patterns in real time and improve response accuracy based on that data. Furthermore, the agent unit can optimize response algorithms based on past instruction pattern data. In addition, the agent unit can learn user instruction patterns and build models to improve response accuracy. For example, the agent unit can analyze user instruction patterns in real time and improve response accuracy based on that data. It can optimize response algorithms based on past instruction pattern data. It can learn user instruction patterns and build models to improve response accuracy. This allows the agent unit to analyze user instruction patterns and improve response accuracy.

[0111] The agent unit can estimate the user's emotions and determine the agent's response priority based on the estimated user emotions. For example, the agent unit can estimate the user's emotions using an emotion estimation algorithm. Furthermore, the agent unit can determine the agent's response priority based on the estimated user emotions. In addition, the agent unit can accumulate user emotion data and analyze long-term emotional trends. For example, if the user is relaxed, the agent unit will prioritize responses of interest. If the user is stressed, it will prioritize important responses. If the user is excited, it will prioritize visually stimulating responses. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows the agent to determine the agent's response priority based on the user's emotions.

[0112] The agent unit can prioritize highly relevant responses based on the user's geographical location when responding to an agent. For example, the agent unit can acquire the user's geographical location and prioritize highly relevant responses based on that information. The agent unit can also improve response accuracy by optimizing the method of acquiring location information. Furthermore, the agent unit can determine which responses to prioritize by setting criteria for evaluating relevance. For example, if the user is in a specific region, the agent unit will prioritize responses related to that region. If the user is in a tourist area, it will prioritize responses related to tourist attractions. If the user is at home, it will prioritize responses related to the home. This allows the agent unit to prioritize highly relevant responses based on the user's geographical location.

[0113] The agent unit can analyze a user's social media activity and provide relevant responses when an agent responds. For example, the agent unit can store a user's social media activity in a database and provide relevant responses based on that data. The agent unit can also improve response accuracy by optimizing the method of collecting social media data. Furthermore, the agent unit can determine which responses to prioritize by setting criteria for evaluating relevance. For example, the agent unit can provide responses related to content the user has shown interest in on social media. It can analyze the content of the user's social media posts and provide relevant responses. It can provide responses related to content that the user's social media followers are interested in. In this way, the agent can analyze the user's social media activity and provide relevant responses.

[0114] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0115] The AR display system can estimate the user's emotions and dynamically change the displayed content based on those emotions. For example, if the user is relaxed, the system can display calming scenery or characters. If the user is stressed, the system can display soothing scenery or characters. If the user is excited, the system can display visually stimulating scenery or characters. This allows the system to provide an optimal AR experience tailored to the user's emotions.

[0116] AR display systems can personalize the displayed content by referencing the user's past behavior history. For example, if a user has previously preferred to display a particular character, the system can prioritize displaying that character. Similarly, if a user has preferred to display a particular landscape in a specific location, the system can prioritize displaying that landscape when the user is in that location. Furthermore, by analyzing the user's past behavior history, the system can provide new suggestions based on the user's preferences. This allows for a more personalized AR experience for the user.

[0117] The AR display system can dynamically change its displayed content based on the user's geographical location. For example, if the user is in a tourist destination, the system can display scenery and characters related to that destination. If the user is at home, the system can display scenery and characters related to the home environment. Furthermore, if the user is participating in a specific event, the system can display scenery and characters related to that event. This allows for the provision of an optimal AR experience tailored to the user's current location.

[0118] AR display systems can analyze a user's social media activity and provide relevant content. For example, if a user shows interest in a particular character or landscape on social media, the system can prioritize displaying that character or landscape. It can also display content related to the interests of the user's social media followers. Furthermore, it can analyze the user's social media posts and provide new suggestions based on the user's interests. This allows for the provision of a personalized AR experience based on the user's social media activity.

[0119] The AR display system can estimate the user's emotions and adjust the agent's response based on those emotions. For example, if the user is relaxed, the agent can respond in a calm voice. If the user is stressed, the agent can respond in a soothing voice. If the user is excited, the agent can respond in a cheerful voice. This allows the system to provide the most appropriate agent response for the user's emotions.

[0120] The AR display system can optimize the agent's response algorithm by referring to the user's past instruction history. For example, if a user has frequently given a particular instruction in the past, the agent can prioritize responses to that instruction. It can also analyze the user's past instruction history and make new suggestions based on the user's preferences. Furthermore, it can extract patterns to improve the agent's response accuracy based on the user's past instruction history. This allows the system to provide optimal agent responses based on the user's past instruction history.

[0121] The AR display system can analyze user instruction patterns in real time and improve the agent's response accuracy based on that data. For example, when a user gives a specific instruction, the system can analyze the instruction pattern in real time and provide the optimal response. It can also optimize the agent's response algorithm based on past instruction pattern data. Furthermore, it can build a model to learn user instruction patterns and improve response accuracy. This allows the system to provide the optimal agent response based on the user's instruction patterns.

[0122] The AR display system can estimate the user's emotions and determine the agent's response priorities based on those emotions. For example, if the user is relaxed, the agent can prioritize responses that interest them. If the user is stressed, the agent can prioritize important responses. If the user is excited, the agent can prioritize visually stimulating responses. This allows the system to provide optimal agent responses based on the user's emotions.

[0123] The AR display system can dynamically change the agent's response based on the user's geographical location. For example, if the user is in a tourist destination, the agent can prioritize providing information related to that destination. If the user is at home, the agent can prioritize providing information related to the home. Furthermore, if the user is participating in a specific event, the agent can prioritize providing information related to that event. This allows for the provision of the most appropriate agent response based on the user's current location.

[0124] The AR display system can analyze a user's social media activity and dynamically change the agent's response. For example, if a user shows interest in a particular topic on social media, the agent can prioritize providing information related to that topic. It can also provide information related to what the user's social media followers are interested in. Furthermore, it can analyze the user's social media posts and make new suggestions based on the user's interests. This allows for the provision of optimal agent responses based on the user's social media activity.

[0125] The following briefly describes the processing flow for example form 2.

[0126] Step 1: The object recognition unit recognizes objects. The object recognition unit recognizes objects using, for example, image processing technology, machine learning algorithms, and deep learning technology. Image processing technology is used to detect and recognize objects from images captured by a camera. Machine learning algorithms build models for recognizing objects based on past data and recognize objects with high accuracy even with new data. Deep learning technology uses multi-layered neural networks to recognize objects and detect complex patterns with high accuracy. Step 2: The posture estimation unit estimates the posture of the object recognized by the object recognition unit. The posture estimation unit estimates the posture of the object using, for example, a 3D model, a method for calculating joint angles, or a skeletal model. The 3D model is used to estimate the position and orientation of the object. The method for calculating joint angles calculates the angles of the object's joints and estimates the posture based on those angles. The skeletal model estimates the posture based on the object's skeletal structure and reproduces complex movements with high accuracy. Step 3: The tracking unit tracks the object estimated by the attitude estimation unit. The tracking unit tracks the object using, for example, a camera, sensors, and an algorithm. The camera tracks the object's position and movement in real time. The sensors detect the object's movement and track the object based on that data. The algorithm analyzes the object's movement pattern and tracks the object based on that pattern. Step 4: The replacement display unit replaces and displays the object tracked by the tracking unit. The replacement display unit replaces and displays the object using, for example, AR technology, 3D models, or video. Using AR technology, real-world objects are replaced and displayed with virtual characters or landscapes. 3D models overlay virtual objects onto real-world objects to provide a realistic experience. Videos overlay virtual landscapes or characters onto real-world landscapes to provide visual enjoyment. Step 5: The agent unit receives instructions from the user. The agent unit receives user instructions using, for example, voice recognition technology, touch operation, and gesture recognition technology. Voice recognition technology analyzes the user's voice instructions and controls the system based on those instructions. Touch operation allows the user to input instructions by touching the screen, and controls the system based on those instructions. Gesture recognition technology detects the user's hand movements and controls the system based on those movements.

[0127] 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.

[0128] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0129] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the object recognition unit, pose estimation unit, tracking unit, replacement display unit, and agent unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the object recognition unit is implemented by the camera 42 and processor 46 of the smart device 14, and recognizes an object by analyzing an image captured by the camera 42. The pose estimation unit is implemented by the identification processing unit 290 of the data processing unit 12, and estimates the pose of the object recognized by the object recognition unit. The tracking unit is implemented by the processor 46 of the smart device 14, and tracks the object estimated by the pose estimation unit in real time. The replacement display unit is implemented by the display 40A of the smart device 14, and displays the object tracked by the tracking unit by replacing it with a virtual character or landscape. The agent unit is implemented by the microphone 38B and touch panel 38A of the smart device 14, and accepts user voice commands and touch operations. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0131] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0132] 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.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] 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.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] 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.

[0138] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] 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.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the object recognition unit, pose estimation unit, tracking unit, replacement display unit, and agent unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the object recognition unit is implemented by the camera 42 and processor 46 of the smart glasses 214, and recognizes objects by analyzing images captured by the camera 42 with the processor 46. The pose estimation unit is implemented by the identification processing unit 290 of the data processing unit 12, and estimates the pose of the object recognized by the object recognition unit. The tracking unit is implemented by the processor 46 of the smart glasses 214, and tracks the object estimated by the pose estimation unit in real time. The replacement display unit is implemented by the display of the smart glasses 214, and displays the object tracked by the tracking unit by replacing it with a virtual character or landscape. The agent unit is implemented by the microphone 238 and touch operation of the smart glasses 214, and accepts user voice commands and touch operations. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0147] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0148] 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.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] 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.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] 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.

[0154] 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.

[0155] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] 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.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the object recognition unit, posture estimation unit, tracking unit, replacement display unit, and agent unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the object recognition unit is implemented by the camera 42 and processor 46 of the headset terminal 314, and recognizes objects by analyzing images captured by the camera 42 with the processor 46. The posture estimation unit is implemented by the identification processing unit 290 of the data processing unit 12, and estimates the posture of the object recognized by the object recognition unit. The tracking unit is implemented by the processor 46 of the headset terminal 314, and tracks the object estimated by the posture estimation unit in real time. The replacement display unit is implemented by the display 343 of the headset terminal 314, and displays the object tracked by the tracking unit by replacing it with a virtual character or landscape. The agent unit is implemented by the microphone 238 and touch operation of the headset terminal 314, and accepts user voice commands and touch operations. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0163] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0164] 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.

[0165] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0166] 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.

[0167] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0169] 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.

[0170] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0171] 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.

[0172] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0173] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0174] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0175] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0176] 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.

[0177] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0178] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0179] Each of the multiple elements described above, including the object recognition unit, posture estimation unit, tracking unit, replacement display unit, and agent unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the object recognition unit is implemented by the camera 42 and processor 46 of the robot 414, and recognizes objects by analyzing images captured by the camera 42. The posture estimation unit is implemented by the identification processing unit 290 of the data processing unit 12, and estimates the posture of the object recognized by the object recognition unit. The tracking unit is implemented by the processor 46 of the robot 414, and tracks the object estimated by the posture estimation unit in real time. The replacement display unit is implemented by the display of the robot 414 and the controlled object 443, and displays the object tracked by the tracking unit by replacing it with a virtual character or landscape. The agent unit is implemented by the microphone 238 and touch operation of the robot 414, and accepts user voice commands and touch operations. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0180] 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.

[0181] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0182] 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.

[0183] 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.

[0184] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0185] 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."

[0186] 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.

[0187] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0196] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0197] 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.

[0198] (Note 1) An object recognition unit that recognizes objects, A posture estimation unit that estimates the posture of an object recognized by the object recognition unit, A tracking unit that tracks the object estimated by the attitude estimation unit, A replacement display unit that replaces and displays the object tracked by the aforementioned tracking unit, A system comprising an agent unit that receives instructions from the user. (Note 2) The aforementioned replacement display unit is, Change the appearance and interior of the room's furniture. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned replacement display unit is, Change the view from the window The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned agent unit is Compatible with AR glasses and AR contact lenses The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned agent unit is Change settings based on user instructions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The object recognition unit, Recognizing objects using a camera built into AR glasses. The system described in Appendix 1, characterized by the features described herein. (Note 7) The attitude estimation unit, The camera built into the AR glasses is used to estimate the orientation of an object. The system described in Appendix 1, characterized by the features described herein. (Note 8) The object recognition unit, It estimates the user's emotions and adjusts the accuracy of object recognition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The object recognition unit, During object recognition, the recognition algorithm is optimized by referencing the user's past recognition history. The system described in Appendix 1, characterized by the features described herein. (Note 10) The object recognition unit, During object recognition, the recognition accuracy is improved by analyzing the movement patterns of the objects. The system described in Appendix 1, characterized by the features described herein. (Note 11) The object recognition unit, It estimates the user's emotions and determines the priority of objects to recognize based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The object recognition unit, During object recognition, the system prioritizes recognizing objects that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The object recognition unit, During object recognition, the system analyzes the user's social media activity to identify relevant objects. The system described in Appendix 1, characterized by the features described herein. (Note 14) The attitude estimation unit, The system estimates the user's emotions and adjusts the accuracy of posture estimation based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The attitude estimation unit, During pose estimation, the estimation algorithm is optimized by referencing the object's past pose data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The attitude estimation unit, During pose estimation, the movement patterns of objects are analyzed to improve estimation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 17) The attitude estimation unit, It estimates the user's emotions and determines the priority of the attitudes to estimate based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The attitude estimation unit, During pose estimation, the system prioritizes estimating the most relevant poses based on the object's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 19) The attitude estimation unit, When estimating posture, referencing relevant literature on the object improves estimation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned tracking unit is It estimates the user's emotions and adjusts the tracking accuracy based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned tracking unit is During tracking, the tracking algorithm is optimized by referring to the object's past tracking data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned tracking unit is During tracking, the tracking accuracy is improved by analyzing the movement patterns of objects. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned tracking unit is It estimates the user's emotions and determines the priority of objects to track based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned tracking unit is During tracking, the system prioritizes tracking highly relevant objects based on their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned tracking unit is During tracking, referencing relevant literature on the object improves tracking accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned replacement display unit is, It estimates the user's emotions and adjusts the replacement display method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned replacement display unit is, When replacing an object, the display algorithm is optimized by referring to the object's past display data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned replacement display unit is, When displaying replacements, the movement patterns of objects are analyzed to improve display accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned replacement display unit is, It estimates the user's emotions and determines the priority of objects to display based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned replacement display unit is, When displaying replacements, objects with higher relevance will be prioritized based on the geographical location information of the objects. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned replacement display unit is, When displaying replacements, the display accuracy is improved by referring to related literature for the object. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned agent unit is The system estimates the user's emotions and adjusts the agent's response based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned agent unit is When the agent responds, it optimizes the response algorithm by referring to the user's past instruction history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned agent unit is The agent analyzes patterns in user instructions during responses to improve response accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned agent unit is The system estimates the user's emotions and determines the agent's response priority based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned agent unit is When the agent responds, it prioritizes responses that are more relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned agent unit is When the agent responds, it analyzes the user's social media activity and provides a relevant response. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An object recognition unit that recognizes objects, A posture estimation unit that estimates the posture of an object recognized by the object recognition unit, A tracking unit that tracks the object estimated by the attitude estimation unit, A replacement display unit that replaces and displays the object tracked by the aforementioned tracking unit, A system comprising an agent unit that receives instructions from the user.

2. The aforementioned replacement display unit is, Change the appearance and interior of the room's furniture. The system according to feature 1.

3. The aforementioned replacement display unit is, Change the view from the window The system according to feature 1.

4. The aforementioned agent unit is Compatible with AR glasses and AR contact lenses The system according to feature 1.

5. The aforementioned agent unit is Change settings based on user instructions. The system according to feature 1.

6. The object recognition unit, Recognizing objects using a camera built into AR glasses. The system according to feature 1.

7. The attitude estimation unit, The camera built into the AR glasses is used to estimate the orientation of an object. The system according to feature 1.

8. The object recognition unit, It estimates the user's emotions and adjusts the accuracy of object recognition based on the estimated user emotions. The system according to feature 1.

Images