system

Abstract

The system according to this embodiment aims to automate the video and photograph restoration process, making it efficient and highly accurate. [Solution] The system according to the embodiment comprises an analysis unit, an image quality improvement unit, a correction unit, and an adjustment unit. The analysis unit analyzes the age, style, and cultural background of the video or photograph. The image quality improvement unit improves the image quality based on the information analyzed by the analysis unit. The correction unit performs color correction and style application based on the image quality improved by the image quality improvement unit. The adjustment unit collects user feedback on the video or photograph corrected by the correction unit and improves the model.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there are problems that it takes a great deal of time and labor to repair videos and photos, and color correction and image quality improvement tend to be uneven.

[0005] The system according to the embodiment aims to automate the video and photo repair process and perform it efficiently and with high precision.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an image quality improvement unit, a correction unit, and an adjustment unit. The analysis unit analyzes the age, style, and cultural background of the video or photograph. The image quality improvement unit improves the image quality based on the information analyzed by the analysis unit. The correction unit performs color correction and style application based on the image quality improved by the image quality improvement unit. The adjustment unit collects user feedback on the video or photograph corrected by the correction unit and improves the model. [Effects of the Invention]

[0007] The system according to this embodiment can automate the video and photo restoration process, enabling it to be performed efficiently and with high accuracy. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that automates and streamlines the restoration of images and photographs. This AI agent system analyzes the age, style, and cultural background of images and photographs and sets an appropriate correction plan. Next, it improves image quality using deep learning technology. Furthermore, it performs color correction and style application, and finally collects user feedback to improve the model. For example, the AI ​​agent system uses generative AI to analyze the age, style, and cultural background of images and photographs. The generative AI analyzes the features of images and photographs and sets an appropriate correction plan. Next, the AI ​​agent system uses Super-Resolution technology to restore low-resolution areas to high definition. For example, it uses SRCNN or GAN models to improve image quality. Furthermore, the AI ​​agent system performs color correction and style application using CycleGAN or style transfer technology. This applies the most appropriate colors for the era and culture to images and photographs. Finally, the AI ​​agent system collects user feedback and continuously improves the model. For example, it collects user feedback via generative AI and reflects the adjustments to optimize the final result. This automates and speeds up the restoration process and reduces the workload. Furthermore, high-precision correction becomes possible, improving the archival value of videos and photographs. This facilitates the deployment of videos and photographs to new markets. As a result, AI agent systems can automate and streamline the video and photograph restoration process.

[0029] The AI ​​agent system according to this embodiment comprises an analysis unit, an image quality improvement unit, a correction unit, and an adjustment unit. The analysis unit analyzes the age, style, and cultural background of the video or photograph. The analysis unit analyzes the features of the video or photograph using, for example, generative AI. The analysis unit needs to clarify the specific range and criteria of the age. For example, this includes a specific year or era classification. The analysis unit needs to clarify the specific type and criteria of the style. For example, this includes art style, design style, etc. The analysis unit needs to clarify the specific range and criteria of the cultural background. For example, this includes a specific region or cultural characteristics. The image quality improvement unit restores low-resolution parts to high resolution using Super-Resolution technology. The image quality improvement unit improves image quality using, for example, SRCNN or GAN models. The image quality improvement unit needs to clarify the specific methods and criteria for image quality improvement. For example, this includes resolution improvement and noise reduction. The correction unit performs color correction and style application using CycleGAN or style transfer technology. The correction unit corrects the colors of the video or photograph using, for example, CycleGAN. The correction unit needs to clearly define the specific methods and criteria for color correction. For example, this includes adjusting color temperature and correcting hue. The correction unit also needs to clearly define the specific methods and criteria for style application. For example, this includes applying a specific art style and using filters. The adjustment unit collects user feedback and continuously improves the model. For example, the adjustment unit collects user feedback using generative AI. The adjustment unit needs to clearly define the specific methods and criteria for collecting feedback. For example, this includes surveys and user reviews. As a result, the AI ​​agent system according to the embodiment can automate and streamline the video and photo restoration process.

[0030] The analysis unit analyzes the age, style, and cultural background of videos and photographs. For example, the analysis unit uses generative AI to analyze the characteristics of videos and photographs. Specifically, the generative AI analyzes the pixel information of videos and photographs in detail and extracts characteristics related to age, style, and cultural background. In age analysis, the unit identifies the time when the video or photograph was taken based on a specific year or period. For example, since the characteristics of the film and camera used differ between a photograph from the 1920s and a photograph from the present day, the generative AI learns these differences and identifies the age. In style analysis, the unit identifies the style of the video or photograph based on specific types such as art style or design style. For example, it learns the characteristics of styles such as Baroque and Art Deco and classifies the style of the video or photograph. In cultural background analysis, the unit identifies the cultural background of the video or photograph based on specific regions or cultural characteristics. For example, it learns the characteristics of Japanese ukiyo-e prints or European Renaissance paintings and analyzes the cultural background of the video or photograph. This allows the analysis unit to analyze the age, style, and cultural background of images and photographs in detail, providing the information necessary for the restoration process.

[0031] The image quality enhancement unit uses Super-Resolution technology to restore low-resolution areas to high definition. Specifically, it improves image quality using SRCNN and GAN models. SRCNN (Super-Resolution Convolutional Neural Network) is a convolutional neural network for converting low-resolution images to high-resolution images, analyzing the pixel information of the input image to generate a high-resolution image. GAN (Generative Adversarial Network) is a technology that generates high-quality images by having two networks, a generative model and a discriminative model, compete, and is used when converting low-resolution images to high-resolution images. By using a combination of these technologies, the image quality enhancement unit achieves improved resolution and reduced noise. For example, it restores details in low-resolution videos and photographs to produce sharp images. In addition, for noisy videos and photographs, it applies noise reduction technology to produce clear images. As a result, the image quality enhancement unit can restore low-resolution videos and photographs to high definition and improve the quality of the restoration process.

[0032] The correction unit performs color correction and style application using CycleGAN and style transfer technology. CycleGAN (Cycle-Consistent Generative Adversarial Network) is a technology that performs image conversion between different domains, and is used, for example, when converting a black and white photograph to a color photograph. The correction unit uses CycleGAN to correct the colors of videos and photographs and reproduce natural hues. Specifically, CycleGAN analyzes the pixel information of a black and white photograph and generates appropriate colors. It also uses style transfer technology to apply specific art styles or design styles to videos and photographs. For example, by applying the style of Van Gogh's paintings to a photograph, the photograph can be transformed into a work of art. By using these technologies in combination, the correction unit adjusts the color temperature and corrects the hue to achieve color correction of videos and photographs. It also applies specific art styles and filters to give videos and photographs a unique style. In this way, the correction unit can perform color correction and style application of videos and photographs and improve the quality of the restoration process.

[0033] The adjustment unit collects user feedback and continuously improves the model. Specifically, it uses generative AI to collect user feedback and reflects it in the analysis, image quality enhancement, and correction departments. Methods of collecting feedback include questionnaires, user reviews, and usage log data. For example, users evaluate restored videos and photos, and the generative AI analyzes the evaluation results. Based on the user's evaluation results, the generative AI identifies which parts of the restoration process need improvement and provides feedback to each department. Based on this feedback, the adjustment unit continuously improves the models in the analysis, image quality enhancement, and correction departments. For example, based on user feedback, the analysis department's date identification algorithm is improved to achieve more accurate date identification. Also, the image quality enhancement department's Super-Resolution technology is improved to generate higher-definition images. Furthermore, the correction department's color correction algorithm is improved to reproduce more natural colors. In this way, the adjustment unit can improve the overall system performance by utilizing user feedback.

[0034] The analysis unit can analyze the age, style, and cultural background of videos and photographs. For example, it can use generative AI to analyze the characteristics of videos and photographs. The analysis unit needs to clearly define the specific range and criteria for age, such as a particular year or period. The analysis unit also needs to clearly define the specific type and criteria for style, such as art style or design style. Furthermore, the analysis unit needs to clearly define the specific range and criteria for cultural background, such as a particular region or cultural characteristics. By analyzing the age, style, and cultural background of videos and photographs, an appropriate correction plan can be established.

[0035] The image quality enhancement unit can restore low-resolution areas to high definition using Super-Resolution technology. The image quality enhancement unit improves image quality using, for example, SRCNN or GAN models. The image quality enhancement unit needs to clearly define specific methods and criteria for image quality improvement. These include, for example, resolution improvement and noise reduction. This allows for the restoration of low-resolution areas to high definition using Super-Resolution technology.

[0036] The correction unit can perform color correction and style application using CycleGAN and style transfer technology. For example, the correction unit can correct the colors of video and photographs using CycleGAN. The correction unit needs to clearly define the specific methods and criteria for color correction, such as adjusting color temperature and correcting hue. The correction unit also needs to clearly define the specific methods and criteria for style application, such as applying a specific art style and using filters. This allows for the application of colors to video and photographs that are optimal for the era and culture, using CycleGAN and style transfer technology.

[0037] The adjustment unit can collect user feedback and continuously improve the model. For example, the adjustment unit collects user feedback using generative AI. The adjustment unit needs to clearly define the specific methods and criteria for collecting feedback, such as surveys and user reviews. This allows for the optimization of the final product by collecting user feedback and continuously improving the model.

[0038] The image quality enhancement unit can improve image quality using SRCNN or GAN models. For example, it can improve the resolution of videos and photos using SRCNN. It can also improve image quality by reducing noise using GAN models. The image quality enhancement unit needs to clearly define specific methods and criteria for image quality improvement. These include, for example, improving resolution and reducing noise. This allows for image quality improvement using SRCNN or GAN models.

[0039] The analysis unit can optimize its analysis algorithm by referring to past analysis data when analyzing video and photographs. For example, the analysis unit can refer to past analysis data using generative AI. Based on past analysis data, the analysis unit can apply algorithms specialized for specific eras or styles. The analysis unit can also select analysis methods suitable for specific cultural backgrounds by referring to past analysis data. The analysis unit can also adjust parameters to improve analysis accuracy using past analysis data. In this way, by referring to past analysis data, the analysis algorithm can be optimized and analysis accuracy can be improved.

[0040] The analysis unit can improve the accuracy of video and photograph analysis by considering the metadata of the subject being analyzed. For example, the analysis unit analyzes metadata using generative AI. The analysis unit adjusts the analysis algorithm based on the shooting date and time included in the metadata. The analysis unit can also perform analysis that takes into account region-specific styles by using the shooting location information included in the metadata. The analysis unit can also improve the accuracy of analysis by referring to the camera setting information included in the metadata. In this way, the accuracy of analysis can be improved by considering the metadata of the subject being analyzed.

[0041] The analysis unit can perform analysis of video and photographs while considering the geographical background information of the subject of analysis. For example, the analysis unit can analyze geographical background information using generative AI. Based on the geographical background information, the analysis unit performs analysis that takes into account the unique style of the region. The analysis unit can also select an analysis method suitable for a specific region by referring to the geographical background information. The analysis unit can also adjust parameters to improve the accuracy of the analysis using the geographical background information. As a result, by considering the geographical background information of the subject of analysis, it becomes possible to perform analysis that takes into account the unique style of the region.

[0042] The analysis unit can improve the accuracy of its analysis by referring to relevant literature on the subject of analysis when analyzing video or photographs. For example, the analysis unit can use generative AI to refer to relevant literature. Based on the relevant literature, the analysis unit can apply algorithms specific to particular eras or styles. The analysis unit can also select analysis methods appropriate to a specific cultural background by referring to relevant literature. Furthermore, the analysis unit can adjust parameters to improve analysis accuracy using relevant literature. In this way, the accuracy of the analysis can be improved by referring to relevant literature on the subject of analysis.

[0043] The image quality enhancement unit can optimize its algorithm by referring to past image quality enhancement data during image quality enhancement. For example, the image quality enhancement unit can refer to past image quality enhancement data using generative AI. Based on past image quality enhancement data, the image quality enhancement unit applies algorithms specialized for specific eras or styles. The image quality enhancement unit can also select image quality enhancement methods suitable for specific cultural backgrounds by referring to past image quality enhancement data. The image quality enhancement unit can also adjust parameters to improve image quality enhancement accuracy using past image quality enhancement data. In this way, by referring to past image quality enhancement data, the algorithm can be optimized and image quality enhancement accuracy can be improved.

[0044] The image quality enhancement unit can apply different image quality enhancement methods depending on the category of the video or photograph. For example, the image quality enhancement unit can use generative AI to apply image quality enhancement methods appropriate to the category. If the video or photograph is a landscape, the image quality enhancement unit can apply an image quality enhancement method that emphasizes natural colors. If the video or photograph is a portrait, the image quality enhancement unit can also apply an image quality enhancement method that makes skin tones appear more natural. If the video or photograph is of architecture, the image quality enhancement unit can also apply an image quality enhancement method that emphasizes fine details. By applying different image quality enhancement methods depending on the category of the video or photograph, optimal image quality enhancement becomes possible.

[0045] The image quality enhancement unit can select the optimal image quality enhancement method by considering the shooting conditions of the video or photograph during image quality enhancement. For example, the image quality enhancement unit analyzes the shooting conditions using generative AI. If the shooting conditions are dark, the image quality enhancement unit applies an image quality enhancement method that reduces noise. If the shooting conditions are bright, the image quality enhancement unit can also apply an image quality enhancement method that enhances contrast. If the shooting conditions are cloudy, the image quality enhancement unit can also apply an image quality enhancement method that makes the colors more vivid. In this way, the optimal image quality enhancement method can be selected by considering the shooting conditions of the video or photograph.

[0046] The image quality enhancement unit can improve the accuracy of image quality enhancement by referring to relevant literature on the video and photographs during the enhancement process. For example, the image quality enhancement unit uses generative AI to refer to relevant literature. Based on the relevant literature, the image quality enhancement unit applies image quality enhancement techniques specific to a particular era or style. The image quality enhancement unit can also select image quality enhancement techniques appropriate to a particular cultural background by referring to relevant literature. Furthermore, the image quality enhancement unit can adjust parameters to improve the accuracy of image quality enhancement using relevant literature. This allows for improved accuracy of image quality enhancement by referring to relevant literature on the video and photographs.

[0047] The correction unit can optimize its algorithm by referencing past correction data when applying color correction and style. For example, the correction unit can reference past correction data using generative AI. Based on past correction data, the correction unit applies algorithms specific to particular eras or styles. The correction unit can also select correction methods suitable for specific cultural backgrounds by referencing past correction data. Furthermore, the correction unit can adjust parameters to improve correction accuracy using past correction data. This allows for algorithm optimization and improved correction accuracy by referencing past correction data.

[0048] The correction unit can apply different correction methods depending on the category of the video or photograph when applying color correction and style. For example, the correction unit can use generative AI to apply a category-appropriate correction method. If the video or photograph is a landscape, the correction unit can apply a correction method that emphasizes natural colors. If the video or photograph is a portrait, the correction unit can also apply a correction method that makes skin tones look natural. If the video or photograph is of architecture, the correction unit can also apply a correction method that emphasizes fine details. This allows for optimal correction by applying different correction methods depending on the category of the video or photograph.

[0049] The correction unit can select the optimal correction method when applying color correction and style, taking into account the shooting conditions of the video or photograph. For example, the correction unit analyzes the shooting conditions using generative AI. If the shooting conditions are dark, the correction unit applies a correction method that reduces noise. If the shooting conditions are bright, the correction unit can also apply a correction method that enhances contrast. If the shooting conditions are cloudy, the correction unit can also apply a correction method that makes the colors more vibrant. In this way, the optimal correction method can be selected by taking into account the shooting conditions of the video or photograph.

[0050] The correction unit can improve the accuracy of color correction and style application by referencing relevant literature for the video or photograph. For example, the correction unit uses generative AI to reference relevant literature. Based on the relevant literature, the correction unit applies correction methods specific to a particular era or style. The correction unit can also select correction methods appropriate to a particular cultural background by referencing relevant literature. The correction unit can also use relevant literature to adjust parameters to improve correction accuracy. This allows for improved correction accuracy by referencing relevant literature for the video or photograph.

[0051] The adjustment unit can optimize the feedback collection algorithm by referring to past feedback data during feedback collection. For example, the adjustment unit can refer to past feedback data using generative AI. Based on past feedback data, the adjustment unit can apply feedback collection methods specific to a particular era or style. The adjustment unit can also select a feedback collection method suitable for a particular cultural background by referring to past feedback data. The adjustment unit can also use past feedback data to adjust parameters to improve the accuracy of feedback collection. In this way, by referring to past feedback data, the collection algorithm can be optimized and the accuracy of feedback collection can be improved.

[0052] The adjustment unit can improve the accuracy of feedback collection by considering user attribute information. For example, the adjustment unit analyzes attribute information using generative AI. The adjustment unit selects an appropriate feedback collection method based on the user's age and gender. The adjustment unit can also provide a more relevant feedback collection method by referring to the user's occupation and hobbies. The adjustment unit can also improve the accuracy of feedback collection by considering the user's place of residence and cultural background. In this way, the accuracy of collection can be improved by considering the user's attribute information.

[0053] The adjustment unit can collect feedback while considering the user's geographical background information. For example, the adjustment unit analyzes geographical background information using generative AI. Based on the geographical background information, the adjustment unit applies region-specific feedback collection methods. The adjustment unit can also select a feedback collection method suitable for a specific region by referring to the geographical background information. The adjustment unit can also use the geographical background information to adjust parameters to improve the accuracy of feedback collection. This makes it possible to collect region-specific feedback by considering the user's geographical background information.

[0054] The adjustment unit can improve the accuracy of feedback collection by referring to the user's relevant literature. For example, the adjustment unit can refer to relevant literature using generative AI. Based on the relevant literature, the adjustment unit applies feedback collection methods specific to a particular era or style. The adjustment unit can also select a feedback collection method suitable for a particular cultural background by referring to relevant literature. The adjustment unit can also use relevant literature to adjust parameters to improve the accuracy of feedback collection. In this way, the accuracy of collection can be improved by referring to the user's relevant literature.

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

[0056] The analysis unit can provide real-time analysis results when analyzing video and photographs. For example, the analysis unit uses generative AI to analyze the features of video and photographs in real time. Based on the real-time analysis results, the analysis unit can immediately set a correction plan. The analysis unit also provides real-time analysis results as feedback to the user, allowing the user to issue correction instructions on the spot. By providing real-time analysis results, a rapid repair process is possible, and user needs can be responded to immediately.

[0057] The image quality enhancement unit can use a combination of different image quality enhancement algorithms when improving the image quality of videos and photos. For example, the image quality enhancement unit can use a combination of SRCNN and a GAN model. The image quality enhancement unit can improve resolution using SRCNN and reduce noise using a GAN model. By combining different algorithms, the image quality enhancement unit can achieve higher precision image quality enhancement. In this way, the accuracy of image quality enhancement can be further improved by combining different image quality enhancement algorithms.

[0058] The correction unit can apply a specific art style selected by the user when performing color correction and style application on videos and photos. For example, the correction unit performs color correction based on the art style selected by the user. The correction unit can also apply styles based on the art style selected by the user. The correction unit can adjust the color temperature and hue according to the art style selected by the user. This allows for color correction and style application tailored to the user's preferences by applying a specific art style selected by the user.

[0059] The adjustment unit can automatically classify the content of user feedback when collecting it. For example, the adjustment unit analyzes the feedback using generative AI. The adjustment unit can classify the feedback into positive, negative, or neutral categories. The adjustment unit can also classify the feedback by category and identify specific problems. This allows for efficient feedback analysis and improvement of the model by automatically classifying the feedback content.

[0060] The analysis unit can visually display the analysis results when analyzing video or photographs. For example, the analysis unit can display the analysis results as graphs or charts using generative AI. The analysis unit can also display the analysis results as a heatmap to highlight specific features. The analysis unit can also display the analysis results in an interactive format, allowing users to check detailed information. This makes it easier for users to intuitively understand the analysis results by visually displaying them.

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

[0062] Step 1: The analysis unit analyzes the age, style, and cultural background of the video or photograph. The analysis unit uses generative AI to analyze the characteristics of the video or photograph, clarifying the specific range and criteria for the age, the specific type and criteria for the style, and the specific range and criteria for the cultural background. Step 2: The image quality enhancement unit improves image quality based on the information analyzed by the analysis unit. The image quality enhancement unit uses Super-Resolution technology to restore low-resolution areas to high resolution and improves image quality using SRCNN or GAN models. Step 3: The correction unit performs color correction and style application based on the image quality improved by the image quality enhancement unit. The correction unit uses CycleGAN and style transfer technology to perform color correction and style application, including adjusting color temperature, correcting hue, applying specific art styles, and using filters. Step 4: The adjustment unit collects user feedback on the images and photos corrected by the correction unit and improves the model. The adjustment unit uses generative AI to collect user feedback and continuously improves the model through surveys, user reviews, etc.

[0063] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that automates and streamlines the restoration of images and photographs. This AI agent system analyzes the age, style, and cultural background of images and photographs and sets an appropriate correction plan. Next, it improves image quality using deep learning technology. Furthermore, it performs color correction and style application, and finally collects user feedback to improve the model. For example, the AI ​​agent system uses generative AI to analyze the age, style, and cultural background of images and photographs. The generative AI analyzes the features of images and photographs and sets an appropriate correction plan. Next, the AI ​​agent system uses Super-Resolution technology to restore low-resolution areas to high definition. For example, it uses SRCNN or GAN models to improve image quality. Furthermore, the AI ​​agent system performs color correction and style application using CycleGAN or style transfer technology. This applies the most appropriate colors for the era and culture to images and photographs. Finally, the AI ​​agent system collects user feedback and continuously improves the model. For example, it collects user feedback via generative AI and reflects the adjustments to optimize the final result. This automates and speeds up the restoration process and reduces the workload. Furthermore, high-precision correction becomes possible, improving the archival value of videos and photographs. This facilitates the deployment of videos and photographs to new markets. As a result, AI agent systems can automate and streamline the video and photograph restoration process.

[0064] The AI ​​agent system according to this embodiment comprises an analysis unit, an image quality improvement unit, a correction unit, and an adjustment unit. The analysis unit analyzes the age, style, and cultural background of the video or photograph. The analysis unit analyzes the features of the video or photograph using, for example, generative AI. The analysis unit needs to clarify the specific range and criteria of the age. For example, this includes a specific year or era classification. The analysis unit needs to clarify the specific type and criteria of the style. For example, this includes art style, design style, etc. The analysis unit needs to clarify the specific range and criteria of the cultural background. For example, this includes a specific region or cultural characteristics. The image quality improvement unit restores low-resolution parts to high resolution using Super-Resolution technology. The image quality improvement unit improves image quality using, for example, SRCNN or GAN models. The image quality improvement unit needs to clarify the specific methods and criteria for image quality improvement. For example, this includes resolution improvement and noise reduction. The correction unit performs color correction and style application using CycleGAN or style transfer technology. The correction unit corrects the colors of the video or photograph using, for example, CycleGAN. The correction unit needs to clearly define the specific methods and criteria for color correction. For example, this includes adjusting color temperature and correcting hue. The correction unit also needs to clearly define the specific methods and criteria for style application. For example, this includes applying a specific art style and using filters. The adjustment unit collects user feedback and continuously improves the model. For example, the adjustment unit collects user feedback using generative AI. The adjustment unit needs to clearly define the specific methods and criteria for collecting feedback. For example, this includes surveys and user reviews. As a result, the AI ​​agent system according to the embodiment can automate and streamline the video and photo restoration process.

[0065] The analysis unit analyzes the age, style, and cultural background of videos and photographs. For example, the analysis unit uses generative AI to analyze the characteristics of videos and photographs. Specifically, the generative AI analyzes the pixel information of videos and photographs in detail and extracts characteristics related to age, style, and cultural background. In age analysis, the unit identifies the time when the video or photograph was taken based on a specific year or period. For example, since the characteristics of the film and camera used differ between a photograph from the 1920s and a photograph from the present day, the generative AI learns these differences and identifies the age. In style analysis, the unit identifies the style of the video or photograph based on specific types such as art style or design style. For example, it learns the characteristics of styles such as Baroque and Art Deco and classifies the style of the video or photograph. In cultural background analysis, the unit identifies the cultural background of the video or photograph based on specific regions or cultural characteristics. For example, it learns the characteristics of Japanese ukiyo-e prints or European Renaissance paintings and analyzes the cultural background of the video or photograph. This allows the analysis unit to analyze the age, style, and cultural background of images and photographs in detail, providing the information necessary for the restoration process.

[0066] The image quality enhancement unit uses Super-Resolution technology to restore low-resolution areas to high definition. Specifically, it improves image quality using SRCNN and GAN models. SRCNN (Super-Resolution Convolutional Neural Network) is a convolutional neural network for converting low-resolution images to high-resolution images, analyzing the pixel information of the input image to generate a high-resolution image. GAN (Generative Adversarial Network) is a technology that generates high-quality images by having two networks, a generative model and a discriminative model, compete, and is used when converting low-resolution images to high-resolution images. By using a combination of these technologies, the image quality enhancement unit achieves improved resolution and reduced noise. For example, it restores details in low-resolution videos and photographs to produce sharp images. In addition, for noisy videos and photographs, it applies noise reduction technology to produce clear images. As a result, the image quality enhancement unit can restore low-resolution videos and photographs to high definition and improve the quality of the restoration process.

[0067] The correction unit performs color correction and style application using CycleGAN and style transfer technology. CycleGAN (Cycle-Consistent Generative Adversarial Network) is a technology that performs image conversion between different domains, and is used, for example, when converting a black and white photograph to a color photograph. The correction unit uses CycleGAN to correct the colors of videos and photographs and reproduce natural hues. Specifically, CycleGAN analyzes the pixel information of a black and white photograph and generates appropriate colors. It also uses style transfer technology to apply specific art styles or design styles to videos and photographs. For example, by applying the style of Van Gogh's paintings to a photograph, the photograph can be transformed into a work of art. By using these technologies in combination, the correction unit adjusts the color temperature and corrects the hue to achieve color correction of videos and photographs. It also applies specific art styles and filters to give videos and photographs a unique style. In this way, the correction unit can perform color correction and style application of videos and photographs and improve the quality of the restoration process.

[0068] The adjustment unit collects user feedback and continuously improves the model. Specifically, it uses generative AI to collect user feedback and reflects it in the analysis, image quality enhancement, and correction departments. Methods of collecting feedback include questionnaires, user reviews, and usage log data. For example, users evaluate restored videos and photos, and the generative AI analyzes the evaluation results. Based on the user's evaluation results, the generative AI identifies which parts of the restoration process need improvement and provides feedback to each department. Based on this feedback, the adjustment unit continuously improves the models in the analysis, image quality enhancement, and correction departments. For example, based on user feedback, the analysis department's date identification algorithm is improved to achieve more accurate date identification. Also, the image quality enhancement department's Super-Resolution technology is improved to generate higher-definition images. Furthermore, the correction department's color correction algorithm is improved to reproduce more natural colors. In this way, the adjustment unit can improve the overall system performance by utilizing user feedback.

[0069] The analysis unit can analyze the age, style, and cultural background of videos and photographs. For example, it can use generative AI to analyze the characteristics of videos and photographs. The analysis unit needs to clearly define the specific range and criteria for age, such as a particular year or period. The analysis unit also needs to clearly define the specific type and criteria for style, such as art style or design style. Furthermore, the analysis unit needs to clearly define the specific range and criteria for cultural background, such as a particular region or cultural characteristics. By analyzing the age, style, and cultural background of videos and photographs, an appropriate correction plan can be established.

[0070] The image quality enhancement unit can restore low-resolution areas to high definition using Super-Resolution technology. The image quality enhancement unit improves image quality using, for example, SRCNN or GAN models. The image quality enhancement unit needs to clearly define specific methods and criteria for image quality improvement. These include, for example, resolution improvement and noise reduction. This allows for the restoration of low-resolution areas to high definition using Super-Resolution technology.

[0071] The correction unit can perform color correction and style application using CycleGAN and style transfer technology. For example, the correction unit can correct the colors of video and photographs using CycleGAN. The correction unit needs to clearly define the specific methods and criteria for color correction, such as adjusting color temperature and correcting hue. The correction unit also needs to clearly define the specific methods and criteria for style application, such as applying a specific art style and using filters. This allows for the application of colors to video and photographs that are optimal for the era and culture, using CycleGAN and style transfer technology.

[0072] The adjustment unit can collect user feedback and continuously improve the model. For example, the adjustment unit collects user feedback using generative AI. The adjustment unit needs to clearly define the specific methods and criteria for collecting feedback, such as surveys and user reviews. This allows for the optimization of the final product by collecting user feedback and continuously improving the model.

[0073] The image quality enhancement unit can improve image quality using SRCNN or GAN models. For example, it can improve the resolution of videos and photos using SRCNN. It can also improve image quality by reducing noise using GAN models. The image quality enhancement unit needs to clearly define specific methods and criteria for image quality improvement. These include, for example, improving resolution and reducing noise. This allows for image quality improvement using SRCNN or GAN models.

[0074] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit estimates the user's emotions using an emotion engine or generative AI. If the user is excited, the analysis unit visually highlights and displays the analysis results. If the user is relaxed, the analysis unit can also display the analysis results in calming colors. If the user is feeling anxious, the analysis unit can also display the analysis results in a simple and easy-to-understand manner. This allows for a user-friendly display by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0075] The analysis unit can optimize its analysis algorithm by referring to past analysis data when analyzing video and photographs. For example, the analysis unit can refer to past analysis data using generative AI. Based on past analysis data, the analysis unit can apply algorithms specialized for specific eras or styles. The analysis unit can also select analysis methods suitable for specific cultural backgrounds by referring to past analysis data. The analysis unit can also adjust parameters to improve analysis accuracy using past analysis data. In this way, by referring to past analysis data, the analysis algorithm can be optimized and analysis accuracy can be improved.

[0076] The analysis unit can improve the accuracy of video and photograph analysis by considering the metadata of the subject being analyzed. For example, the analysis unit analyzes metadata using generative AI. The analysis unit adjusts the analysis algorithm based on the shooting date and time included in the metadata. The analysis unit can also perform analysis that takes into account region-specific styles by using the shooting location information included in the metadata. The analysis unit can also improve the accuracy of analysis by referring to the camera setting information included in the metadata. In this way, the accuracy of analysis can be improved by considering the metadata of the subject being analyzed.

[0077] The analysis unit can estimate the user's emotions and determine the priority of analysis results based on the estimated emotions. For example, the analysis unit estimates the user's emotions using an emotion engine or generative AI. If the user is excited, the analysis unit displays important analysis results first. If the user is relaxed, the analysis unit can also display analysis results sequentially. If the user is anxious, the analysis unit can also display analysis results in stages. This allows the system to prioritize information important to the user by determining the priority of analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0078] The analysis unit can perform analysis of video and photographs while considering the geographical background information of the subject of analysis. For example, the analysis unit can analyze geographical background information using generative AI. Based on the geographical background information, the analysis unit performs analysis that takes into account the unique style of the region. The analysis unit can also select an analysis method suitable for a specific region by referring to the geographical background information. The analysis unit can also adjust parameters to improve the accuracy of the analysis using the geographical background information. As a result, by considering the geographical background information of the subject of analysis, it becomes possible to perform analysis that takes into account the unique style of the region.

[0079] The analysis unit can improve the accuracy of its analysis by referring to relevant literature on the subject of analysis when analyzing video or photographs. For example, the analysis unit can use generative AI to refer to relevant literature. Based on the relevant literature, the analysis unit can apply algorithms specific to particular eras or styles. The analysis unit can also select analysis methods appropriate to a specific cultural background by referring to relevant literature. Furthermore, the analysis unit can adjust parameters to improve analysis accuracy using relevant literature. In this way, the accuracy of the analysis can be improved by referring to relevant literature on the subject of analysis.

[0080] The image quality enhancement unit can estimate the user's emotions and adjust the image quality enhancement method based on the estimated emotions. For example, the image quality enhancement unit estimates the user's emotions using an emotion engine or generative AI. When the user is relaxed, the image quality enhancement unit performs natural image quality enhancement. When the user is excited, the image quality enhancement unit can also enhance image quality by emphasizing vivid colors. When the user is anxious, the image quality enhancement unit can also enhance image quality with calming colors. This allows for optimal image quality enhancement for the user by adjusting the image quality enhancement method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] The image quality enhancement unit can optimize its algorithm by referring to past image quality enhancement data during image quality enhancement. For example, the image quality enhancement unit can refer to past image quality enhancement data using generative AI. Based on past image quality enhancement data, the image quality enhancement unit applies algorithms specialized for specific eras or styles. The image quality enhancement unit can also select image quality enhancement methods suitable for specific cultural backgrounds by referring to past image quality enhancement data. The image quality enhancement unit can also adjust parameters to improve image quality enhancement accuracy using past image quality enhancement data. In this way, by referring to past image quality enhancement data, the algorithm can be optimized and image quality enhancement accuracy can be improved.

[0082] The image quality enhancement unit can apply different image quality enhancement methods depending on the category of the video or photograph. For example, the image quality enhancement unit can use generative AI to apply image quality enhancement methods appropriate to the category. If the video or photograph is a landscape, the image quality enhancement unit can apply an image quality enhancement method that emphasizes natural colors. If the video or photograph is a portrait, the image quality enhancement unit can also apply an image quality enhancement method that makes skin tones appear more natural. If the video or photograph is of architecture, the image quality enhancement unit can also apply an image quality enhancement method that emphasizes fine details. By applying different image quality enhancement methods depending on the category of the video or photograph, optimal image quality enhancement becomes possible.

[0083] The image quality enhancement unit can estimate the user's emotions and determine the priority of image quality enhancements based on the estimated emotions. The image quality enhancement unit estimates the user's emotions using, for example, an emotion engine or generative AI. If the user is excited, the image quality enhancement unit prioritizes enhancing the image quality of important parts. If the user is relaxed, the image quality enhancement unit can sequentially enhance the overall image quality. If the user is feeling anxious, the image quality enhancement unit can also gradually enhance the image quality of specific parts. This allows for prioritizing image quality enhancements according to the user's emotions, thereby prioritizing enhancements to parts important to the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The image quality enhancement unit can select the optimal image quality enhancement method by considering the shooting conditions of the video or photograph during image quality enhancement. For example, the image quality enhancement unit analyzes the shooting conditions using generative AI. If the shooting conditions are dark, the image quality enhancement unit applies an image quality enhancement method that reduces noise. If the shooting conditions are bright, the image quality enhancement unit can also apply an image quality enhancement method that enhances contrast. If the shooting conditions are cloudy, the image quality enhancement unit can also apply an image quality enhancement method that makes the colors more vivid. In this way, the optimal image quality enhancement method can be selected by considering the shooting conditions of the video or photograph.

[0085] The image quality enhancement unit can improve the accuracy of image quality enhancement by referring to relevant literature on the video and photographs during the enhancement process. For example, the image quality enhancement unit uses generative AI to refer to relevant literature. Based on the relevant literature, the image quality enhancement unit applies image quality enhancement techniques specific to a particular era or style. The image quality enhancement unit can also select image quality enhancement techniques appropriate to a particular cultural background by referring to relevant literature. Furthermore, the image quality enhancement unit can adjust parameters to improve the accuracy of image quality enhancement using relevant literature. This allows for improved accuracy of image quality enhancement by referring to relevant literature on the video and photographs.

[0086] The correction unit can estimate the user's emotions and adjust the color correction and style application methods based on the estimated user emotions. For example, the correction unit estimates the user's emotions using an emotion engine or generative AI. If the user is relaxed, the correction unit performs color correction that emphasizes natural colors. If the user is excited, the correction unit can also perform color correction that emphasizes vibrant colors. If the user is feeling anxious, the correction unit can also perform color correction with calmer tones. This allows for optimal correction for the user by adjusting the color correction and style application methods according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The correction unit can optimize its algorithm by referencing past correction data when applying color correction and style. For example, the correction unit can reference past correction data using generative AI. Based on past correction data, the correction unit applies algorithms specific to particular eras or styles. The correction unit can also select correction methods suitable for specific cultural backgrounds by referencing past correction data. Furthermore, the correction unit can adjust parameters to improve correction accuracy using past correction data. This allows for algorithm optimization and improved correction accuracy by referencing past correction data.

[0088] The correction unit can apply different correction methods depending on the category of the video or photograph when applying color correction and style. For example, the correction unit can use generative AI to apply a category-appropriate correction method. If the video or photograph is a landscape, the correction unit can apply a correction method that emphasizes natural colors. If the video or photograph is a portrait, the correction unit can also apply a correction method that makes skin tones look natural. If the video or photograph is of architecture, the correction unit can also apply a correction method that emphasizes fine details. This allows for optimal correction by applying different correction methods depending on the category of the video or photograph.

[0089] The correction unit can estimate the user's emotions and determine the priority of color correction and style application based on the estimated user emotions. The correction unit estimates the user's emotions using, for example, an emotion engine or generative AI. If the user is excited, the correction unit first applies color correction and style application to important parts. If the user is relaxed, the correction unit can also sequentially apply color correction and style application to the entire image. If the user is feeling anxious, the correction unit can also apply color correction and style application to specific parts in stages. This allows for prioritizing corrections to parts that are important to the user by determining the priority of color correction and style application according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The correction unit can select the optimal correction method when applying color correction and style, taking into account the shooting conditions of the video or photograph. For example, the correction unit analyzes the shooting conditions using generative AI. If the shooting conditions are dark, the correction unit applies a correction method that reduces noise. If the shooting conditions are bright, the correction unit can also apply a correction method that enhances contrast. If the shooting conditions are cloudy, the correction unit can also apply a correction method that makes the colors more vibrant. In this way, the optimal correction method can be selected by taking into account the shooting conditions of the video or photograph.

[0091] The correction unit can improve the accuracy of color correction and style application by referencing relevant literature for the video or photograph. For example, the correction unit uses generative AI to reference relevant literature. Based on the relevant literature, the correction unit applies correction methods specific to a particular era or style. The correction unit can also select correction methods appropriate to a particular cultural background by referencing relevant literature. The correction unit can also use relevant literature to adjust parameters to improve correction accuracy. This allows for improved correction accuracy by referencing relevant literature for the video or photograph.

[0092] The adjustment unit can estimate the user's emotions and adjust the feedback collection method based on the estimated user emotions. For example, the adjustment unit estimates the user's emotions using an emotion engine or generative AI. If the user is relaxed, the adjustment unit provides questions requesting detailed feedback. If the user is in a hurry, the adjustment unit can also provide questions requesting concise feedback. If the user is feeling anxious, the adjustment unit can also provide a reassuring feedback collection method. This allows for optimal feedback collection for the user by adjusting the feedback collection method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The adjustment unit can optimize the feedback collection algorithm by referring to past feedback data during feedback collection. For example, the adjustment unit can refer to past feedback data using generative AI. Based on past feedback data, the adjustment unit can apply feedback collection methods specific to a particular era or style. The adjustment unit can also select a feedback collection method suitable for a particular cultural background by referring to past feedback data. The adjustment unit can also use past feedback data to adjust parameters to improve the accuracy of feedback collection. In this way, by referring to past feedback data, the collection algorithm can be optimized and the accuracy of feedback collection can be improved.

[0094] The adjustment unit can improve the accuracy of feedback collection by considering user attribute information. For example, the adjustment unit analyzes attribute information using generative AI. The adjustment unit selects an appropriate feedback collection method based on the user's age and gender. The adjustment unit can also provide a more relevant feedback collection method by referring to the user's occupation and hobbies. The adjustment unit can also improve the accuracy of feedback collection by considering the user's place of residence and cultural background. In this way, the accuracy of collection can be improved by considering the user's attribute information.

[0095] The adjustment unit can estimate the user's emotions and determine the priority of feedback based on the estimated emotions. The adjustment unit estimates the user's emotions using, for example, an emotion engine or generative AI. If the user is excited, the adjustment unit collects important feedback first. If the user is relaxed, the adjustment unit can also collect overall feedback sequentially. If the user is anxious, the adjustment unit can also collect specific feedback step by step. This allows for the priority collection of feedback that is important to the user by determining the priority of feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The adjustment unit can collect feedback while considering the user's geographical background information. For example, the adjustment unit analyzes geographical background information using generative AI. Based on the geographical background information, the adjustment unit applies region-specific feedback collection methods. The adjustment unit can also select a feedback collection method suitable for a specific region by referring to the geographical background information. The adjustment unit can also use the geographical background information to adjust parameters to improve the accuracy of feedback collection. This makes it possible to collect region-specific feedback by considering the user's geographical background information.

[0097] The adjustment unit can improve the accuracy of feedback collection by referring to the user's relevant literature. For example, the adjustment unit can refer to relevant literature using generative AI. Based on the relevant literature, the adjustment unit applies feedback collection methods specific to a particular era or style. The adjustment unit can also select a feedback collection method suitable for a particular cultural background by referring to relevant literature. The adjustment unit can also use relevant literature to adjust parameters to improve the accuracy of feedback collection. In this way, the accuracy of collection can be improved by referring to the user's relevant literature.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The analysis unit can provide real-time analysis results when analyzing video and photographs. For example, the analysis unit uses generative AI to analyze the features of video and photographs in real time. Based on the real-time analysis results, the analysis unit can immediately set a correction plan. The analysis unit also provides real-time analysis results as feedback to the user, allowing the user to issue correction instructions on the spot. By providing real-time analysis results, a rapid repair process is possible, and user needs can be responded to immediately.

[0100] The image quality enhancement unit can use a combination of different image quality enhancement algorithms when improving the image quality of videos and photos. For example, the image quality enhancement unit can use a combination of SRCNN and a GAN model. The image quality enhancement unit can improve resolution using SRCNN and reduce noise using a GAN model. By combining different algorithms, the image quality enhancement unit can achieve higher precision image quality enhancement. In this way, the accuracy of image quality enhancement can be further improved by combining different image quality enhancement algorithms.

[0101] The correction unit can apply a specific art style selected by the user when performing color correction and style application on videos and photos. For example, the correction unit performs color correction based on the art style selected by the user. The correction unit can also apply styles based on the art style selected by the user. The correction unit can adjust the color temperature and hue according to the art style selected by the user. This allows for color correction and style application tailored to the user's preferences by applying a specific art style selected by the user.

[0102] The adjustment unit can automatically classify the content of user feedback when collecting it. For example, the adjustment unit analyzes the feedback using generative AI. The adjustment unit can classify the feedback into positive, negative, or neutral categories. The adjustment unit can also classify the feedback by category and identify specific problems. This allows for efficient feedback analysis and improvement of the model by automatically classifying the feedback content.

[0103] The analysis unit can visually display the analysis results when analyzing video or photographs. For example, the analysis unit can display the analysis results as graphs or charts using generative AI. The analysis unit can also display the analysis results as a heatmap to highlight specific features. The analysis unit can also display the analysis results in an interactive format, allowing users to check detailed information. This makes it easier for users to intuitively understand the analysis results by visually displaying them.

[0104] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, the analysis unit estimates the user's emotions using an emotion engine or generative AI. If the user is excited, the analysis unit visually highlights and displays the analysis results. If the user is relaxed, the analysis unit can also display the analysis results in calming colors. If the user is feeling anxious, the analysis unit can also display the analysis results in a simple and easy-to-understand manner. By adjusting how the analysis results are displayed according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand.

[0105] The image quality enhancement unit can estimate the user's emotions and adjust the image quality enhancement method based on the estimated emotions. For example, the image quality enhancement unit estimates the user's emotions using an emotion engine or generative AI. When the user is relaxed, the image quality enhancement unit performs natural image quality enhancement. When the user is excited, the image quality enhancement unit can also enhance image quality by emphasizing vibrant colors. When the user is feeling anxious, the image quality enhancement unit can also enhance image quality with calming colors. This allows for optimal image quality enhancement for the user by adjusting the image quality enhancement method according to the user's emotions.

[0106] The correction unit can estimate the user's emotions and adjust the color correction and style application methods based on the estimated emotions. For example, the correction unit estimates the user's emotions using an emotion engine or generative AI. When the user is relaxed, the correction unit performs color correction that emphasizes natural colors. When the user is excited, the correction unit can also perform color correction that emphasizes vivid colors. When the user is feeling anxious, the correction unit can also perform color correction with calming tones. This allows for optimal correction for the user by adjusting the color correction and style application methods according to the user's emotions.

[0107] The adjustment unit can estimate the user's emotions and adjust the feedback collection method based on the estimated emotions. For example, the adjustment unit estimates the user's emotions using an emotion engine or generative AI. If the user is relaxed, the adjustment unit provides questions that request detailed feedback. If the user is in a hurry, the adjustment unit can also provide questions that request concise feedback. If the user is feeling anxious, the adjustment unit can also provide feedback collection methods that provide reassurance. By adjusting the feedback collection method according to the user's emotions, it becomes possible to collect the most optimal feedback for the user.

[0108] The adjustment unit can estimate the user's emotions and prioritize feedback based on those emotions. For example, the adjustment unit estimates the user's emotions using an emotion engine or generative AI. If the user is excited, the adjustment unit collects important feedback first. If the user is relaxed, the adjustment unit can also collect overall feedback sequentially. If the user is anxious, the adjustment unit can also collect specific feedback step by step. This allows for the priority collection of feedback that is important to the user by prioritizing feedback according to the user's emotions.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The analysis unit analyzes the age, style, and cultural background of the video or photograph. The analysis unit uses generative AI to analyze the characteristics of the video or photograph, clarifying the specific range and criteria for the age, the specific type and criteria for the style, and the specific range and criteria for the cultural background. Step 2: The image quality enhancement unit improves image quality based on the information analyzed by the analysis unit. The image quality enhancement unit uses Super-Resolution technology to restore low-resolution areas to high resolution and improves image quality using SRCNN or GAN models. Step 3: The correction unit performs color correction and style application based on the image quality improved by the image quality enhancement unit. The correction unit uses CycleGAN and style transfer technology to perform color correction and style application, including adjusting color temperature, correcting hue, applying specific art styles, and using filters. Step 4: The adjustment unit collects user feedback on the images and photos corrected by the correction unit and improves the model. The adjustment unit uses generative AI to collect user feedback and continuously improves the model through surveys, user reviews, etc.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the analysis unit, image quality enhancement unit, correction unit, and adjustment unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 and analyzes the age, style, and cultural background of images and photographs. The image quality enhancement unit is implemented by the specific processing unit 290 of the data processing unit 12 and restores low-resolution areas to high definition using Super-Resolution technology. The correction unit is implemented by the control unit 46A of the smart device 14 and performs color correction and style application using CycleGAN or style transfer technology. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and collects user feedback to continuously improve the model. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the analysis unit, image quality enhancement unit, correction unit, and adjustment unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the age, style, and cultural background of images and photographs. The image quality enhancement unit is implemented by the specific processing unit 290 of the data processing unit 12 and restores low-resolution areas to high definition using Super-Resolution technology. The correction unit is implemented by the control unit 46A of the smart glasses 214 and performs color correction and style application using CycleGAN or style transfer technology. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and collects user feedback to continuously improve the model. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

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

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the analysis unit, image quality enhancement unit, correction unit, and adjustment unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the age, style, and cultural background of images and photographs. The image quality enhancement unit is implemented by the specific processing unit 290 of the data processing unit 12 and restores low-resolution areas to high definition using Super-Resolution technology. The correction unit is implemented by the control unit 46A of the headset terminal 314 and performs color correction and style application using CycleGAN or style transfer technology. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and collects user feedback to continuously improve the model. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

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

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the analysis unit, image quality enhancement unit, correction unit, and adjustment unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 and analyzes the age, style, and cultural background of images and photographs. The image quality enhancement unit is implemented by the specific processing unit 290 of the data processing unit 12 and restores low-resolution areas to high definition using Super-Resolution technology. The correction unit is implemented by the control unit 46A of the robot 414 and performs color correction and style application using CycleGAN or style transfer technology. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and collects user feedback to continuously improve the model. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0164] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] 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.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) The analysis department analyzes the era, style, and cultural background of the videos and photographs, An image quality improvement unit that improves image quality based on the information analyzed by the aforementioned analysis unit, A correction unit performs color correction and style application based on the image quality improved by the aforementioned image quality improvement unit, The system includes an adjustment unit that collects user feedback on images and photographs corrected by the correction unit and improves the model. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze the era, style, and cultural background of the images and photographs. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned image quality improvement unit is Super-Resolution technology is used to restore low-resolution areas to high definition. The system described in Appendix 1, characterized by the features described herein. (Note 4) The correction unit, Color correction and style application are performed using CycleGAN and style transfer techniques. The system described in Appendix 1, characterized by the features described herein. (Note 5) The adjustment unit is, We collect user feedback and continuously improve the model. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned image quality improvement unit is Improving image quality using SRCNN and GAN models The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing video and photos, the analysis algorithm is optimized by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing video and photos, consider the metadata of the subject being analyzed to improve analysis accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing video or photographs, the analysis should take into account the geographical background information of the subject being analyzed. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing video and photographs, we improve the accuracy of the analysis by referring to relevant literature on the subject of analysis. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned image quality improvement unit is It estimates the user's emotions and adjusts the method of improving image quality based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned image quality improvement unit is When improving image quality, the algorithm is optimized by referring to past image quality improvement data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned image quality improvement unit is When improving image quality, different image quality enhancement methods are applied depending on the category of the video or photo. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned image quality improvement unit is It estimates the user's emotions and determines the priority of image quality improvements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned image quality improvement unit is When improving image quality, the optimal image quality enhancement method is selected considering the shooting conditions of the video or photograph. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned image quality improvement unit is When improving image quality, we refer to relevant literature on video and photography to enhance the accuracy of the image quality improvement. The system described in Appendix 1, characterized by the features described herein. (Note 19) The correction unit, It estimates the user's emotions and adjusts the color correction and style application methods based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The correction unit, When applying color correction and styles, the algorithm is optimized by referencing past correction data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The correction unit, When applying color correction and styles, different correction methods are applied depending on the category of the video or photo. The system described in Appendix 1, characterized by the features described herein. (Note 22) The correction unit, It estimates the user's emotions and determines the priority of color correction and style application based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The correction unit, When applying color correction and styles, the optimal correction method is selected considering the shooting conditions of the video or photo. The system described in Appendix 1, characterized by the features described herein. (Note 24) The correction unit, When applying color correction and styles, refer to relevant documentation for the video and photographs to improve the accuracy of the corrections. The system described in Appendix 1, characterized by the features described herein. (Note 25) The adjustment unit is, We estimate the user's emotions and adjust the feedback collection method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The adjustment unit is, When collecting feedback, we optimize the collection algorithm by referring to past feedback data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The adjustment unit is, When collecting feedback, we improve the accuracy of the collection by considering user attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The adjustment unit is, It estimates the user's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The adjustment unit is, When collecting feedback, the system takes into account the user's geographical background information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The adjustment unit is, When collecting feedback, we improve the accuracy of the collection by referring to relevant user literature. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis department analyzes the era, style, and cultural background of the videos and photographs, An image quality improvement unit that improves image quality based on the information analyzed by the aforementioned analysis unit, A correction unit performs color correction and style application based on the image quality improved by the aforementioned image quality improvement unit, The system includes an adjustment unit that collects user feedback on images and photographs corrected by the correction unit and improves the model. A system characterized by the following features.

2. The aforementioned image quality improvement unit is Super-Resolution technology is used to restore low-resolution areas to high definition. The system according to feature 1.

3. The correction unit, Color correction and style application are performed using CycleGAN and style transfer techniques. The system according to feature 1.

4. The adjustment unit is, We collect user feedback and continuously improve the model. The system according to feature 1.

5. The aforementioned image quality improvement unit is Improving image quality using SRCNN and GAN models The system according to feature 1.

6. The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system according to feature 1.

7. The aforementioned analysis unit, When analyzing video and photos, the analysis algorithm is optimized by referring to past analysis data. The system according to feature 1.

Images