system

Abstract

The system according to this embodiment aims to efficiently manage stored image data and organize it in a way that is easily accessible to users. [Solution] The system according to the embodiment comprises an annotation unit, a vectorization unit, a text conversion unit, and an organization unit. The annotation unit performs annotation of image data. The vectorization unit processes the image data annotated by the annotation unit as vector data. The text conversion unit converts the image data processed as vector data by the vectorization unit into text in natural language. The organization unit organizes the data converted into text by the text conversion unit in a format that can be accessed by the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 is a problem that it is difficult to efficiently manage the stored image data and organize it in a form that is easily accessible to users.

[0005] The system according to the embodiment aims to efficiently manage the stored image data and organize it in a form that is easily accessible to users.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an annotation unit, a vectorization unit, a text conversion unit, and an organization unit. The annotation unit performs annotation on image data. The vectorization unit processes the image data annotated by the annotation unit as vector data. The text conversion unit converts the image data processed as vector data by the vectorization unit into text in natural language. The organization unit organizes the text data converted by the text conversion unit into a format accessible to the user. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently manage stored image data and organize it in a way that is easily accessible to users. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, 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 receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The image management system according to an embodiment of the present invention is a method to solve the problem that in modern times, many photographs are stored on HDDs or in the cloud, but are rarely looked at again. The image management system proposes an economical method to reduce the cost of image recognition by having AI process images as vector data, annotate the image data, and support the training of a highly accurate AI model, thereby managing multiple images together. Furthermore, the generative AI converts the images into text in natural language, rediscovering the stories and emotions embedded in the photographs as text, and organizing them in a form that is easily accessible to the user. This preserves the moments and emotions embedded in the photographs not merely as records, but as memories, allowing users to rediscover easily forgotten memories in words. For example, the image management system has AI process images as vector data. Specifically, by representing images as vectors (sets of numbers), it becomes easier for the AI ​​to extract and compare the features of the images. This method is a common technique used in image search and recognition, and similar image detection. Advantages of vector data include efficient searching, storage savings, and improved recognition accuracy. In efficient searching, converting to vector data allows for the comparison of similarity through calculations between numbers, enabling quick searching of images with similar features from large amounts of data. In terms of storage savings, vectorizing multiple images reduces the data size compared to the original images, making storage more economical. For improved recognition accuracy, the AI ​​can use the extracted features as vectors to more precisely capture visual similarities. Next, the generative AI translates the data into natural language text. The generative AI rediscovers the stories and emotions embedded in the photos as text, organizing them in an easily accessible format for the user. This preserves the moments and emotions contained in photos not merely as records, but as memories, allowing users to rediscover often-forgotten memories in words. For example, if the generative AI analyzes a family photo and outputs the emotions and stories embedded in it as text, users can relive the memories associated with the photo when they look back at it. This system allows for efficient photo management and increases the opportunities to revisit photos.Users can easily search for specific photos within a vast dataset and rediscover the stories and emotions embedded within them. This allows them to preserve photos not merely as records, but as memories, cherishing those memories. The image management system enables users to rediscover the moments and emotions contained within photos and organize them in a way that is easily accessible to them.

[0029] The image management system according to this embodiment comprises an annotation unit, a vectorization unit, a text conversion unit, and an organization unit. The annotation unit performs annotation on image data. For example, the annotation unit labels the image data to make it easier to identify the content of the image. The annotation unit can also tag the image data to facilitate searching and classification. For example, the annotation unit labels objects and people in the image. The annotation unit can also tag specific areas in the image. Furthermore, the annotation unit can add descriptive text to the image data. For example, the annotation unit adds text that describes the scene or situation in the image. The vectorization unit processes the image data annotated by the annotation unit as vector data. For example, the vectorization unit represents the image as a vector (a set of numbers) to make it easier for AI to extract and compare image features. By representing image features as numerical data, the vectorization unit enables efficient searching and recognition. For example, the vectorization unit extracts features such as color, shape, and pattern in the image as numerical data. The vectorization unit can represent image features as vectors and calculate similarity. For example, the vectorization unit compares image feature vectors and calculates similarity. The text conversion unit converts the image data processed as vector data by the vectorization unit into natural language text. The text conversion unit uses generative AI to rediscover the stories and emotions embedded in the images as text. For example, the text conversion unit generates text that describes the scenes and situations in the images. The text conversion unit can also express the emotions embedded in the images as text. For example, the text conversion unit estimates emotions based on the facial expressions and actions of people in the images and expresses them as text. The organization unit organizes the data converted into text by the text conversion unit in a way that is accessible to the user. For example, the organization unit classifies the text data by category so that users can easily search for it. The organization unit can also organize the text data chronologically. For example, the organization unit organizes the data based on the date and time the images were taken.The organization unit can also customize the data according to the user's preferences. For example, the organization unit organizes the data based on keywords specified by the user. This allows the image management system according to the embodiment to efficiently perform annotation, vectorization, text conversion, and organization of image data.

[0030] The annotation unit performs annotation on image data. For example, it labels image data to make its content easier to identify. It can also tag image data to facilitate searching and classification. For instance, it labels objects and people within an image. It can also tag specific areas within an image. Furthermore, it can add descriptive text to image data. For example, it adds text describing the scene or situation within the image. When labeling or tagging image data, the annotation unit can utilize AI to automatically generate labels and tags. For example, it can recognize objects within an image and automatically assign appropriate labels. It can also detect specific areas within an image and automatically generate tags related to those areas. This significantly improves the efficiency of annotation work and reduces the user's workload. Additionally, the annotation unit provides a function for users to manually add labels and tags, enabling flexible annotation. For example, users can add their own labels and tags to specific objects or scenes. This allows for customization to meet user needs, resulting in more accurate annotations. Furthermore, the annotation unit can utilize generative AI to generate natural language descriptions when adding descriptive text to image data. For example, it can automatically generate detailed text describing scenes and situations within an image, providing it in a user-friendly format. This allows for a deeper understanding of the image data content, improving the accuracy of searches and classifications.

[0031] The vectorization unit processes image data annotated by the annotation unit as vector data. For example, the vectorization unit represents images as vectors (sets of numbers), making it easier for AI to extract and compare image features. By representing image features as numerical data, the vectorization unit enables efficient searching and recognition. For example, the vectorization unit extracts features such as color, shape, and pattern within an image as numerical data. The vectorization unit can also represent image features as vectors and calculate similarity. For example, the vectorization unit compares image feature vectors to calculate similarity. When vectorizing image data, the vectorization unit can utilize deep learning techniques to extract high-dimensional features. For example, it can use a convolutional neural network (CNN) to extract image features across multiple layers, generating more accurate vector data. This allows for the capture of subtle features and complex patterns in images, improving the accuracy of similarity calculations. Furthermore, the vectorization unit builds a database for efficiently managing the generated vector data, enabling rapid searching and comparison. For example, by indexing vector data and applying a high-speed search algorithm, similar images can be quickly searched from a large amount of image data. Furthermore, the vectorization unit can be customized to meet user needs when vectorizing image data. For instance, it can perform vectorization that focuses on specific features or vectorization that is suitable for specific applications. This enables the generation of optimal vector data tailored to the user's purpose, resulting in efficient image management.

[0032] The text conversion unit converts image data, processed as vector data by the vectorization unit, into natural language text. Using generative AI, the text conversion unit rediscovers the stories and emotions embedded in the images as text. For example, it generates text that describes scenes and situations within the image. It can also express emotions embedded in images as text. For example, it estimates emotions based on the facial expressions and actions of people in the image and expresses them as text. Utilizing generative AI, the text conversion unit combines multiple models to achieve highly accurate text generation from image data. For example, by combining an image caption generation model and an emotion analysis model, it can generate text that accurately expresses emotions while providing detailed descriptions of scenes and situations within the image. This allows for a deeper understanding of the image data content and provides users with richer information. Furthermore, the text conversion unit can customize the generated text according to user needs. For example, it can generate text suitable for specific purposes or text in a specific style. This provides optimal text tailored to the user's purpose and enables efficient image management. Furthermore, the text generation unit can integrate the generated text with other systems and applications. For example, by linking the generated text to search engines and social media, image data can be easily searched and shared. This allows the text generation unit to maximize the value of image data and provide users with rich information.

[0033] The organization unit organizes the text data converted by the text conversion unit into a format accessible to users. For example, the organization unit classifies the text data by category, making it easy for users to search. The organization unit can also organize the text data chronologically. For example, it organizes data based on the date and time the image was taken. The organization unit can also customize the data according to user preferences. For example, it organizes data based on keywords specified by the user. The organization unit builds a database for efficiently managing the text data, enabling rapid searching and access. For example, by indexing the text data and applying a high-speed search algorithm, it is possible to quickly find the desired information from large amounts of data. Furthermore, the organization unit provides a user interface, allowing users to intuitively manipulate the data. For example, it provides drag-and-drop operations and filtering functions, making it easy for users to organize and search data. In addition, the organization unit can perform personalized data organization based on the user's usage history and search history. For example, it prioritizes displaying keywords and categories that the user frequently searches for, supporting efficient data access. In this way, the organization unit can achieve flexible data organization according to user needs and support efficient image management. Furthermore, the data organization unit integrates with other systems and applications to facilitate data sharing and integration. For example, it can connect with cloud storage and social media to easily share and publish text-based data. This allows the data organization unit to provide users with richer information access and maximize the value of image data.

[0034] The annotation unit can perform annotation on image data to support the training of high-precision AI models. For example, the annotation unit can label image data and use it as training data for an AI model. It can also tag image data and use it as training data for an AI model. For example, the annotation unit can label objects and people in an image. It can also tag specific areas in an image. Furthermore, the annotation unit can add descriptive text to image data. For example, the annotation unit can add text that describes the scene or situation in the image. This improves the accuracy of the annotation by supporting the training of high-precision AI models. Some or all of the above processing in the annotation unit may be performed using AI, for example, or not using AI. For example, the annotation unit can input image data into an AI, and the AI ​​can perform the annotation automatically.

[0035] The vectorization unit represents images as vectors, making it easier for AI to extract and compare image features. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also represent image features as vectors and calculate similarity. For example, the vectorization unit compares the feature vectors of images and calculates similarity. This improves the accuracy of image recognition by making it easier to extract and compare image features. Some or all of the above processing in the vectorization unit may be performed using AI, or without AI. For example, the vectorization unit can input image data into an AI, which can automatically extract features and represent them as vectors.

[0036] The text conversion unit, using a generative AI, can rediscover the stories and emotions embedded in photographs as text. For example, the text conversion unit generates text that describes the scenes and situations within the image. The text conversion unit can also express the emotions embedded in the image as text. For example, the text conversion unit estimates emotions based on the facial expressions and actions of people in the image and expresses them as text. This allows users to rediscover the stories and emotions embedded in photographs, enabling them to relive memories when looking back at the photos. Some or all of the above processing in the text conversion unit is performed using a generative AI. For example, the text conversion unit can input image data into the generative AI, which can automatically generate stories and emotions as text.

[0037] The organization unit can organize digitized data in a way that is easily accessible to users. For example, the organization unit can categorize the digitized data so that users can easily search for it. The organization unit can also organize digitized data chronologically. For example, the organization unit can organize data based on the date and time the image was taken. The organization unit can also customize the data according to user preferences. For example, the organization unit can organize data based on keywords specified by the user. This streamlines photo management by organizing the data in a way that is easily accessible to users. Some or all of the above processes in the organization unit may be performed using AI or not. For example, the organization unit can input digitized data into AI, and the AI ​​can automatically organize the data.

[0038] The vectorization unit converts data into vector data, allowing it to compare similarities through numerical calculations and quickly search for images with similar features from a large amount of data. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also represent image features as vectors and calculate similarity. For example, the vectorization unit compares image feature vectors and calculates similarity. This allows it to quickly search for images with similar features from a large amount of data. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image data into AI, which can automatically extract features and represent them as vectors.

[0039] The vectorization unit reduces the data size of multiple images by vectorizing them, making them more economical to store. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also reduce the data size by representing the image features as vectors. For example, the vectorization unit compresses the image feature vectors to reduce the data size. This reduces the data size and makes it more economical to store images. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image data into an AI, which can automatically extract features, represent them as vectors, and reduce the data size.

[0040] The vectorization unit can capture visual similarities more precisely by using the features extracted as vectors. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also represent the features of an image as vectors and capture visual similarities. For example, the vectorization unit compares the feature vectors of images to capture visual similarities. This allows for a more precise capture of visual similarities. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image data into an AI, which can automatically extract features, represent them as vectors, and capture visual similarities.

[0041] The annotation unit can adjust the level of detail of annotations based on the date, time, and location where the image was taken. For example, if the image was taken at a specific event, the annotation unit will add detailed annotations related to that event. If the image was taken during a trip, the annotation unit can also add annotations that include information about the travel destination. For example, if the image is a snapshot of everyday life, the annotation unit will add concise annotations. By adjusting the level of detail of annotations based on the date, time, and location where the image was taken, more appropriate annotations can be provided. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input data on the date, time, and location where the image was taken into the AI, and the AI ​​can automatically adjust the level of detail of the annotations.

[0042] The annotation unit can apply different annotation algorithms depending on the image category during the annotation process. For example, for landscape photographs, it can apply an annotation algorithm that emphasizes natural elements. For portraits, it can also add annotations about individual people using face recognition technology. For example, for food photographs, it can add annotations about the names of the dishes and ingredients. By applying different annotation algorithms depending on the image category, it is possible to provide more appropriate annotations. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input image category data into AI, and the AI ​​can automatically apply an annotation algorithm.

[0043] The annotation unit can perform annotation while considering the attribute information of the image's photographer. For example, the annotation unit can add annotations that include technical details to images taken by professional photographers. For images taken by amateurs, the annotation unit can also add concise and easy-to-understand annotations. For example, the annotation unit can add annotations that reflect the child's perspective to images taken by children. This allows for more appropriate annotations by considering the attribute information of the image's photographer. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input the image's photographer's attribute information into AI, and the AI ​​can perform the annotation automatically.

[0044] The annotation unit can improve the accuracy of annotations by referring to relevant literature for the image during the annotation process. For example, the annotation unit can obtain the historical background of a building in an image from relevant literature and add it to the annotation. The annotation unit can also obtain the types of plants in an image from relevant literature and add them to the annotation. For example, the annotation unit can obtain background information of a person in an image from relevant literature and add it to the annotation. This allows the accuracy of annotations to be improved by referring to relevant literature for the image. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input data from relevant literature into AI, and the AI ​​can automatically improve the accuracy of the annotations.

[0045] The vectorization unit can adjust the level of detail in the vectorization process based on the date, time, and location where the image was taken. For example, if the image was taken at a specific event, the vectorization unit will perform detailed vectorization related to that event. If the image was taken during a trip, the vectorization unit can also perform vectorization that includes information about the travel destination. For example, if the image is a snapshot of everyday life, the vectorization unit will perform simple vectorization. By adjusting the level of detail in the vectorization process based on the date, time, and location where the image was taken, a more appropriate vectorization can be provided. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input data on the date, time, and location where the image was taken into the AI, which can then automatically adjust the level of detail in the vectorization.

[0046] The vectorization unit can apply different vectorization algorithms depending on the image category during the vectorization process. For example, for landscape photographs, the vectorization unit can apply a vectorization algorithm that emphasizes natural elements. For portraits, the vectorization unit can also perform vectorization of individual people using face recognition technology. For example, for food photographs, the vectorization unit can perform vectorization of the dish name and ingredients. By applying different vectorization algorithms depending on the image category, more appropriate vectorization can be provided. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image category data into AI, and the AI ​​can automatically apply a vectorization algorithm.

[0047] The vectorization unit can perform vectorization while considering the attribute information of the image's photographer. For example, the vectorization unit can perform vectorization that includes technical details for images taken by professional photographers. For images taken by amateurs, the vectorization unit can also perform vectorization that is simple and easy to understand. For example, the vectorization unit can perform vectorization that reflects the child's perspective for images taken by children. By considering the attribute information of the image's photographer during vectorization, a more appropriate vectorization can be provided. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input the attribute information of the image's photographer into AI, and the AI ​​can automatically perform vectorization.

[0048] The vectorization unit can improve the accuracy of vectorization by referring to related literature for the image during the vectorization process. For example, the vectorization unit can obtain the historical background of buildings in the image from related literature and reflect it in the vectorization. The vectorization unit can also obtain the types of plants in the image from related literature and reflect them in the vectorization. For example, the vectorization unit can obtain background information of people in the image from related literature and reflect it in the vectorization. This allows the accuracy of vectorization to be improved by referring to related literature for the image. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input data from related literature into AI, and the AI ​​can automatically improve the accuracy of vectorization.

[0049] The text conversion unit can adjust the level of detail in the text conversion based on the importance of the image. For example, the text conversion unit can perform detailed text conversion on images of important events, while performing concise text conversion on images of everyday scenes. For example, the text conversion unit can perform detailed text conversion related to a specific theme on images related to that theme. By adjusting the level of detail in the text conversion based on the importance of the image, it is possible to provide more appropriate text conversion. Some or all of the above processing in the text conversion unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the text conversion unit can input image importance data into a generation AI, which can then automatically adjust the level of detail in the text conversion.

[0050] The text conversion unit can apply different text conversion algorithms depending on the image category during the text conversion process. For example, the text conversion unit can apply a text conversion algorithm that emphasizes natural elements to landscape photographs. For portrait photographs, the text conversion unit can also perform detailed text conversion about individual people. For example, the text conversion unit can convert food photographs into text about the names of dishes and ingredients. By applying different text conversion algorithms depending on the image category, more appropriate text conversion can be provided. Some or all of the above processing in the text conversion unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the text conversion unit can input image category data into a generative AI, and the generative AI can automatically apply a text conversion algorithm.

[0051] The text conversion unit can determine the priority of text conversion based on the date and time the image was taken. For example, if the image was taken at a specific event, the text conversion unit will prioritize text related to that event. If the image was taken during a trip, the text conversion unit may also prioritize text containing information about the travel destination. For example, if the image is a snapshot of everyday life, the text conversion unit will prioritize concise text. This allows for more appropriate text conversion by determining the priority of text conversion based on the date and time the image was taken. Some or all of the above processing in the text conversion unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the text conversion unit can input the image's date and time data into a generation AI, which can then automatically determine the priority of text conversion.

[0052] The text conversion unit can adjust the order of text conversion based on the relevance of the images. For example, if an image is related to a specific theme, the text conversion unit will prioritize text conversion related to that theme. The text conversion unit can also perform text conversion consecutively if the images were taken at the same event. For example, if images belong to different categories, the text conversion unit will adjust the order of text conversion for each category. This allows for more appropriate text conversion by adjusting the order of text conversion based on the relevance of the images. Some or all of the above processing in the text conversion unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the text conversion unit can input image relevance data into a generative AI, which can then automatically adjust the order of text conversion.

[0053] The sorting unit can select the optimal sorting method by referring to the user's past access history during sorting. For example, the sorting unit may prioritize displaying images that the user has frequently accessed in the past. If the sorting unit has viewed many images of a particular category in the past, it can also prioritize sorting images of that category. For example, the sorting unit may predict and sort images that the user will access at a specific time based on their past access history. This allows for more appropriate sorting by selecting the optimal sorting method by referring to the user's past access history. Some or all of the above processing in the sorting unit may be performed using AI or not. For example, the sorting unit can input the user's past access history data into AI, which can then automatically select the optimal sorting method.

[0054] The organization unit can select the optimal organization method while considering the user's device information. For example, if the user is using a smartphone, the organization unit provides an organization method that matches the screen size. If the user is using a tablet, the organization unit can also provide an organization method optimized for a larger screen. For example, if the user is using a desktop, the organization unit provides an organization method that includes detailed information. This allows for more appropriate organization by selecting the optimal organization method while considering the user's device information. Some or all of the above processing in the organization unit may be performed using AI or not. For example, the organization unit can input the user's device information into the AI, and the AI ​​can automatically select the optimal organization method.

[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 annotation unit can adjust the level of detail of annotations based on the date, time, and location where the image was taken. For example, if an image was taken at a specific event, detailed annotations related to that event can be added. If an image was taken during a trip, annotations including information about the travel destination can also be added. Furthermore, if the image is a snapshot of everyday life, concise annotations can be added. By adjusting the level of detail of annotations based on the date, time, and location where the image was taken, more appropriate annotations can be provided. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input data on the date, time, and location where the image was taken into the AI, and the AI ​​can automatically adjust the level of detail of the annotations.

[0057] The vectorization unit can adjust the level of detail in the vectorization process based on the date, time, and location where the image was taken. For example, if the image was taken at a specific event, it can perform detailed vectorization related to that event. If the image was taken during a trip, it can also perform vectorization that includes information about the travel destination. Furthermore, if the image is a snapshot of everyday life, it can perform simplified vectorization. By adjusting the level of detail in the vectorization process based on the date, time, and location where the image was taken, it is possible to provide more appropriate vectorization. Some or all of the above processing in the vectorization unit may be performed using AI, or it may be performed without AI. For example, the vectorization unit can input data on the date, time, and location where the image was taken into the AI, and the AI ​​can automatically adjust the level of detail in the vectorization.

[0058] The text conversion unit can adjust the level of detail in the text conversion based on the importance of the image. For example, images of important events can be converted to detailed text, while images of everyday scenes can be converted to concise text. Furthermore, images related to a specific theme can be converted to detailed text related to that theme. By adjusting the level of detail in the text conversion based on the importance of the image, more appropriate text conversion can be provided. Some or all of the above processing in the text conversion unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the text conversion unit can input image importance data into a generation AI, which can then automatically adjust the level of detail in the text conversion.

[0059] The sorting unit can select the optimal sorting method by referring to the user's past access history during sorting. For example, it can prioritize displaying images that the user has frequently accessed in the past. If the user has viewed many images of a particular category in the past, it can also prioritize sorting images of that category. Furthermore, it can predict and sort images that the user will access at specific times based on their past access history. By selecting the optimal sorting method by referring to the user's past access history, it can provide a more appropriate sorting service. Some or all of the above processing in the sorting unit may be performed using AI, or not. For example, the sorting unit can input the user's past access history data into AI, which can then automatically select the optimal sorting method.

[0060] The organization unit can select the optimal organization method while considering the user's device information. For example, if the user is using a smartphone, it can provide an organization method that matches the screen size. If the user is using a tablet, it can also provide an organization method optimized for a larger screen. Furthermore, if the user is using a desktop, it can provide an organization method that includes detailed information. By selecting the optimal organization method while considering the user's device information, a more appropriate organization can be provided. Some or all of the above processing in the organization unit may be performed using AI or not. For example, the organization unit can input the user's device information into the AI, and the AI ​​can automatically select the optimal organization method.

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

[0062] Step 1: The annotation section performs annotation on the image data. Specifically, it labels and tags the image data to make the content of the image easier to identify. It is also possible to label objects and people within the image, or tag specific areas. Furthermore, it is possible to add descriptive text to the image data, adding text that explains the scene or situation within the image. Step 2: The vectorization unit processes the image data annotated by the annotation unit as vector data. Specifically, it represents the image as a vector (a set of numbers), making it easier for the AI ​​to extract and compare image features. Representing image features as numerical data enables efficient searching and recognition. For example, features such as color, shape, and pattern within an image can be extracted as numerical data, and the similarity can be calculated by comparing the feature vectors. Step 3: The text conversion unit converts the image data, which has been processed as vector data by the vectorization unit, into natural language text. Specifically, it uses generative AI to rediscover the story and emotions embedded in the image as text. For example, it can generate text that describes the scene or situation in the image, or estimate emotions based on the facial expressions and actions of people in the image and express them as text. Step 4: The organization unit organizes the data converted into text by the text conversion unit in a format accessible to the user. Specifically, it classifies the text data into categories so that users can easily search for it. It can also organize the text data chronologically or customize the data according to the user's preferences. For example, it is possible to organize the data based on keywords specified by the user.

[0063] (Example of form 2) The image management system according to an embodiment of the present invention is a method to solve the problem that in modern times, many photographs are stored on HDDs or in the cloud, but are rarely looked at again. The image management system proposes an economical method to reduce the cost of image recognition by having AI process images as vector data, annotate the image data, and support the training of a highly accurate AI model, thereby managing multiple images together. Furthermore, the generative AI converts the images into text in natural language, rediscovering the stories and emotions embedded in the photographs as text, and organizing them in a form that is easily accessible to the user. This preserves the moments and emotions embedded in the photographs not merely as records, but as memories, allowing users to rediscover easily forgotten memories in words. For example, the image management system has AI process images as vector data. Specifically, by representing images as vectors (sets of numbers), it becomes easier for the AI ​​to extract and compare the features of the images. This method is a common technique used in image search and recognition, and similar image detection. Advantages of vector data include efficient searching, storage savings, and improved recognition accuracy. In efficient searching, converting to vector data allows for the comparison of similarity through calculations between numbers, enabling quick searching of images with similar features from large amounts of data. In terms of storage savings, vectorizing multiple images reduces the data size compared to the original images, making storage more economical. For improved recognition accuracy, the AI ​​can use the extracted features as vectors to more precisely capture visual similarities. Next, the generative AI translates the data into natural language text. The generative AI rediscovers the stories and emotions embedded in the photos as text, organizing them in an easily accessible format for the user. This preserves the moments and emotions contained in photos not merely as records, but as memories, allowing users to rediscover often-forgotten memories in words. For example, if the generative AI analyzes a family photo and outputs the emotions and stories embedded in it as text, users can relive the memories associated with the photo when they look back at it. This system allows for efficient photo management and increases the opportunities to revisit photos.Users can easily search for specific photos within a vast dataset and rediscover the stories and emotions embedded within them. This allows them to preserve photos not merely as records, but as memories, cherishing those memories. The image management system enables users to rediscover the moments and emotions contained within photos and organize them in a way that is easily accessible to them.

[0064] The image management system according to this embodiment comprises an annotation unit, a vectorization unit, a text conversion unit, and an organization unit. The annotation unit performs annotation on image data. For example, the annotation unit labels the image data to make it easier to identify the content of the image. The annotation unit can also tag the image data to facilitate searching and classification. For example, the annotation unit labels objects and people in the image. The annotation unit can also tag specific areas in the image. Furthermore, the annotation unit can add descriptive text to the image data. For example, the annotation unit adds text that describes the scene or situation in the image. The vectorization unit processes the image data annotated by the annotation unit as vector data. For example, the vectorization unit represents the image as a vector (a set of numbers) to make it easier for AI to extract and compare image features. By representing image features as numerical data, the vectorization unit enables efficient searching and recognition. For example, the vectorization unit extracts features such as color, shape, and pattern in the image as numerical data. The vectorization unit can represent image features as vectors and calculate similarity. For example, the vectorization unit compares image feature vectors and calculates similarity. The text conversion unit converts the image data processed as vector data by the vectorization unit into natural language text. The text conversion unit uses generative AI to rediscover the stories and emotions embedded in the images as text. For example, the text conversion unit generates text that describes the scenes and situations in the images. The text conversion unit can also express the emotions embedded in the images as text. For example, the text conversion unit estimates emotions based on the facial expressions and actions of people in the images and expresses them as text. The organization unit organizes the data converted into text by the text conversion unit in a way that is accessible to the user. For example, the organization unit classifies the text data by category so that users can easily search for it. The organization unit can also organize the text data chronologically. For example, the organization unit organizes the data based on the date and time the images were taken.The organization unit can also customize the data according to the user's preferences. For example, the organization unit organizes the data based on keywords specified by the user. This allows the image management system according to the embodiment to efficiently perform annotation, vectorization, text conversion, and organization of image data.

[0065] The annotation unit performs annotation on image data. For example, it labels image data to make its content easier to identify. It can also tag image data to facilitate searching and classification. For instance, it labels objects and people within an image. It can also tag specific areas within an image. Furthermore, it can add descriptive text to image data. For example, it adds text describing the scene or situation within the image. When labeling or tagging image data, the annotation unit can utilize AI to automatically generate labels and tags. For example, it can recognize objects within an image and automatically assign appropriate labels. It can also detect specific areas within an image and automatically generate tags related to those areas. This significantly improves the efficiency of annotation work and reduces the user's workload. Additionally, the annotation unit provides a function for users to manually add labels and tags, enabling flexible annotation. For example, users can add their own labels and tags to specific objects or scenes. This allows for customization to meet user needs, resulting in more accurate annotations. Furthermore, the annotation unit can utilize generative AI to generate natural language descriptions when adding descriptive text to image data. For example, it can automatically generate detailed text describing scenes and situations within an image, providing it in a user-friendly format. This allows for a deeper understanding of the image data content, improving the accuracy of searches and classifications.

[0066] The vectorization unit processes image data annotated by the annotation unit as vector data. For example, the vectorization unit represents images as vectors (sets of numbers), making it easier for AI to extract and compare image features. By representing image features as numerical data, the vectorization unit enables efficient searching and recognition. For example, the vectorization unit extracts features such as color, shape, and pattern within an image as numerical data. The vectorization unit can also represent image features as vectors and calculate similarity. For example, the vectorization unit compares image feature vectors to calculate similarity. When vectorizing image data, the vectorization unit can utilize deep learning techniques to extract high-dimensional features. For example, it can use a convolutional neural network (CNN) to extract image features across multiple layers, generating more accurate vector data. This allows for the capture of subtle features and complex patterns in images, improving the accuracy of similarity calculations. Furthermore, the vectorization unit builds a database for efficiently managing the generated vector data, enabling rapid searching and comparison. For example, by indexing vector data and applying a high-speed search algorithm, similar images can be quickly searched from a large amount of image data. Furthermore, the vectorization unit can be customized to meet user needs when vectorizing image data. For instance, it can perform vectorization that focuses on specific features or vectorization that is suitable for specific applications. This enables the generation of optimal vector data tailored to the user's purpose, resulting in efficient image management.

[0067] The text conversion unit converts image data, processed as vector data by the vectorization unit, into natural language text. Using generative AI, the text conversion unit rediscovers the stories and emotions embedded in the images as text. For example, it generates text that describes scenes and situations within the image. It can also express emotions embedded in images as text. For example, it estimates emotions based on the facial expressions and actions of people in the image and expresses them as text. Utilizing generative AI, the text conversion unit combines multiple models to achieve highly accurate text generation from image data. For example, by combining an image caption generation model and an emotion analysis model, it can generate text that accurately expresses emotions while providing detailed descriptions of scenes and situations within the image. This allows for a deeper understanding of the image data content and provides users with richer information. Furthermore, the text conversion unit can customize the generated text according to user needs. For example, it can generate text suitable for specific purposes or text in a specific style. This provides optimal text tailored to the user's purpose and enables efficient image management. Furthermore, the text generation unit can integrate the generated text with other systems and applications. For example, by linking the generated text to search engines and social media, image data can be easily searched and shared. This allows the text generation unit to maximize the value of image data and provide users with rich information.

[0068] The organization unit organizes the text data converted by the text conversion unit into a format accessible to users. For example, the organization unit classifies the text data by category, making it easy for users to search. The organization unit can also organize the text data chronologically. For example, it organizes data based on the date and time the image was taken. The organization unit can also customize the data according to user preferences. For example, it organizes data based on keywords specified by the user. The organization unit builds a database for efficiently managing the text data, enabling rapid searching and access. For example, by indexing the text data and applying a high-speed search algorithm, it is possible to quickly find the desired information from large amounts of data. Furthermore, the organization unit provides a user interface, allowing users to intuitively manipulate the data. For example, it provides drag-and-drop operations and filtering functions, making it easy for users to organize and search data. In addition, the organization unit can perform personalized data organization based on the user's usage history and search history. For example, it prioritizes displaying keywords and categories that the user frequently searches for, supporting efficient data access. In this way, the organization unit can achieve flexible data organization according to user needs and support efficient image management. Furthermore, the data organization unit integrates with other systems and applications to facilitate data sharing and integration. For example, it can connect with cloud storage and social media to easily share and publish text-based data. This allows the data organization unit to provide users with richer information access and maximize the value of image data.

[0069] The annotation unit can perform annotation on image data to support the training of high-precision AI models. For example, the annotation unit can label image data and use it as training data for an AI model. It can also tag image data and use it as training data for an AI model. For example, the annotation unit can label objects and people in an image. It can also tag specific areas in an image. Furthermore, the annotation unit can add descriptive text to image data. For example, the annotation unit can add text that describes the scene or situation in the image. This improves the accuracy of the annotation by supporting the training of high-precision AI models. Some or all of the above processing in the annotation unit may be performed using AI, for example, or not using AI. For example, the annotation unit can input image data into an AI, and the AI ​​can perform the annotation automatically.

[0070] The vectorization unit represents images as vectors, making it easier for AI to extract and compare image features. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also represent image features as vectors and calculate similarity. For example, the vectorization unit compares the feature vectors of images and calculates similarity. This improves the accuracy of image recognition by making it easier to extract and compare image features. Some or all of the above processing in the vectorization unit may be performed using AI, or without AI. For example, the vectorization unit can input image data into an AI, which can automatically extract features and represent them as vectors.

[0071] The text conversion unit, using a generative AI, can rediscover the stories and emotions embedded in photographs as text. For example, the text conversion unit generates text that describes the scenes and situations within the image. The text conversion unit can also express the emotions embedded in the image as text. For example, the text conversion unit estimates emotions based on the facial expressions and actions of people in the image and expresses them as text. This allows users to rediscover the stories and emotions embedded in photographs, enabling them to relive memories when looking back at the photos. Some or all of the above processing in the text conversion unit is performed using a generative AI. For example, the text conversion unit can input image data into the generative AI, which can automatically generate stories and emotions as text.

[0072] The organization unit can organize digitized data in a way that is easily accessible to users. For example, the organization unit can categorize the digitized data so that users can easily search for it. The organization unit can also organize digitized data chronologically. For example, the organization unit can organize data based on the date and time the image was taken. The organization unit can also customize the data according to user preferences. For example, the organization unit can organize data based on keywords specified by the user. This streamlines photo management by organizing the data in a way that is easily accessible to users. Some or all of the above processes in the organization unit may be performed using AI or not. For example, the organization unit can input digitized data into AI, and the AI ​​can automatically organize the data.

[0073] The vectorization unit converts data into vector data, allowing it to compare similarities through numerical calculations and quickly search for images with similar features from a large amount of data. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also represent image features as vectors and calculate similarity. For example, the vectorization unit compares image feature vectors and calculates similarity. This allows it to quickly search for images with similar features from a large amount of data. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image data into AI, which can automatically extract features and represent them as vectors.

[0074] The vectorization unit reduces the data size of multiple images by vectorizing them, making them more economical to store. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also reduce the data size by representing the image features as vectors. For example, the vectorization unit compresses the image feature vectors to reduce the data size. This reduces the data size and makes it more economical to store images. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image data into an AI, which can automatically extract features, represent them as vectors, and reduce the data size.

[0075] The vectorization unit can capture visual similarities more precisely by using the features extracted as vectors. For example, the vectorization unit extracts features such as color, shape, and pattern from an image as numerical data. The vectorization unit can also represent the features of an image as vectors and capture visual similarities. For example, the vectorization unit compares the feature vectors of images to capture visual similarities. This allows for a more precise capture of visual similarities. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image data into an AI, which can automatically extract features, represent them as vectors, and capture visual similarities.

[0076] The annotation unit can estimate the user's emotions and adjust the content of the annotations based on the estimated emotions. For example, if the user is sad, the annotation unit can add positive annotations that alleviate the emotion. If the user is happy, the annotation unit can also add annotations that emphasize that emotion. For example, if the user is excited, the annotation unit can add annotations that reflect that excitement. In this way, by adjusting the content of the annotations based on the user's emotions, more appropriate annotations can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input user emotion data into an AI, which can then automatically estimate the emotion and adjust the content of the annotations.

[0077] The annotation unit can adjust the level of detail of annotations based on the date, time, and location where the image was taken. For example, if the image was taken at a specific event, the annotation unit will add detailed annotations related to that event. If the image was taken during a trip, the annotation unit can also add annotations that include information about the travel destination. For example, if the image is a snapshot of everyday life, the annotation unit will add concise annotations. By adjusting the level of detail of annotations based on the date, time, and location where the image was taken, more appropriate annotations can be provided. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input data on the date, time, and location where the image was taken into the AI, and the AI ​​can automatically adjust the level of detail of the annotations.

[0078] The annotation unit can apply different annotation algorithms depending on the image category during the annotation process. For example, for landscape photographs, it can apply an annotation algorithm that emphasizes natural elements. For portraits, it can also add annotations about individual people using face recognition technology. For example, for food photographs, it can add annotations about the names of the dishes and ingredients. By applying different annotation algorithms depending on the image category, it is possible to provide more appropriate annotations. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input image category data into AI, and the AI ​​can automatically apply an annotation algorithm.

[0079] The annotation unit can estimate the user's emotions and determine annotation priorities based on those estimated emotions. For example, if the user is sad, the annotation unit will prioritize adding annotations that alleviate those emotions. If the user is happy, the annotation unit can also prioritize adding annotations that emphasize that emotion. For example, if the user is excited, the annotation unit will prioritize adding annotations that reflect that excitement. This allows for the provision of more appropriate annotations by prioritizing annotations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input user emotion data into an AI, which can then automatically estimate the emotions and determine annotation priorities.

[0080] The annotation unit can perform annotation while considering the attribute information of the image's photographer. For example, the annotation unit can add annotations that include technical details to images taken by professional photographers. For images taken by amateurs, the annotation unit can also add concise and easy-to-understand annotations. For example, the annotation unit can add annotations that reflect the child's perspective to images taken by children. This allows for more appropriate annotations by considering the attribute information of the image's photographer. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input the image's photographer's attribute information into AI, and the AI ​​can perform the annotation automatically.

[0081] The annotation unit can improve the accuracy of annotations by referring to relevant literature for the image during the annotation process. For example, the annotation unit can obtain the historical background of a building in an image from relevant literature and add it to the annotation. The annotation unit can also obtain the types of plants in an image from relevant literature and add them to the annotation. For example, the annotation unit can obtain background information of a person in an image from relevant literature and add it to the annotation. This allows the accuracy of annotations to be improved by referring to relevant literature for the image. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input data from relevant literature into AI, and the AI ​​can automatically improve the accuracy of the annotations.

[0082] The vectorization unit can estimate the user's emotions and adjust the vectorization method based on the estimated emotions. For example, if the user is relaxed, the vectorization unit can perform detailed vectorization to improve accuracy. If the user is in a hurry, the vectorization unit can also perform simplified vectorization to prioritize processing speed. For example, if the user is excited, the vectorization unit will perform vectorization that emphasizes visually stimulating elements. In this way, by adjusting the vectorization method based on the user's emotions, a more appropriate vectorization can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input user emotion data into an AI, which can automatically estimate emotions and adjust the vectorization method.

[0083] The vectorization unit can adjust the level of detail in the vectorization process based on the date, time, and location where the image was taken. For example, if the image was taken at a specific event, the vectorization unit will perform detailed vectorization related to that event. If the image was taken during a trip, the vectorization unit can also perform vectorization that includes information about the travel destination. For example, if the image is a snapshot of everyday life, the vectorization unit will perform simple vectorization. By adjusting the level of detail in the vectorization process based on the date, time, and location where the image was taken, a more appropriate vectorization can be provided. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input data on the date, time, and location where the image was taken into the AI, which can then automatically adjust the level of detail in the vectorization.

[0084] The vectorization unit can apply different vectorization algorithms depending on the image category during the vectorization process. For example, for landscape photographs, the vectorization unit can apply a vectorization algorithm that emphasizes natural elements. For portraits, the vectorization unit can also perform vectorization of individual people using face recognition technology. For example, for food photographs, the vectorization unit can perform vectorization of the dish name and ingredients. By applying different vectorization algorithms depending on the image category, more appropriate vectorization can be provided. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input image category data into AI, and the AI ​​can automatically apply a vectorization algorithm.

[0085] The vectorization unit can estimate the user's emotions and determine vectorization priorities based on the estimated emotions. For example, if the user is relaxed, the vectorization unit may prioritize detailed vectorization. If the user is in a hurry, the vectorization unit may also prioritize simplified vectorization. For example, if the user is excited, the vectorization unit may prioritize vectorization that emphasizes visually stimulating elements. This allows for more appropriate vectorization by determining vectorization priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input user emotion data into an AI, which can automatically estimate emotions and determine vectorization priorities.

[0086] The vectorization unit can perform vectorization while considering the attribute information of the image's photographer. For example, the vectorization unit can perform vectorization that includes technical details for images taken by professional photographers. For images taken by amateurs, the vectorization unit can also perform vectorization that is simple and easy to understand. For example, the vectorization unit can perform vectorization that reflects the child's perspective for images taken by children. By considering the attribute information of the image's photographer during vectorization, a more appropriate vectorization can be provided. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input the attribute information of the image's photographer into AI, and the AI ​​can automatically perform vectorization.

[0087] The vectorization unit can improve the accuracy of vectorization by referring to related literature for the image during the vectorization process. For example, the vectorization unit can obtain the historical background of buildings in the image from related literature and reflect it in the vectorization. The vectorization unit can also obtain the types of plants in the image from related literature and reflect them in the vectorization. For example, the vectorization unit can obtain background information of people in the image from related literature and reflect it in the vectorization. This allows the accuracy of vectorization to be improved by referring to related literature for the image. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input data from related literature into AI, and the AI ​​can automatically improve the accuracy of vectorization.

[0088] The text generation unit can estimate the user's emotions and adjust the textual expression based on the estimated emotions. For example, if the user is sad, the text generation unit can use positive expressions that alleviate those emotions. If the user is happy, the text generation unit can also use expressions that emphasize that emotion. For example, if the user is excited, the text generation unit can use expressions that reflect that excitement. By adjusting the textual expression based on the user's emotions, a more appropriate text can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generative AI, but is not limited to these examples. Some or all of the above processing in the text generation unit is performed using the generative AI. For example, the text generation unit can input user emotion data into the generative AI, which can automatically estimate the emotions and adjust the textual expression.

[0089] The text conversion unit can adjust the level of detail in the text conversion based on the importance of the image. For example, the text conversion unit can perform detailed text conversion on images of important events, while performing concise text conversion on images of everyday scenes. For example, the text conversion unit can perform detailed text conversion related to a specific theme on images related to that theme. By adjusting the level of detail in the text conversion based on the importance of the image, it is possible to provide more appropriate text conversion. Some or all of the above processing in the text conversion unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the text conversion unit can input image importance data into a generation AI, which can then automatically adjust the level of detail in the text conversion.

[0090] The text conversion unit can apply different text conversion algorithms depending on the image category during the text conversion process. For example, the text conversion unit can apply a text conversion algorithm that emphasizes natural elements to landscape photographs. For portrait photographs, the text conversion unit can also perform detailed text conversion about individual people. For example, the text conversion unit can convert food photographs into text about the names of dishes and ingredients. By applying different text conversion algorithms depending on the image category, more appropriate text conversion can be provided. Some or all of the above processing in the text conversion unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the text conversion unit can input image category data into a generative AI, and the generative AI can automatically apply a text conversion algorithm.

[0091] The text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is in a hurry, the text generation unit will produce a short, concise text. If the user is relaxed, the text generation unit can produce a longer text that includes detailed explanations. For example, if the user is excited, the text generation unit will produce text that includes visually stimulating expressions. By adjusting the length of the text based on the user's emotions, a more appropriate text can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the text generation unit is performed using generative AI. For example, the text generation unit can input user emotion data into the generative AI, which can automatically estimate the emotions and adjust the length of the text.

[0092] The text conversion unit can determine the priority of text conversion based on the date and time the image was taken. For example, if the image was taken at a specific event, the text conversion unit will prioritize text related to that event. If the image was taken during a trip, the text conversion unit may also prioritize text containing information about the travel destination. For example, if the image is a snapshot of everyday life, the text conversion unit will prioritize concise text. This allows for more appropriate text conversion by determining the priority of text conversion based on the date and time the image was taken. Some or all of the above processing in the text conversion unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the text conversion unit can input the image's date and time data into a generation AI, which can then automatically determine the priority of text conversion.

[0093] The text conversion unit can adjust the order of text conversion based on the relevance of the images. For example, if an image is related to a specific theme, the text conversion unit will prioritize text conversion related to that theme. The text conversion unit can also perform text conversion consecutively if the images were taken at the same event. For example, if images belong to different categories, the text conversion unit will adjust the order of text conversion for each category. This allows for more appropriate text conversion by adjusting the order of text conversion based on the relevance of the images. Some or all of the above processing in the text conversion unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the text conversion unit can input image relevance data into a generative AI, which can then automatically adjust the order of text conversion.

[0094] The sorting unit can estimate the user's emotions and adjust the sorting method based on the estimated emotions. For example, if the user is sad, the sorting unit can provide a sorting method that alleviates those emotions. If the user is happy, the sorting unit can also provide a sorting method that emphasizes those emotions. For example, if the user is excited, the sorting unit can provide a sorting method that reflects that excitement. By adjusting the sorting method based on the user's emotions, a more appropriate sorting can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the sorting unit may be performed using AI or not. For example, the sorting unit can input user emotion data into an AI, which can then automatically estimate the emotions and adjust the sorting method.

[0095] The sorting unit can select the optimal sorting method by referring to the user's past access history during sorting. For example, the sorting unit may prioritize displaying images that the user has frequently accessed in the past. If the sorting unit has viewed many images of a particular category in the past, it can also prioritize sorting images of that category. For example, the sorting unit may predict and sort images that the user will access at a specific time based on their past access history. This allows for more appropriate sorting by selecting the optimal sorting method by referring to the user's past access history. Some or all of the above processing in the sorting unit may be performed using AI or not. For example, the sorting unit can input the user's past access history data into AI, which can then automatically select the optimal sorting method.

[0096] The sorting unit can estimate the user's emotions and determine sorting priorities based on the estimated emotions. For example, if the user is sad, the sorting unit will prioritize sorting images that alleviate those emotions. If the user is happy, the sorting unit can also prioritize sorting images that emphasize that emotion. For example, if the user is excited, the sorting unit will prioritize sorting images that reflect that excitement. This allows for more appropriate sorting by determining sorting priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the sorting unit may be performed using AI or not. For example, the sorting unit can input user emotion data into an AI, which can then automatically estimate the emotions and determine sorting priorities.

[0097] The organization unit can select the optimal organization method while considering the user's device information. For example, if the user is using a smartphone, the organization unit provides an organization method that matches the screen size. If the user is using a tablet, the organization unit can also provide an organization method optimized for a larger screen. For example, if the user is using a desktop, the organization unit provides an organization method that includes detailed information. This allows for more appropriate organization by selecting the optimal organization method while considering the user's device information. Some or all of the above processing in the organization unit may be performed using AI or not. For example, the organization unit can input the user's device information into the AI, and the AI ​​can automatically select the optimal organization method.

[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 annotation unit can estimate the user's emotions and adjust the annotation content based on the estimated emotions. For example, if the user is sad, positive annotations that alleviate the emotion can be added. If the user is happy, annotations that emphasize that emotion can also be added. Furthermore, if the user is excited, annotations that reflect that excitement can be added. In this way, by adjusting the annotation content based on the user's emotions, more appropriate annotations can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input user emotion data into an AI, which can then automatically estimate the emotion and adjust the annotation content.

[0100] The vectorization unit can estimate the user's emotions and adjust the vectorization method based on the estimated emotions. For example, if the user is relaxed, detailed vectorization can be performed to improve accuracy. If the user is in a hurry, simplified vectorization can be performed to prioritize processing speed. Furthermore, if the user is excited, vectorization can be performed to emphasize visually stimulating elements. In this way, by adjusting the vectorization method based on the user's emotions, more appropriate vectorization can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can input user emotion data into an AI, which can automatically estimate emotions and adjust the vectorization method.

[0101] The text generation unit can estimate the user's emotions and adjust the textual expression based on the estimated emotions. For example, if the user is sad, positive expressions that alleviate the emotion are used. If the user is happy, expressions that emphasize that emotion may be used. Furthermore, if the user is excited, expressions that reflect that excitement are used. In this way, by adjusting the textual expression based on the user's emotions, more appropriate text can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generative AI, but is not limited to these examples. Some or all of the above processing in the text generation unit is performed using the generative AI. For example, the text generation unit can input user emotion data into the generative AI, which can automatically estimate the emotions and adjust the textual expression.

[0102] The sorting unit can estimate the user's emotions and adjust the sorting method based on the estimated emotions. For example, if the user is sad, it can provide a sorting method that alleviates those emotions. If the user is happy, it can also provide a sorting method that emphasizes those emotions. Furthermore, if the user is excited, it can provide a sorting method that reflects that excitement. In this way, by adjusting the sorting method based on the user's emotions, a more appropriate sorting can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the sorting unit may be performed using AI or not. For example, the sorting unit can input user emotion data into an AI, which can automatically estimate the emotions and adjust the sorting method.

[0103] The sorting unit can estimate the user's emotions and determine sorting priorities based on the estimated emotions. For example, if the user is sad, images that alleviate those emotions may be prioritized. If the user is happy, images that emphasize that emotion may be prioritized. Furthermore, if the user is excited, images that reflect that excitement may be prioritized. This allows for more appropriate sorting by determining sorting priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the sorting unit may be performed using AI or not. For example, the sorting unit can input user emotion data into an AI, which can then automatically estimate the emotions and determine sorting priorities.

[0104] The annotation unit can adjust the level of detail of annotations based on the date, time, and location where the image was taken. For example, if an image was taken at a specific event, detailed annotations related to that event can be added. If an image was taken during a trip, annotations including information about the travel destination can also be added. Furthermore, if the image is a snapshot of everyday life, concise annotations can be added. By adjusting the level of detail of annotations based on the date, time, and location where the image was taken, more appropriate annotations can be provided. Some or all of the above processing in the annotation unit may be performed using AI or not. For example, the annotation unit can input data on the date, time, and location where the image was taken into the AI, and the AI ​​can automatically adjust the level of detail of the annotations.

[0105] The vectorization unit can adjust the level of detail in the vectorization process based on the date, time, and location where the image was taken. For example, if the image was taken at a specific event, it can perform detailed vectorization related to that event. If the image was taken during a trip, it can also perform vectorization that includes information about the travel destination. Furthermore, if the image is a snapshot of everyday life, it can perform simplified vectorization. By adjusting the level of detail in the vectorization process based on the date, time, and location where the image was taken, it is possible to provide more appropriate vectorization. Some or all of the above processing in the vectorization unit may be performed using AI, or it may be performed without AI. For example, the vectorization unit can input data on the date, time, and location where the image was taken into the AI, and the AI ​​can automatically adjust the level of detail in the vectorization.

[0106] The text conversion unit can adjust the level of detail in the text conversion based on the importance of the image. For example, images of important events can be converted to detailed text, while images of everyday scenes can be converted to concise text. Furthermore, images related to a specific theme can be converted to detailed text related to that theme. By adjusting the level of detail in the text conversion based on the importance of the image, more appropriate text conversion can be provided. Some or all of the above processing in the text conversion unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the text conversion unit can input image importance data into a generation AI, which can then automatically adjust the level of detail in the text conversion.

[0107] The sorting unit can select the optimal sorting method by referring to the user's past access history during sorting. For example, it can prioritize displaying images that the user has frequently accessed in the past. If the user has viewed many images of a particular category in the past, it can also prioritize sorting images of that category. Furthermore, it can predict and sort images that the user will access at specific times based on their past access history. By selecting the optimal sorting method by referring to the user's past access history, it can provide a more appropriate sorting service. Some or all of the above processing in the sorting unit may be performed using AI, or not. For example, the sorting unit can input the user's past access history data into AI, which can then automatically select the optimal sorting method.

[0108] The organization unit can select the optimal organization method while considering the user's device information. For example, if the user is using a smartphone, it can provide an organization method that matches the screen size. If the user is using a tablet, it can also provide an organization method optimized for a larger screen. Furthermore, if the user is using a desktop, it can provide an organization method that includes detailed information. By selecting the optimal organization method while considering the user's device information, a more appropriate organization can be provided. Some or all of the above processing in the organization unit may be performed using AI or not. For example, the organization unit can input the user's device information into the AI, and the AI ​​can automatically select the optimal organization method.

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

[0110] Step 1: The annotation section performs annotation on the image data. Specifically, it labels and tags the image data to make the content of the image easier to identify. It is also possible to label objects and people within the image, or tag specific areas. Furthermore, it is possible to add descriptive text to the image data, adding text that explains the scene or situation within the image. Step 2: The vectorization unit processes the image data annotated by the annotation unit as vector data. Specifically, it represents the image as a vector (a set of numbers), making it easier for the AI ​​to extract and compare image features. Representing image features as numerical data enables efficient searching and recognition. For example, features such as color, shape, and pattern within an image can be extracted as numerical data, and the similarity can be calculated by comparing the feature vectors. Step 3: The text conversion unit converts the image data, which has been processed as vector data by the vectorization unit, into natural language text. Specifically, it uses generative AI to rediscover the story and emotions embedded in the image as text. For example, it can generate text that describes the scene or situation in the image, or estimate emotions based on the facial expressions and actions of people in the image and express them as text. Step 4: The organization unit organizes the data converted into text by the text conversion unit in a format accessible to the user. Specifically, it classifies the text data into categories so that users can easily search for it. It can also organize the text data chronologically or customize the data according to the user's preferences. For example, it is possible to organize the data based on keywords specified by the user.

[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 annotation unit, vectorization unit, text conversion unit, and organization unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the annotation unit is implemented by the control unit 46A of the smart device 14 and performs labeling and tagging of image data. The vectorization unit is implemented by the specific processing unit 290 of the data processing device 12 and processes image data as vector data. The text conversion unit is implemented by the specific processing unit 290 of the data processing device 12 and uses generation AI to convert the story and emotions embedded in the image into text. The organization unit is implemented by the control unit 46A of the smart device 14 and organizes the text data in a format that can be accessed by the user. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed 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 annotation unit, vectorization unit, text conversion unit, and organization unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the annotation unit is implemented by the control unit 46A of the smart glasses 214 and performs labeling and tagging of image data. The vectorization unit is implemented by the specific processing unit 290 of the data processing unit 12 and processes image data as vector data. The text conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generation AI to convert the story and emotions embedded in the image into text. The organization unit is implemented by the control unit 46A of the smart glasses 214 and organizes the text data in a format that can be accessed by the user. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed 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 annotation unit, vectorization unit, text conversion unit, and organization unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the annotation unit is implemented by the control unit 46A of the headset terminal 314 and performs labeling and tagging of image data. The vectorization unit is implemented by the specific processing unit 290 of the data processing unit 12 and processes image data as vector data. The text conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generation AI to convert the story and emotions embedded in the image into text. The organization unit is implemented by the control unit 46A of the headset terminal 314 and organizes the text data in a format that can be accessed by the user. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed 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 annotation unit, vectorization unit, text conversion unit, and organization unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the annotation unit is implemented by the control unit 46A of the robot 414 and performs labeling and tagging of image data. The vectorization unit is implemented by the specific processing unit 290 of the data processing unit 12 and processes image data as vector data. The text conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses generation AI to convert the story and emotions embedded in the image into text. The organization unit is implemented by the control unit 46A of the robot 414 and organizes the text data in a form that can be accessed by the user. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed 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) An annotation unit that performs annotation of image data, A vectorization unit processes the image data annotated by the annotation unit as vector data, A text conversion unit converts image data processed as vector data by the vectorization unit into text in natural language, The system includes a text conversion unit that organizes the text data converted by the text conversion unit into a format accessible to the user. A system characterized by the following features. (Note 2) The annotation unit described above is: Annotating image data helps support the training of high-precision AI models. The system described in Appendix 1, characterized by the features described herein. (Note 3) The vectorization unit, Representing images as vectors makes it easier for AI to extract and compare image features. The system described in Appendix 1, characterized by the features described herein. (Note 4) The text conversion unit, Generative AI helps rediscover the stories and emotions embedded in photographs as text. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned editing unit, Organize text data into a format that is easily accessible to users. The system described in Appendix 1, characterized by the features described herein. (Note 6) The vectorization unit, By converting to vector data, similarity can be compared through numerical calculations, allowing for quick searching of images with similar features from a large dataset. The system described in Appendix 1, characterized by the features described herein. (Note 7) The vectorization unit, By vectorizing multiple images, the data size is reduced compared to the original images, making storage more economical. The system described in Appendix 1, characterized by the features described herein. (Note 8) The vectorization unit, By using features extracted as vectors, visual similarities can be captured more precisely. The system described in Appendix 1, characterized by the features described herein. (Note 9) The annotation unit described above is: It estimates the user's emotions and adjusts the annotation content based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The annotation unit described above is: During annotation, adjust the level of detail based on the date, time, and location where the image was taken. The system described in Appendix 1, characterized by the features described herein. (Note 11) The annotation unit described above is: During annotation, different annotation algorithms are applied depending on the image category. The system described in Appendix 1, characterized by the features described herein. (Note 12) The annotation unit described above is: The system estimates the user's emotions and determines annotation priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The annotation unit described above is: When annotating images, the attribute information of the image's photographer is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 14) The annotation unit described above is: During annotation, referencing relevant literature for images improves the accuracy of annotation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The vectorization unit, It estimates the user's emotions and adjusts the vectorization method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The vectorization unit, During vectorization, adjust the level of detail based on the date and location where the image was taken. The system described in Appendix 1, characterized by the features described herein. (Note 17) The vectorization unit, When vectorizing, different vectorization algorithms are applied depending on the image category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The vectorization unit, The system estimates the user's emotions and determines the vectorization priority based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The vectorization unit, When vectorizing images, the vectorization process takes into account the attributes of the image's photographer. The system described in Appendix 1, characterized by the features described herein. (Note 20) The vectorization unit, During vectorization, we refer to related literature for the image to improve the accuracy of the vectorization. The system described in Appendix 1, characterized by the features described herein. (Note 21) The text conversion unit, It estimates the user's emotions and adjusts the textual expression based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The text conversion unit, When converting to text, adjust the level of detail in the text based on the importance of the image. The system described in Appendix 1, characterized by the features described herein. (Note 23) The text conversion unit, When converting to text, different text conversion algorithms are applied depending on the image category. The system described in Appendix 1, characterized by the features described herein. (Note 24) The text conversion unit, It estimates the user's emotions and adjusts the length of the text based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The text conversion unit, When converting to text, the priority of text conversion is determined based on the date and time the image was taken. The system described in Appendix 1, characterized by the features described herein. (Note 26) The text conversion unit, When converting to text, adjust the order of text based on the relevance of the images. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned editing unit, It estimates the user's emotions and adjusts the sorting method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned editing unit, During the cleanup process, the system selects the optimal cleanup method by referring to the user's past access history. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned editing unit, It estimates the user's emotions and determines the priority of sorting based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned editing unit, When organizing, the optimal organization method is selected considering the user's device information. 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. An annotation unit that performs annotation of image data, A vectorization unit processes the image data annotated by the annotation unit as vector data, A text conversion unit converts image data processed as vector data by the vectorization unit into text in natural language, The system includes a text conversion unit that organizes the text data converted by the text conversion unit into a format accessible to the user. A system characterized by the following features.

2. The annotation unit described above is: Annotating image data helps support the training of high-precision AI models. The system according to feature 1.

3. The vectorization unit, Representing images as vectors makes it easier for AI to extract and compare image features. The system according to feature 1.

4. The text conversion unit, Generative AI allows us to rediscover the stories and emotions embedded in photographs as text. The system according to feature 1.

5. The aforementioned editing unit, Organize text data into a format that is easily accessible to users. The system according to feature 1.

6. The vectorization unit, By converting to vector data, similarity can be compared through numerical calculations, allowing for quick searching of images with similar features from a large dataset. The system according to feature 1.

7. The vectorization unit, By vectorizing multiple images, the data size is reduced compared to the original images, making storage more economical. The system according to feature 1.

8. The vectorization unit, By using features extracted as vectors, visual similarities can be captured more precisely. The system according to feature 1.

Images