System

Abstract

An object of a system according to an embodiment is to automatically determine whether a generated image is valid as training data for a AI model.SOLUTION: A system according to an embodiment includes a generated image acquisition unit, a feature extraction unit, a comparison unit, a determination unit, and an output unit. The generated image acquiring unit acquires the image generated by the generation AI. The feature extraction unit extracts a feature from the generated image acquired by the generated image acquisition unit. The comparison unit compares the feature extracted by the feature extraction unit with a feature of an actual image. The determination unit determines whether the generated image is valid as learning data on the basis of a result of the comparison by the comparison unit. The output unit outputs a result determined by the determination unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not fully automate the process of determining whether generated images are valid as training data for AI models, leaving room for improvement.

[0005] The system according to the embodiment aims to automatically determine whether a generated image is effective as learning data for an AI model. [Means for solving the problem]

[0006] The system according to the embodiment includes a generated image acquisition unit, a feature extraction unit, a comparison unit, a determination unit, and an output unit. The generated image acquisition unit acquires an image generated by the generation AI. The feature extraction unit extracts features from the generated image acquired by the generated image acquisition unit. The comparison unit compares the features extracted by the feature extraction unit with the features of the actual image. The determination unit determines whether the generated image is valid as learning data based on the comparison result by the comparison unit. The output unit outputs the result determined by the determination unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically determine whether the generated image is effective as learning data for an AI model. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A classifier according to an embodiment of the present invention is a system for determining whether a generated image is effective as training data for an AI model. This system evaluates whether an image generated by a generation AI is appropriate as training data for an AI model, similar to an image actually captured by a camera. This allows the classifier to efficiently determine whether a generated image is effective as training data for an AI model.

[0029] A decision device according to an embodiment includes a generated image acquisition unit, a feature extraction unit, a comparison unit, a determination unit, and an output unit. The generated image acquisition unit acquires an image generated by a generation AI. For example, the generation AI generates an image based on instructions from a user. The generation AI receives a prompt, such as "Please generate an image of a natural landscape," and generates an image based on the instruction. The generated image appears to have been captured by a camera. The feature extraction unit extracts features from the generated image acquired by the generated image acquisition unit. For example, the generation AI extracts features such as the color distribution, edge information, and texture of the image. The generation AI analyzes, for example, the distribution of red, green, and blue colors, the number of edges in the image, and texture patterns. The comparison unit compares the features extracted by the feature extraction unit with the features of the actual image. For example, the generation AI compares the features of the generated image with the features of an image actually captured by a camera. This comparison is performed based on, for example, the degree of similarity of the color distribution, the degree of similarity of the edge information, the degree of similarity of the texture, and the like. The determination unit determines whether the generated image is valid as training data based on the comparison results by the comparison unit. For example, if the color distribution, edge information, and texture of the generated image show a high degree of similarity with the actual image, the generation AI determines that the generated image is valid as training data. On the other hand, if the degree of similarity is low, the generation AI determines that the generated image is invalid. The output unit outputs the result determined by the determination unit. For example, the generation AI displays a message such as "This generated image is valid as training data." This allows the determiner according to the embodiment to efficiently determine whether the generated image is valid as training data for an AI model. For example, when training an AI model using images generated by the generation AI, invalid data can be eliminated, improving the accuracy of training. It is also possible to evaluate the performance of the generation AI by evaluating how closely the generated image resembles the actual image.

[0030] The generative image acquisition unit can generate images incorporating different styles and art forms. For example, the generative AI generates images incorporating different styles and art forms. For example, it generates a variety of images for the same prompt using different art styles such as impressionism, abstract painting, and realism. The generative AI also generates images that reflect different cultural and historical backgrounds. For example, it generates images that incorporate elements of different eras and cultures, such as ancient Egyptian, Renaissance, and modern art. The generative AI also generates images that simulate different techniques and materials. For example, it generates images using different techniques and materials such as watercolor, oil painting, and digital art. This allows for an increase in the variety of generated images by generating images that incorporate different styles and art forms.

[0031] The generated image acquisition unit can learn the user's past instruction history and automatically generate images that match the user's preferences. In the generated image acquisition unit, for example, the generation AI analyzes the user's past instruction history and generates images that match the user's preferences. For example, it learns the style and theme of images that the user has previously preferred and generates new images based on that. The generation AI also learns the characteristics of images that the user has given high ratings based on the user's past evaluation data and generates images based on that. For example, it generates images that reflect the user's preferred colors and composition. The generation AI also analyzes the user's past search history and browsing history and generates images based on the user's interests. For example, it generates images that reflect themes and keywords that the user frequently searches for. This allows the automatic generation of images that match the user's preferences, thereby improving user satisfaction.

[0032] The generated image acquisition unit can combine audio and text with the generated images and provide them as multimedia content. For example, the generated image acquisition unit automatically generates related audio and text for images generated by the generation AI and provides them as multimedia content. For example, combining birdsong and the sound of wind with images of natural scenery. The generation AI also automatically generates explanatory text and captions for the generated images, providing information both visually and textually. For example, adding text explaining the history and features of a building to an image of a historical building. The generation AI also automatically generates audio narration for the generated images, providing information both visually and audibly. For example, adding audio narration explaining the location to an image of a tourist spot. In this way, richer content can be provided by combining audio and text with the generated images.

[0033] The generated image acquisition unit can generate images optimized for different devices. In the generated image acquisition unit, for example, the generation AI generates images optimized for the screen size and resolution of different devices. For example, it generates portrait images for smartphones and landscape images for PCs. The generation AI also adjusts images to match the display characteristics of different devices (e.g., color reproducibility and brightness). For example, it generates vivid images optimized for the OLED display of a smartphone. The generation AI also generates images tailored to the usage scenarios of different devices. For example, it generates educational illustrations and infographics for tablets and presentation slides for PCs. By generating images optimized for different devices, it is possible to display images optimally according to the user's usage environment.

[0034] The feature extraction unit can extract features by taking image metadata into consideration. For example, the generative AI analyzes image metadata and extracts features based on information such as the shooting location, time, and camera settings. For example, it learns the features of images taken in a specific location and extracts the color and light patterns unique to that location. It also extracts features under different shooting conditions based on image metadata. For example, it compares the features of images taken under different conditions, such as daytime and nighttime, or sunny and cloudy days, and extracts similarities and differences. The generative AI also uses image metadata to extract features based on specific camera settings (e.g., shutter speed and aperture value). For example, it learns the features of images taken with a long exposure and extracts those features. This allows for more accurate feature extraction by taking image metadata into consideration.

[0035] The feature extraction unit recognizes objects within an image and can extract the presence of specific objects as features. In the feature extraction unit, for example, the generation AI recognizes objects within an image and extracts the presence of specific objects as features. For example, it recognizes people, animals, buildings, etc. within an image and extracts their presence as features. The generation AI also analyzes the position and size of objects within an image and extracts them as features. For example, it extracts features based on the arrangement and size of objects within an image. The generation AI also analyzes the relationships between objects within an image and extracts them as features. For example, it extracts features based on how multiple objects are arranged and what relationships they have. In this way, by recognizing objects within an image, it is possible to extract the presence of specific objects as features.

[0036] The feature extraction unit can extract features using different visual characteristics. For example, the generation AI uses infrared images to extract features that are not visible in normal visible light images. For example, it analyzes infrared images and extracts temperature distribution and the location of heat sources as features. The generation AI also uses thermal images to extract features of an object's temperature and thermal radiation. For example, it analyzes thermal images and extracts the temperature distribution and thermal radiation pattern of a specific object as features. The generation AI also combines different visual characteristics to extract features from multiple perspectives. For example, it combines and analyzes visible light images and infrared images, and integrates the features obtained from both perspectives. This makes it possible to extract a wider variety of features by using different visual characteristics.

[0037] The feature extraction unit can extract multimodal features by combining audio and text information. For example, the feature extraction unit uses a generative AI to analyze audio information related to an image and extract features from both the audio and the image. For example, it analyzes audio related to a scene in the image (e.g., natural sounds or human voices) and extracts it as features. The generative AI also analyzes text information related to the image and extracts features from both the text and the image. For example, it analyzes explanatory text or captions accompanying the image and extracts them as features. The generative AI also integrates audio, text, and image information to extract multimodal features. For example, it combines and analyzes audio and text information related to a scene in an image and extracts comprehensive features. This allows for the extraction of richer features by combining audio and text information.

[0038] The comparison unit can simulate and compare the shooting conditions of an image. For example, when the generation AI compares an image with an actual image, the comparison unit simulates the intensity and angle of light to evaluate the degree of match between the generated image and the actual image. For example, it simulates illumination from different light sources and angles to compare. In addition, when the generation AI compares an image with an actual image, it simulates shooting conditions (e.g., weather and time of day) to evaluate the degree of match between the generated image and the actual image. For example, it simulates and compares conditions such as sunny and cloudy weather, daytime and nighttime. In addition, when the generation AI compares an image with an actual image, it simulates camera settings (e.g., shutter speed and aperture value) to evaluate the degree of match between the generated image and the actual image. For example, it simulates and compares different camera settings. This allows for more accurate comparison by simulating the shooting conditions of the image.

[0039] The comparison unit can take dynamic elements within an image into account when making a comparison. For example, when the generation AI compares an image with an actual image, the comparison unit analyzes dynamic elements within the image (e.g., the movement of animals or people) and compares them based on their movement patterns. For example, it can simulate and compare the walking of an animal or the movements of a person. When the generation AI compares an image with an actual image, it can analyze the position and speed of the dynamic elements and evaluate the degree of similarity between the generated image and the actual image based on that. For example, it can compare based on the speed at which an animal moves or the speed at which a person moves. When the generation AI compares an image with an actual image, it can analyze the interactions of the dynamic elements and evaluate the degree of similarity between the generated image and the actual image based on that. For example, it can compare based on how multiple animals or people interact with each other. This allows for more accurate comparisons by taking dynamic elements within the image into account.

[0040] The comparison unit can make comparisons using different visual characteristics. For example, the generation AI uses infrared images to compare features that are not visible in normal visible light images. For example, it analyzes infrared images and compares the generated image with the actual image based on temperature distribution and the location of heat sources. The generation AI also uses thermal images to compare the temperature and thermal radiation characteristics of an object. For example, it analyzes thermal images and compares the generated image with the actual image based on the temperature distribution and thermal radiation pattern of a specific object. The generation AI also combines different visual characteristics to compare the generated image with the actual image from multiple perspectives. For example, it combines visible light images and infrared images and analyzes them, comparing them based on features obtained from both perspectives. This enables more diverse comparisons by using different visual characteristics.

[0041] The comparison unit can perform multimodal comparisons by combining audio and text information. For example, the comparison unit uses the generation AI to analyze audio information related to an image and compare it based on features obtained from both the audio and the image. For example, it analyzes audio related to the scene in the image (e.g., natural sounds or human voices) and compares the generated image with the actual image based on that. The generation AI also analyzes text information related to the image and compares it based on features obtained from both the text and the image. For example, it analyzes explanatory text or captions accompanying the image and compares the generated image with the actual image based on that. The generation AI also integrates audio, text, and image information to perform multimodal comparisons. For example, it combines and analyzes audio and text information related to the scene in the image to perform a comprehensive comparison. This enables richer comparisons by combining audio and text information.

[0042] The judgment unit recognizes objects in an image and can evaluate the effectiveness of the data as training data based on the presence of specific objects. For example, the generation AI recognizes objects in an image and the judgment unit evaluates the effectiveness of the data as training data based on the presence of specific objects. For example, the generation AI recognizes people, animals, buildings, etc. in an image and evaluates the effectiveness based on their presence. The generation AI also analyzes the position and size of objects in an image and evaluates the effectiveness of the data as training data based on this. For example, the effectiveness is evaluated based on the arrangement and size of objects in an image. The generation AI also analyzes the relationships between objects in an image and evaluates the effectiveness of the data as training data based on this. For example, the effectiveness is evaluated based on how multiple objects are arranged and what kind of relationships there are. In this way, by recognizing objects in an image, the effectiveness can be evaluated based on the presence of specific objects.

[0043] The judgment unit can evaluate the effectiveness of the data as training data using different visual characteristics. For example, the generation AI uses infrared images to evaluate the effectiveness of the data as training data based on features that are not visible in normal visible light images. For example, the generation AI analyzes infrared images and evaluates the effectiveness based on the temperature distribution and the location of heat sources. The generation AI also uses thermal images to evaluate the effectiveness of the data as training data based on the temperature and thermal radiation characteristics of an object. For example, the generation AI analyzes thermal images and evaluates the effectiveness based on the temperature distribution and thermal radiation pattern of a specific object. The generation AI also combines different visual characteristics to evaluate the effectiveness of the data as training data from multiple perspectives. For example, the generation AI combines visible light images and infrared images and analyzes them, evaluating the effectiveness based on the features obtained from both perspectives. This enables more diverse evaluations by using different visual characteristics.

[0044] The judgment unit can perform multimodal evaluation by combining audio and text information. For example, the generation AI analyzes audio information related to an image and evaluates its effectiveness as training data based on features obtained from both the audio and the image. For example, the generation AI analyzes audio related to the scene in the image (e.g., natural sounds or human voices) and evaluates its effectiveness based on that. The generation AI also analyzes text information related to the image and evaluates its effectiveness as training data based on features obtained from both the text and the image. For example, the generation AI analyzes explanatory text and captions accompanying the image and evaluates its effectiveness based on that. The generation AI also integrates audio, text, and image information to perform multimodal evaluation. For example, it combines and analyzes audio and text information related to the scene in the image and performs a comprehensive evaluation. This enables richer evaluation by combining audio and text information.

[0045] The output unit can display the judgment results in a visually easy-to-understand format. For example, when the generation AI outputs the judgment results to the user, the output unit displays them in a visually easy-to-understand format. For example, the judgment results can be displayed as graphs or charts so that the user can understand them at a glance. In addition, when the judgment results are output to the user, they can be displayed in a visually easy-to-understand format using color coding and icons. For example, valid data can be displayed in green and invalid data in red. In addition, when the generation AI outputs the judgment results to the user, an interactive dashboard is provided so that the user can access detailed information. For example, clicking on the judgment result displays detailed analysis results. In this way, the judgment results can be displayed in a visually easy-to-understand format so that the user can understand them at a glance.

[0046] The output unit can combine the judgment result with audio and text information to provide multimodal output. For example, when the generation AI outputs the judgment result to the user, the output unit provides information in both audio and text. For example, the judgment result can be read aloud and simultaneously displayed in text. In addition, when outputting the judgment result to the user, related explanatory text and captions can be added to provide information both visually and audibly. For example, a detailed explanation of the judgment result can be displayed in text and supplemented with audio. In addition, when the generation AI outputs the judgment result to the user, audio narration can be added to provide information both visually and audibly. For example, the main points of the judgment result can be explained in audio and detailed information can be displayed in text. This enables richer output by combining audio and text information.

[0047] The output unit can display the results in a format optimized for different devices. For example, when the generation AI outputs the judgment results to the user, the output unit displays them in a format optimized for the screen size and resolution of different devices. For example, it uses a portrait layout for smartphones and a landscape layout for PCs. In addition, when outputting the judgment results to the user, it adjusts them to suit the display characteristics (e.g., color reproducibility and brightness) of different devices. For example, it provides a vivid display optimized for the OLED display of a smartphone. In addition, when the generation AI outputs the judgment results to the user, it displays them in a format tailored to the usage scenario of different devices. For example, it displays educational illustrations and infographics for tablets and presentation slides for PCs. In this way, by displaying the results in a format optimized for different devices, it is possible to provide an optimal display according to the user's usage environment.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The generated image acquisition unit can automatically generate related audio and text for images generated by the generation AI and provide them as multimedia content. For example, combining birdsong and the sound of wind with images of natural scenery. The generation AI also automatically generates explanatory text and captions for the generated images, providing information both visually and in text. For example, adding text explaining the history and characteristics of a building to an image of a historical building. The generation AI also automatically generates audio narration for the generated images, providing information both visually and audibly. For example, adding audio narration explaining the location to an image of a tourist spot. This allows for richer content to be provided by combining audio and text with the generated images.

[0050] The generated image acquisition unit can generate images optimized for different devices. For example, the generation AI generates images optimized for the screen size and resolution of different devices. For example, it generates portrait images for smartphones and landscape images for PCs. The generation AI also adjusts images to match the display characteristics of different devices (e.g., color reproduction and brightness). For example, it generates vivid images optimized for the OLED display of a smartphone. The generation AI also generates images tailored to the usage scenarios of different devices. For example, it generates educational illustrations and infographics for tablets and presentation slides for PCs. By generating images optimized for different devices, it is possible to display images optimally according to the user's usage environment.

[0051] The generated image acquisition unit can learn the user's past instruction history and automatically generate images that match the user's preferences. For example, the generation AI analyzes the user's past instruction history and generates images that match the user's preferences. For example, it learns the style and theme of images that the user has previously preferred and generates new images based on that. The generation AI also learns the characteristics of images that the user has given high ratings based on the user's past evaluation data and generates images based on that. For example, it generates images that reflect the user's preferred colors and composition. The generation AI also analyzes the user's past search history and browsing history and generates images based on the user's interests. For example, it generates images that reflect themes and keywords that the user frequently searches for. This allows the automatic generation of images that match the user's preferences, thereby improving user satisfaction.

[0052] The generative image acquisition unit can generate images incorporating different styles and art forms. For example, the generative AI generates images incorporating different styles and art forms. For example, it generates a variety of images for the same prompt using different art styles such as impressionism, abstract painting, and realism. The generative AI also generates images that reflect different cultural and historical backgrounds. For example, it generates images that incorporate elements of different eras and cultures, such as ancient Egyptian, Renaissance, and modern art. The generative AI also generates images that simulate different techniques and materials. For example, it generates images using different techniques and materials such as watercolor, oil painting, and digital art. This increases the variety of generated images by generating images that incorporate different styles and art forms.

[0053] The feature extraction unit can extract features by taking image metadata into consideration. For example, the generative AI analyzes image metadata and extracts features based on information such as the shooting location, time, and camera settings. For example, it learns the characteristics of images taken in a specific location and extracts the color and light patterns unique to that location. It also extracts features under different shooting conditions based on image metadata. For example, it compares the features of images taken under different conditions, such as daytime and nighttime, or sunny and cloudy days, and extracts similarities and differences. The generative AI also uses image metadata to extract features based on specific camera settings (e.g., shutter speed and aperture value). For example, it learns the features of images taken with a long exposure and extracts those features. This allows for more accurate feature extraction by taking image metadata into consideration.

[0054] The feature extraction unit recognizes objects within an image and can extract the presence of specific objects as features. For example, the generation AI recognizes objects within an image and extracts the presence of specific objects as features. For example, it recognizes people, animals, buildings, etc. within an image and extracts their presence as features. The generation AI also analyzes the position and size of objects within an image and extracts them as features. For example, it extracts features based on the arrangement and size of objects within an image. The generation AI also analyzes the relationships between objects within an image and extracts them as features. For example, it extracts features based on how multiple objects are arranged and what relationships they have. In this way, by recognizing objects within an image, it is possible to extract the presence of specific objects as features.

[0055] The feature extraction unit can extract features using different visual characteristics. For example, the generation AI uses infrared images to extract features that are not visible in normal visible light images. For example, it analyzes infrared images and extracts temperature distribution and the location of heat sources as features. The generation AI also uses thermal images to extract features of an object's temperature and thermal radiation. For example, it analyzes thermal images and extracts the temperature distribution and thermal radiation pattern of a specific object as features. The generation AI also combines different visual characteristics to extract features from multiple perspectives. For example, it combines and analyzes visible light images and infrared images, and integrates the features obtained from both perspectives. This makes it possible to extract a wider variety of features by using different visual characteristics.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The generated image acquisition unit acquires the image generated by the generation AI. For example, the generation AI generates an image based on instructions from a user, and the generated image appears to be an actual image taken with a camera. Step 2: The feature extraction unit extracts features from the generated image acquired by the generated image acquisition unit, such as color distribution, edge information, texture, etc. of the image. Step 3: The comparison unit compares the features extracted by the feature extraction unit with the features of the actual image, for example, based on the degree of similarity in color distribution, edge information, texture, etc. Step 4: The judgment unit judges whether the generated image is valid as learning data based on the results of the comparison by the comparison unit. For example, if the color distribution, edge information, and texture show a high degree of similarity with the actual image, it is judged to be valid, and if the degree of similarity is low, it is judged to be invalid. Step 5: The output unit outputs the result of the judgment made by the judgment unit. For example, it displays a message such as "This generated image is valid as learning data."

[0058] (Example 2) A classifier according to an embodiment of the present invention is a system for determining whether a generated image is effective as training data for an AI model. This system evaluates whether an image generated by a generation AI is appropriate as training data for an AI model, similar to an image actually captured by a camera. This allows the classifier to efficiently determine whether a generated image is effective as training data for an AI model.

[0059] A decision device according to an embodiment includes a generated image acquisition unit, a feature extraction unit, a comparison unit, a determination unit, and an output unit. The generated image acquisition unit acquires an image generated by a generation AI. For example, the generation AI generates an image based on instructions from a user. The generation AI receives a prompt, such as "Please generate an image of a natural landscape," and generates an image based on the instruction. The generated image appears to have been captured by a camera. The feature extraction unit extracts features from the generated image acquired by the generated image acquisition unit. For example, the generation AI extracts features such as the color distribution, edge information, and texture of the image. The generation AI analyzes, for example, the distribution of red, green, and blue colors, the number of edges in the image, and texture patterns. The comparison unit compares the features extracted by the feature extraction unit with the features of the actual image. For example, the generation AI compares the features of the generated image with the features of an image actually captured by a camera. This comparison is performed based on, for example, the degree of similarity of the color distribution, the degree of similarity of the edge information, the degree of similarity of the texture, and the like. The determination unit determines whether the generated image is valid as training data based on the comparison results by the comparison unit. For example, if the color distribution, edge information, and texture of the generated image show a high degree of similarity with the actual image, the generation AI determines that the generated image is valid as training data. On the other hand, if the degree of similarity is low, the generation AI determines that the generated image is invalid. The output unit outputs the result determined by the determination unit. For example, the generation AI displays a message such as "This generated image is valid as training data." This allows the determiner according to the embodiment to efficiently determine whether the generated image is valid as training data for an AI model. For example, when training an AI model using images generated by the generation AI, invalid data can be eliminated, improving the accuracy of training. It is also possible to evaluate the performance of the generation AI by evaluating how closely the generated image resembles the actual image.

[0060] The generative image acquisition unit can generate images incorporating different styles and art forms. For example, the generative AI generates images incorporating different styles and art forms. For example, it generates a variety of images for the same prompt using different art styles such as impressionism, abstract painting, and realism. The generative AI also generates images that reflect different cultural and historical backgrounds. For example, it generates images that incorporate elements of different eras and cultures, such as ancient Egyptian, Renaissance, and modern art. The generative AI also generates images that simulate different techniques and materials. For example, it generates images using different techniques and materials such as watercolor, oil painting, and digital art. This allows for an increase in the variety of generated images by generating images that incorporate different styles and art forms.

[0061] The generated image acquisition unit can learn the user's past instruction history and automatically generate images that match the user's preferences. In the generated image acquisition unit, for example, the generation AI analyzes the user's past instruction history and generates images that match the user's preferences. For example, it learns the style and theme of images that the user has previously preferred and generates new images based on that. The generation AI also learns the characteristics of images that the user has given high ratings based on the user's past evaluation data and generates images based on that. For example, it generates images that reflect the user's preferred colors and composition. The generation AI also analyzes the user's past search history and browsing history and generates images based on the user's interests. For example, it generates images that reflect themes and keywords that the user frequently searches for. This allows the automatic generation of images that match the user's preferences, thereby improving user satisfaction.

[0062] The generated image acquisition unit can use the emotion estimation function to generate images that correspond to the user's emotional state. For example, the generated image acquisition unit uses the emotion estimation function to analyze the user's emotional state in real time and generate images based on the results. For example, if the user is feeling stressed, it generates an image of a natural landscape that has a relaxing effect. The generation AI also adjusts the theme and color of the generated image according to the user's emotional state. For example, if the user is happy, it generates a bright and colorful image, and if the user is sad, it generates an image with a calm color tone. The emotion estimation function also automatically generates prompts for image generation that match the user's emotional state. For example, if the user wants to relax, it automatically generates a prompt such as "Please generate a relaxing landscape." This allows the system to generate images that correspond to the user's emotional state and provide content that is in tune with the user's emotions.

[0063] The generated image acquisition unit can combine audio and text with the generated images and provide them as multimedia content. For example, the generated image acquisition unit automatically generates related audio and text for images generated by the generation AI and provides them as multimedia content. For example, combining birdsong and the sound of wind with images of natural scenery. The generation AI also automatically generates explanatory text and captions for the generated images, providing information both visually and textually. For example, adding text explaining the history and features of a building to an image of a historical building. The generation AI also automatically generates audio narration for the generated images, providing information both visually and audibly. For example, adding audio narration explaining the location to an image of a tourist spot. In this way, richer content can be provided by combining audio and text with the generated images.

[0064] The generated image acquisition unit can generate images optimized for different devices. In the generated image acquisition unit, for example, the generation AI generates images optimized for the screen size and resolution of different devices. For example, it generates portrait images for smartphones and landscape images for PCs. The generation AI also adjusts images to match the display characteristics of different devices (e.g., color reproducibility and brightness). For example, it generates vivid images optimized for the OLED display of a smartphone. The generation AI also generates images tailored to the usage scenarios of different devices. For example, it generates educational illustrations and infographics for tablets and presentation slides for PCs. By generating images optimized for different devices, it is possible to display images optimally according to the user's usage environment.

[0065] The generated image acquisition unit can use the emotion estimation function to estimate the emotion a user is feeling when inputting an image generation prompt in real time and make suggestions that will elicit positive emotions. The generated image acquisition unit, for example, uses the emotion estimation function to analyze the emotion a user is feeling when inputting an image generation prompt in real time and make suggestions that will elicit positive emotions. For example, if the user is tired, the unit suggests a refreshing image prompt. The unit also automatically generates an image generation prompt based on the user's emotional state to elicit positive emotions. For example, if the user is feeling down, the unit suggests an uplifting image prompt. The emotion estimation function can also be used to provide positive feedback in response to the prompt input by the user to enhance emotions. For example, a message such as "That's a great idea!" is displayed in response to the prompt input by the user. In this way, the unit can estimate the user's emotion in real time and make suggestions that will elicit positive emotions, thereby improving user satisfaction.

[0066] The feature extraction unit can extract features by taking image metadata into consideration. For example, the generative AI analyzes image metadata and extracts features based on information such as the shooting location, time, and camera settings. For example, it learns the features of images taken in a specific location and extracts the color and light patterns unique to that location. It also extracts features under different shooting conditions based on image metadata. For example, it compares the features of images taken under different conditions, such as daytime and nighttime, or sunny and cloudy days, and extracts similarities and differences. The generative AI also uses image metadata to extract features based on specific camera settings (e.g., shutter speed and aperture value). For example, it learns the features of images taken with a long exposure and extracts those features. This allows for more accurate feature extraction by taking image metadata into consideration.

[0067] The feature extraction unit recognizes objects within an image and can extract the presence of specific objects as features. In the feature extraction unit, for example, the generation AI recognizes objects within an image and extracts the presence of specific objects as features. For example, it recognizes people, animals, buildings, etc. within an image and extracts their presence as features. The generation AI also analyzes the position and size of objects within an image and extracts them as features. For example, it extracts features based on the arrangement and size of objects within an image. The generation AI also analyzes the relationships between objects within an image and extracts them as features. For example, it extracts features based on how multiple objects are arranged and what relationships they have. In this way, by recognizing objects within an image, it is possible to extract the presence of specific objects as features.

[0068] The feature extraction unit can extract features using different visual characteristics. For example, the generation AI uses infrared images to extract features that are not visible in normal visible light images. For example, it analyzes infrared images and extracts temperature distribution and the location of heat sources as features. The generation AI also uses thermal images to extract features of an object's temperature and thermal radiation. For example, it analyzes thermal images and extracts the temperature distribution and thermal radiation pattern of a specific object as features. The generation AI also combines different visual characteristics to extract features from multiple perspectives. For example, it combines and analyzes visible light images and infrared images, and integrates the features obtained from both perspectives. This makes it possible to extract a wider variety of features by using different visual characteristics.

[0069] The feature extraction unit can extract multimodal features by combining audio and text information. For example, the feature extraction unit uses a generative AI to analyze audio information related to an image and extract features from both the audio and the image. For example, it analyzes audio related to a scene in the image (e.g., natural sounds or human voices) and extracts it as features. The generative AI also analyzes text information related to the image and extracts features from both the text and the image. For example, it analyzes explanatory text or captions accompanying the image and extracts them as features. The generative AI also integrates audio, text, and image information to extract multimodal features. For example, it combines and analyzes audio and text information related to a scene in an image and extracts comprehensive features. This allows for the extraction of richer features by combining audio and text information.

[0070] The feature extraction unit uses the emotion estimation function to consider the user's emotional state when extracting image features, thereby extracting features that are likely to be emotionally relatable. The feature extraction unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and extract features that are likely to be emotionally relatable based on the results. For example, parts to which the user showed a strong emotional reaction may be preferentially extracted as features. Furthermore, specific elements in the image (e.g., color tone or composition) may be extracted as features that are likely to be emotionally relatable based on the user's emotional state. For example, color tone or composition that shows the user a positive emotion may be extracted as features. Furthermore, the emotion estimation function may be used to analyze the user's emotional state, and the image feature extraction algorithm may be adjusted based on the results. For example, the algorithm may be adjusted to preferentially extract features that are likely to be emotionally relatable by the user. In this way, features that are likely to be emotionally relatable may be extracted by considering the user's emotional state.

[0071] The comparison unit can simulate and compare the shooting conditions of an image. For example, when the generation AI compares an image with an actual image, the comparison unit simulates the intensity and angle of light to evaluate the degree of match between the generated image and the actual image. For example, it simulates illumination from different light sources and angles to compare. In addition, when the generation AI compares an image with an actual image, it simulates shooting conditions (e.g., weather and time of day) to evaluate the degree of match between the generated image and the actual image. For example, it simulates and compares conditions such as sunny and cloudy weather, daytime and nighttime. In addition, when the generation AI compares an image with an actual image, it simulates camera settings (e.g., shutter speed and aperture value) to evaluate the degree of match between the generated image and the actual image. For example, it simulates and compares different camera settings. This allows for more accurate comparison by simulating the shooting conditions of the image.

[0072] The comparison unit can take dynamic elements within an image into account when making a comparison. For example, when the generation AI compares an image with an actual image, the comparison unit analyzes dynamic elements within the image (e.g., the movement of animals or people) and compares them based on their movement patterns. For example, it can simulate and compare the walking of an animal or the movements of a person. When the generation AI compares an image with an actual image, it can analyze the position and speed of the dynamic elements and evaluate the degree of similarity between the generated image and the actual image based on that. For example, it can compare based on the speed at which an animal moves or the speed at which a person moves. When the generation AI compares an image with an actual image, it can analyze the interactions of the dynamic elements and evaluate the degree of similarity between the generated image and the actual image based on that. For example, it can compare based on how multiple animals or people interact with each other. This allows for more accurate comparisons by taking dynamic elements within the image into account.

[0073] The comparison unit can use the emotion estimation function to analyze the user's emotional response when comparing the actual image and the generated image, and prioritize comparison of emotionally significant elements. For example, the comparison unit can use the emotion estimation function to analyze the user's emotional response in real time when comparing the actual image and the generated image, and prioritize comparison of emotionally significant elements based on the results. For example, the comparison unit can focus on comparing parts to which the user showed a strong emotional response. Furthermore, based on the user's emotional response data, the comparison unit can compare specific elements (e.g., color tone or composition) of the actual image and the generated image as emotionally significant elements. For example, the comparison unit can focus on comparing color tone or composition to which the user showed positive emotions. Furthermore, the emotion estimation function can analyze the user's emotional response, and adjust the comparison algorithm between the actual image and the generated image based on the results. For example, the algorithm can be adjusted to prioritize comparison of elements that the user is likely to emotionally empathize with. In this way, by analyzing the user's emotional response, it is possible to prioritize comparison of emotionally significant elements.

[0074] The comparison unit can make comparisons using different visual characteristics. For example, the generation AI uses infrared images to compare features that are not visible in normal visible light images. For example, it analyzes infrared images and compares the generated image with the actual image based on temperature distribution and the location of heat sources. The generation AI also uses thermal images to compare the temperature and thermal radiation characteristics of an object. For example, it analyzes thermal images and compares the generated image with the actual image based on the temperature distribution and thermal radiation pattern of a specific object. The generation AI also combines different visual characteristics to compare the generated image with the actual image from multiple perspectives. For example, it combines visible light images and infrared images and analyzes them, comparing them based on features obtained from both perspectives. This enables more diverse comparisons by using different visual characteristics.

[0075] The comparison unit can perform multimodal comparisons by combining audio and text information. For example, the comparison unit uses the generation AI to analyze audio information related to an image and compare it based on features obtained from both the audio and the image. For example, it analyzes audio related to the scene in the image (e.g., natural sounds or human voices) and compares the generated image with the actual image based on that. The generation AI also analyzes text information related to the image and compares it based on features obtained from both the text and the image. For example, it analyzes explanatory text or captions accompanying the image and compares the generated image with the actual image based on that. The generation AI also integrates audio, text, and image information to perform multimodal comparisons. For example, it combines and analyzes audio and text information related to the scene in the image to perform a comprehensive comparison. This enables richer comparisons by combining audio and text information.

[0076] The comparison unit can use the emotion estimation function to consider the user's emotional state when comparing with the actual image and compare elements that are likely to elicit emotional empathy. The comparison unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and compare elements that are likely to elicit emotional empathy based on the results. For example, the comparison unit may focus on parts to which the user showed a strong emotional reaction. Furthermore, based on the user's emotional state, the comparison unit compares specific elements (e.g., color tone or composition) of the actual image and the generated image as elements that are likely to elicit emotional empathy. For example, the comparison may focus on color tone or composition to which the user showed positive emotions. Furthermore, the emotion estimation function can be used to analyze the user's emotional state and adjust the comparison algorithm between the actual image and the generated image based on the results. For example, the algorithm can be adjusted to prioritize comparison of elements that are likely to elicit emotional empathy by considering the user's emotional state.

[0077] The judgment unit recognizes objects in an image and can evaluate the effectiveness of the data as training data based on the presence of specific objects. For example, the generation AI recognizes objects in an image and the judgment unit evaluates the effectiveness of the data as training data based on the presence of specific objects. For example, the generation AI recognizes people, animals, buildings, etc. in an image and evaluates the effectiveness based on their presence. The generation AI also analyzes the position and size of objects in an image and evaluates the effectiveness of the data as training data based on this. For example, the effectiveness is evaluated based on the arrangement and size of objects in an image. The generation AI also analyzes the relationships between objects in an image and evaluates the effectiveness of the data as training data based on this. For example, the effectiveness is evaluated based on how multiple objects are arranged and what kind of relationships there are. In this way, by recognizing objects in an image, the effectiveness can be evaluated based on the presence of specific objects.

[0078] The determination unit can use the emotion estimation function to analyze the user's emotional response when determining the effectiveness of the learning data, and prioritize evaluation of emotionally important elements. For example, the determination unit uses the emotion estimation function to analyze the user's emotional response when viewing an image in real time, and prioritize evaluation of emotionally important elements based on the results. For example, the determination unit may prioritize evaluation of parts to which the user showed a strong emotional response. Furthermore, based on the user's emotional response data, the determination unit evaluates specific elements in the image (e.g., color tone or composition) as emotionally important elements. For example, the determination unit may prioritize evaluation of color tone or composition to which the user showed positive emotions. Furthermore, the determination unit uses the emotion estimation function to analyze the user's emotional response, and adjusts the effectiveness evaluation algorithm for the learning data based on the results. For example, the algorithm is adjusted to prioritize evaluation of elements that the user is likely to empathize with emotionally. In this way, the determination unit can prioritize evaluation of emotionally important elements by analyzing the user's emotional response.

[0079] The judgment unit can evaluate the effectiveness of the data as training data using different visual characteristics. For example, the generation AI uses infrared images to evaluate the effectiveness of the data as training data based on features that are not visible in normal visible light images. For example, the generation AI analyzes infrared images and evaluates the effectiveness based on the temperature distribution and the location of heat sources. The generation AI also uses thermal images to evaluate the effectiveness of the data as training data based on the temperature and thermal radiation characteristics of an object. For example, the generation AI analyzes thermal images and evaluates the effectiveness based on the temperature distribution and thermal radiation pattern of a specific object. The generation AI also combines different visual characteristics to evaluate the effectiveness of the data as training data from multiple perspectives. For example, the generation AI combines visible light images and infrared images and analyzes them, evaluating the effectiveness based on the features obtained from both perspectives. This enables more diverse evaluations by using different visual characteristics.

[0080] The judgment unit can perform multimodal evaluation by combining audio and text information. For example, the generation AI analyzes audio information related to an image and evaluates its effectiveness as training data based on features obtained from both the audio and the image. For example, the generation AI analyzes audio related to the scene in the image (e.g., natural sounds or human voices) and evaluates its effectiveness based on that. The generation AI also analyzes text information related to the image and evaluates its effectiveness as training data based on features obtained from both the text and the image. For example, the generation AI analyzes explanatory text and captions accompanying the image and evaluates its effectiveness based on that. The generation AI also integrates audio, text, and image information to perform multimodal evaluation. For example, it combines and analyzes audio and text information related to the scene in the image and performs a comprehensive evaluation. This enables richer evaluation by combining audio and text information.

[0081] The determination unit can use the emotion estimation function to consider the user's emotional state when determining the effectiveness of the data as learning data, and evaluate elements that are likely to be emotionally relatable. For example, the determination unit uses the emotion estimation function to analyze the user's emotional state in real time and evaluate elements that are likely to be emotionally relatable based on the results. For example, the determination unit may focus on evaluating parts to which the user showed a strong emotional response. Furthermore, based on the user's emotional state, the determination unit evaluates specific elements in the image (e.g., color tone or composition) as elements that are likely to be emotionally relatable. For example, the determination unit may focus on evaluating color tone or composition to which the user showed positive emotions. Furthermore, the determination unit uses the emotion estimation function to analyze the user's emotional state, and adjusts the algorithm for evaluating the effectiveness of the data as learning data based on the results. For example, the algorithm is adjusted to prioritize evaluation of elements that are likely to be emotionally relatable by the user. In this way, elements that are likely to be emotionally relatable can be evaluated by taking the user's emotional state into consideration.

[0082] The output unit can display the judgment results in a visually easy-to-understand format. For example, when the generation AI outputs the judgment results to the user, the output unit displays them in a visually easy-to-understand format. For example, the judgment results can be displayed as graphs or charts so that the user can understand them at a glance. In addition, when the judgment results are output to the user, they can be displayed in a visually easy-to-understand format using color coding and icons. For example, valid data can be displayed in green and invalid data in red. In addition, when the generation AI outputs the judgment results to the user, an interactive dashboard is provided so that the user can access detailed information. For example, clicking on the judgment result displays detailed analysis results. In this way, the judgment results can be displayed in a visually easy-to-understand format so that the user can understand them at a glance.

[0083] The output unit can combine the judgment result with audio and text information to provide multimodal output. For example, when the generation AI outputs the judgment result to the user, the output unit provides information in both audio and text. For example, the judgment result can be read aloud and simultaneously displayed in text. In addition, when outputting the judgment result to the user, related explanatory text and captions can be added to provide information both visually and audibly. For example, a detailed explanation of the judgment result can be displayed in text and supplemented with audio. In addition, when the generation AI outputs the judgment result to the user, audio narration can be added to provide information both visually and audibly. For example, the main points of the judgment result can be explained in audio and detailed information can be displayed in text. This enables richer output by combining audio and text information.

[0084] The output unit can use the emotion estimation function to provide feedback according to the user's emotional state. For example, the output unit uses the emotion estimation function to analyze the user's emotional state in real time and provide feedback based on the results. For example, if the user is feeling anxious, the output unit displays a reassuring message. The output unit also adjusts the content and format of the feedback based on the user's emotional state. For example, if the user is showing positive emotions, the output unit displays an encouraging message, and if the user is showing negative emotions, the output unit displays a comforting message. The output unit also uses the emotion estimation function to analyze the user's emotional state and adjusts the timing of the feedback based on the results. For example, the output unit provides feedback when the user is relaxed. In this way, by providing feedback according to the user's emotional state, the output unit can improve user satisfaction.

[0085] The output unit can display the results in a format optimized for different devices. For example, when the generation AI outputs the judgment results to the user, the output unit displays them in a format optimized for the screen size and resolution of different devices. For example, it uses a portrait layout for smartphones and a landscape layout for PCs. In addition, when outputting the judgment results to the user, it adjusts them to suit the display characteristics (e.g., color reproducibility and brightness) of different devices. For example, it provides a vivid display optimized for the OLED display of a smartphone. In addition, when the generation AI outputs the judgment results to the user, it displays them in a format tailored to the usage scenario of different devices. For example, it displays educational illustrations and infographics for tablets and presentation slides for PCs. In this way, by displaying the results in a format optimized for different devices, it is possible to provide an optimal display according to the user's usage environment.

[0086] The output unit can use the emotion estimation function to monitor the user's emotional response in real time and dynamically adjust the content of the feedback. For example, the output unit uses the emotion estimation function to monitor the user's emotional response in real time and dynamically adjust the content of the feedback based on the results. For example, if the user is feeling anxious, a reassuring message is displayed. The content and format of the feedback are also adjusted based on the user's emotional response data. For example, an encouraging message is displayed if the user is showing positive emotions, and a comforting message is displayed if the user is showing negative emotions. The emotion estimation function is also used to analyze the user's emotional response and adjust the timing of the feedback based on the results. For example, feedback is provided when the user is relaxed. In this way, by monitoring the user's emotional response in real time and dynamically adjusting the content of the feedback, user satisfaction can be improved.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The generated image acquisition unit can automatically generate related audio and text for images generated by the generation AI and provide them as multimedia content. For example, combining birdsong and the sound of wind with images of natural scenery. The generation AI also automatically generates explanatory text and captions for the generated images, providing information both visually and in text. For example, adding text explaining the history and characteristics of a building to an image of a historical building. The generation AI also automatically generates audio narration for the generated images, providing information both visually and audibly. For example, adding audio narration explaining the location to an image of a tourist spot. This allows for richer content to be provided by combining audio and text with the generated images.

[0089] The generated image acquisition unit can generate images optimized for different devices. For example, the generation AI generates images optimized for the screen size and resolution of different devices. For example, it generates portrait images for smartphones and landscape images for PCs. The generation AI also adjusts images to match the display characteristics of different devices (e.g., color reproduction and brightness). For example, it generates vivid images optimized for the OLED display of a smartphone. The generation AI also generates images tailored to the usage scenarios of different devices. For example, it generates educational illustrations and infographics for tablets and presentation slides for PCs. By generating images optimized for different devices, it is possible to display images optimally according to the user's usage environment.

[0090] The generated image acquisition unit can use the emotion estimation function to generate images that correspond to the user's emotional state. For example, the emotion estimation function can be used to analyze the user's emotional state in real time and generate images based on the results. For example, if the user is feeling stressed, an image of a natural landscape with a relaxing effect can be generated. The generation AI also adjusts the theme and color of the generated image according to the user's emotional state. For example, if the user is happy, a bright and colorful image can be generated, and if the user is sad, an image with a calm color tone can be generated. The emotion estimation function can also be used to automatically generate prompts for image generation that match the user's emotional state. For example, if the user wants to relax, a prompt such as "Please generate a relaxing landscape" can be automatically generated. This allows the system to generate images that correspond to the user's emotional state, thereby providing content that is in tune with the user's emotions.

[0091] The generated image acquisition unit can learn the user's past instruction history and automatically generate images that match the user's preferences. For example, the generation AI analyzes the user's past instruction history and generates images that match the user's preferences. For example, it learns the style and theme of images that the user has previously preferred and generates new images based on that. The generation AI also learns the characteristics of images that the user has given high ratings based on the user's past evaluation data and generates images based on that. For example, it generates images that reflect the user's preferred colors and composition. The generation AI also analyzes the user's past search history and browsing history and generates images based on the user's interests. For example, it generates images that reflect themes and keywords that the user frequently searches for. This allows the automatic generation of images that match the user's preferences, thereby improving user satisfaction.

[0092] The generative image acquisition unit can generate images incorporating different styles and art forms. For example, the generative AI generates images incorporating different styles and art forms. For example, it generates a variety of images for the same prompt using different art styles such as impressionism, abstract painting, and realism. The generative AI also generates images that reflect different cultural and historical backgrounds. For example, it generates images that incorporate elements of different eras and cultures, such as ancient Egyptian, Renaissance, and modern art. The generative AI also generates images that simulate different techniques and materials. For example, it generates images using different techniques and materials such as watercolor, oil painting, and digital art. This increases the variety of generated images by generating images that incorporate different styles and art forms.

[0093] The generated image acquisition unit can use the emotion estimation function to estimate the emotion a user is feeling when inputting an image generation prompt in real time and make suggestions that will elicit positive emotions. For example, the emotion estimation function can be used to analyze the emotion a user is feeling when inputting an image generation prompt in real time and make suggestions that will elicit positive emotions. For example, if the user is tired, the unit can suggest a refreshing image prompt. The unit can also automatically generate an image generation prompt based on the user's emotional state to elicit positive emotions. For example, if the user is feeling down, the unit can suggest an uplifting image prompt. The emotion estimation function can also be used to provide positive feedback in response to the prompt input by the user to enhance emotions. For example, a message such as "That's a great idea!" can be displayed in response to the prompt input by the user. In this way, the user's emotions can be estimated in real time and suggestions that will elicit positive emotions can be made, thereby improving user satisfaction.

[0094] The feature extraction unit can extract features by taking image metadata into consideration. For example, the generative AI analyzes image metadata and extracts features based on information such as the shooting location, time, and camera settings. For example, it learns the characteristics of images taken in a specific location and extracts the color and light patterns unique to that location. It also extracts features under different shooting conditions based on image metadata. For example, it compares the features of images taken under different conditions, such as daytime and nighttime, or sunny and cloudy days, and extracts similarities and differences. The generative AI also uses image metadata to extract features based on specific camera settings (e.g., shutter speed and aperture value). For example, it learns the features of images taken with a long exposure and extracts those features. This allows for more accurate feature extraction by taking image metadata into consideration.

[0095] The feature extraction unit recognizes objects within an image and can extract the presence of specific objects as features. For example, the generation AI recognizes objects within an image and extracts the presence of specific objects as features. For example, it recognizes people, animals, buildings, etc. within an image and extracts their presence as features. The generation AI also analyzes the position and size of objects within an image and extracts them as features. For example, it extracts features based on the arrangement and size of objects within an image. The generation AI also analyzes the relationships between objects within an image and extracts them as features. For example, it extracts features based on how multiple objects are arranged and what relationships they have. In this way, by recognizing objects within an image, it is possible to extract the presence of specific objects as features.

[0096] The feature extraction unit uses the emotion estimation function to consider the user's emotional state when extracting image features, thereby extracting features that are likely to be emotionally relatable. For example, the emotion estimation function is used to analyze the user's emotional state in real time, and features that are likely to be emotionally relatable are extracted based on the results. For example, parts to which the user showed a strong emotional reaction are preferentially extracted as features. Furthermore, specific elements in the image (e.g., color tone or composition) are extracted as features that are likely to be emotionally relatable based on the user's emotional state. For example, color tone or composition that the user showed positive emotions are extracted as features. Furthermore, the emotion estimation function is used to analyze the user's emotional state, and the image feature extraction algorithm is adjusted based on the results. For example, the algorithm is adjusted to preferentially extract features that are likely to be emotionally relatable by the user. In this way, features that are likely to be emotionally relatable can be extracted by taking the user's emotional state into consideration.

[0097] The feature extraction unit can extract features using different visual characteristics. For example, the generation AI uses infrared images to extract features that are not visible in normal visible light images. For example, it analyzes infrared images and extracts temperature distribution and the location of heat sources as features. The generation AI also uses thermal images to extract features of an object's temperature and thermal radiation. For example, it analyzes thermal images and extracts the temperature distribution and thermal radiation pattern of a specific object as features. The generation AI also combines different visual characteristics to extract features from multiple perspectives. For example, it combines and analyzes visible light images and infrared images, and integrates the features obtained from both perspectives. This makes it possible to extract a wider variety of features by using different visual characteristics.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The generated image acquisition unit acquires the image generated by the generation AI. For example, the generation AI generates an image based on instructions from a user, and the generated image appears to be an actual image taken with a camera. Step 2: The feature extraction unit extracts features from the generated image acquired by the generated image acquisition unit, such as color distribution, edge information, texture, etc. of the image. Step 3: The comparison unit compares the features extracted by the feature extraction unit with the features of the actual image, for example, based on the degree of similarity in color distribution, edge information, texture, etc. Step 4: The judgment unit judges whether the generated image is valid as learning data based on the results of the comparison by the comparison unit. For example, if the color distribution, edge information, and texture show a high degree of similarity with the actual image, it is judged to be valid, and if the degree of similarity is low, it is judged to be invalid. Step 5: The output unit outputs the result of the judgment made by the judgment unit. For example, it displays a message such as "This generated image is valid as learning data."

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 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.

[0105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0110] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0111] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0113] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 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.

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

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0150] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0151] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0152] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0153] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0154] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0155] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0156] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0158] 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.

[0159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0160] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0161] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0164] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0165] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0166] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a generated image acquisition unit that acquires the image generated by the generation AI; a feature extraction unit that extracts features from the generated image acquired by the generated image acquisition unit; a comparison unit that compares the features extracted by the feature extraction unit with features of an actual image; a determination unit that determines whether the generated image is valid as learning data based on the comparison result by the comparison unit; an output unit that outputs the result determined by the determination unit; A system characterized by:

2. The generated image acquisition unit Generate images that incorporate different styles and art forms 2. The system of claim 1.

3. The generated image acquisition unit Learns the user's past instruction history and automatically generates images that match the user's preferences 2. The system of claim 1.

4. The generated image acquisition unit Generate images according to the user's emotional state 2. The system of claim 1.

5. The generated image acquisition unit Combine generated images with audio and text to provide multimedia content 2. The system of claim 1.

6. The generated image acquisition unit Generate optimized images for different devices 2. The system of claim 1.

Images