system

Abstract

We provide the system. [Solution] A means of receiving and storing digital image data, A means for analyzing the aforementioned digital image data and utilizing a generative model to convert its content into natural language, A means for assigning labels related to place, emotion, and event based on the aforementioned natural language and storing them in a database, A means for searching the database in response to a user's search query and outputting the corresponding digital image data, A system that includes this.

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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, a huge amount of photos taken by individuals with digital devices have been stored, but many of them are buried as mere data. It is required to efficiently organize and search for photos as valuable memories so that users can easily re-experience them. Therefore, it is necessary to break away from the management of mere photo data and provide an environment that enhances the value of photos as memories.

Means for Solving the Problems

[0005] This invention comprises means for receiving digital image data and storing it in cloud storage, and means for analyzing and converting the image data into text using a generative model, assigning labels related to location, emotion, and event, and storing it in a database. Furthermore, it constructs a system that searches the database for relevant digital image data based on a search query entered by the user and provides it to the user along with related information. This allows users to rediscover a vast number of photographs as valuable memories and access them easily.

[0006] "Digital image data" refers to image information stored in digital format, specifically photographic data taken or acquired by a user.

[0007] A "generative model" is a model based on AI technology that analyzes digital image data and generates meaningful natural language text from it.

[0008] A "label" is a tag or symbol that indicates specific attributes or characteristics of a digital image or its content, and is information added to facilitate organization and searching.

[0009] A "database" is a computer system that systematically stores and manages digital image data and associated information such as labels, enabling efficient searching.

[0010] A "user" refers to an individual or group that uses a digital image data system to upload their own photographic data or access specific memories.

[0011] A "search query" refers to keywords or phrases that a user enters to retrieve specific information from a database, and represents the search criteria. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[0033] This invention is configured as a system for organizing and utilizing digital image data owned by users as valuable memories. Users can upload photos from their devices, and the server receives them. The received image data is securely stored in cloud storage.

[0034] The server then utilizes generative models to analyze the stored image data. These generative models convert digital images into natural language text, extracting key elements such as location, emotion, and events from the image content. This allows the context associated with the photographs to be assigned as labels and stored in a database.

[0035] Users can search from their devices using specific themes or keywords to recall their memories. The server quickly searches the database based on the user's search query and provides the user with relevant images and related information. This allows users to easily access their intended memories from a vast collection of photographs.

[0036] For example, if a user searches for "birthday party," the server will display all images with the relevant label. It is also possible to search based on emotions such as "fun," allowing users to easily relive photos and moments associated with that emotion. In this form, the invention transforms photographs from mere data into valuable memories, providing users with an emotionally rich experience.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The user uses their device to select their digital images and clicks the upload button. The device then sends the selected image data to the server.

[0040] Step 2:

[0041] The server stores the received digital image data in temporary storage. Furthermore, the data is moved to cloud storage in preparation for long-term storage.

[0042] Step 3:

[0043] The server invokes a generative model in the cloud and requests analysis of the stored image data. It generates a request for analysis and transfers the digital images to the model.

[0044] Step 4:

[0045] The generative model analyzes image data and generates natural language text based on that analysis. This text includes information about the image's location, people, objects, background, and emotions or events.

[0046] Step 5:

[0047] The server receives the generated text data and assigns labels based on its content. These labels include tags related to location, emotions, events, etc.

[0048] Step 6:

[0049] The server stores labeled information in a database and organizes it systematically so that users can search for it later.

[0050] Step 7:

[0051] The user uses the device's interface to enter a specific theme or keyword and perform a search.

[0052] Step 8:

[0053] The server searches the database based on the user's search query. It quickly identifies and organizes image data with the corresponding label.

[0054] Step 9:

[0055] The server sends search results to the terminal and presents the user with digital image data and related information that matches the criteria specified by the user.

[0056] Step 10:

[0057] Users can relive their memories by viewing the displayed search results and checking the images and accompanying information.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] A challenge exists in efficiently organizing and retrieving important memories and information buried within a vast amount of digital image data. Existing methods make it difficult to understand and tag image content in detail, preventing users from quickly obtaining the information they intend.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for receiving image data and storing it in a remote storage device, means for analyzing the image data and utilizing a generative model to convert its contents into language data, and means for assigning location information, emotion information, and event-related tags based on the language data and storing them in the storage device. This makes it possible for users to easily search for and retrieve images based on specific contexts or emotions from a vast amount of image data.

[0063] "Image data" refers to files that represent visual information acquired by a user in a digital format and can be processed by a computer.

[0064] "Remote storage" refers to a system or device for storing data in storage located at a physically distant location.

[0065] A "generative model" refers to an algorithm based on artificial intelligence technology that analyzes input data and generates a specific output.

[0066] "Linguistic data" refers to data that represents images and other information in natural language.

[0067] "Location information" refers to geographical information that indicates where specific data or events occurred.

[0068] "Emotional information" refers to information about the emotional state and nuances associated with data or events.

[0069] "Event" refers to the occurrences or activities that take place within the image data.

[0070] A "tag" refers to an identifier or label assigned to data to make it easier to classify and search for.

[0071] A "storage device" refers to hardware or software that stores data and allows that data to be retrieved as needed.

[0072] A "search request" refers to an instruction or query that a user sends to a system in order to retrieve specific information.

[0073] This invention is a system that makes it easier for users to organize and utilize large amounts of digital image data they possess, and its details are described below. First, users can upload their digital images using a terminal. The server stores the received image data in a physically distant, remote data storage. This storage can utilize a cloud-based storage service, and specifically, a general-purpose data storage platform is expected to be used.

[0074] The stored image data is analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms to convert the image content into natural language and extract location information, sentiment information, and event-related tags from it. For example, software incorporating open-source machine learning libraries or commercial APIs may be used.

[0075] This generates detailed linguistic data about the image data, which is then assigned as tags. The data, along with the generated tags, is managed in a storage device, allowing users to quickly find the desired image in subsequent searches.

[0076] Users can enter search queries from their terminal to invoke specific contexts. An example of a prompt might be, "Show me fun travel moments." Based on this search query, the server quickly extracts the relevant image data from the database and provides it to the user.

[0077] For example, when a user enters the search query "birthday party," the server selects images tagged with "birthday" and related emotions and displays them on the user's device. This system allows users to easily rediscover and experience richer memories from multiple image data.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user accesses the system interface using their device, selects a digital image file, and begins uploading. The input is image data stored on the user's device, and the output is the transmission of image data to the server. Specifically, when the user clicks the upload button, the device sends the image data to the server via an HTTP POST request.

[0081] Step 2:

[0082] The server receives image data sent by the user and verifies its format. The input is the image data sent by the user, and the output is the verified image data. The server verifies that the received image data is in the correct format and size, and if there are no problems, it proceeds to the next step.

[0083] Step 3:

[0084] The server saves verified image data to remote storage. The input is verified image data, and the output is data stored in a data storage system such as cloud storage. Specifically, the server uses an API to save the image data to the cloud and obtain a unique identifier.

[0085] Step 4:

[0086] The server sends the stored image data to a generating AI model and begins analysis. The input is image data retrieved from cloud storage, and the output is generated text data. The server feeds the image data into the generating AI model, which generates linguistic data based on it and extracts location information, sentiment information, and event-related tags.

[0087] Step 5:

[0088] The server organizes and stores data in its storage device based on the generated language data and tag information. The input is the parsed language data and tag information, and the output is the information recorded in the database. Specifically, the server uses a database management system to efficiently store the tagged information.

[0089] Step 6:

[0090] The user enters a search query from their device using specific context and keywords. The input is a text-based prompt from the user, and the output is a list of related images obtained as search results. The user submits the query by entering keywords in the search box and clicking the search button.

[0091] Step 7:

[0092] The server receives search queries from users and searches the database. The input is the user's search query, and the output is the relevant image data and its tag information. Specifically, the server quickly extracts the relevant image data based on the tag information in the database and provides it to the user.

[0093] Step 8:

[0094] The user views the images and information provided as search results on their device. The input is the search results sent from the server, and the output is the displayed images and related information. The user can scroll through the displayed images and click to view more detailed information.

[0095] This allows users to effectively search for information based on specific emotions or themes from a vast amount of image data and easily access images related to memories.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] In recent years, the amount of digital image data has increased rapidly, making it difficult for users to effectively manage their memories and access them quickly when needed. Furthermore, conventional systems lack the means to efficiently organize images and easily search based on specific emotions or events, highlighting the need for improved user experience.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for receiving and storing digital image data, means for analyzing the digital image data and utilizing a generative model to convert its content into natural language, and means for outputting the relevant digital image data to a display device in response to a search query from the user. This enables the user to emotionally manage their memories and to quickly and intuitively retrieve related images and information.

[0101] "Digital image data" refers to a collection of visual information that is stored and managed electronically.

[0102] A "generative model" is a system equipped with a learning algorithm that analyzes the content of digital images and converts it into natural language.

[0103] "Natural language" refers to information expressed in the form of language or words that humans use on a daily basis.

[0104] A "label" is a tag or identifier associated with digital image data, and is information assigned to represent its content or attributes.

[0105] A "database" is a management system for storing a collection of data that is systematically organized according to a specific purpose.

[0106] A "search query" is a question or command that a user enters into a database to retrieve information.

[0107] A "display device" is a device used to visually represent information generated by computers or electronic devices.

[0108] "Voice instructions" are commands or requests that are communicated in the form of sound, which a machine interprets and responds to.

[0109] To implement this invention, a system for processing digital image data is required. The central element of this system is a server, which receives and stores digital image data from users. The stored data is securely stored in cloud storage. The server also includes a generative AI model for analyzing the image data, converting digital images into natural language text and extracting key elements related to location, emotions, and events. As a result, the image data is labeled and organized and stored in a database.

[0110] Users can issue voice commands through physical devices in their daily lives. For example, a home assistant robot can function as part of this system, presenting relevant images according to the user's requests. In this case, the robot processes the voice commands received from the user with the help of a generative AI model, searches for the corresponding data, and displays it on an output device.

[0111] The specific hardware used includes home robots, digital displays, and cameras. The software consists of an image processing system using PIL (Python Imaging Library) and a proprietary generative AI model. These are responsible for analyzing images, generating necessary text information, and storing it in a database.

[0112] As a concrete example, when a user gives a voice command to a robot saying, "Show me the fun moments from last summer's vacation," the robot can analyze all the stored images, find images that match the specified criteria, and display them on a screen or projector. In this process, the generative AI model processes prompts such as, "Show me the photos taken on last summer's trip. Please highlight the fun moments in particular." This makes it easy for the user to relive their intended memories from a vast amount of digital images.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server receives digital image data from the user's device. The received image data is securely stored in cloud storage. In this step, the input is the image file sent by the user via their device, and the output is the image data stored in cloud storage. No data processing is performed; the data is saved in its original format.

[0116] Step 2:

[0117] The server retrieves image data stored in cloud storage and performs analysis using a generative AI model. The input is stored digital image data, and the output is natural language text as the analysis result. The data calculation involves analyzing the content of the image data and extracting important elements (location, emotion, events, etc.). This model uses a neural network to convert the image into a multidimensional vector and analyze its features.

[0118] Step 3:

[0119] The server labels image data based on the generated natural language text and then records those labels in a database. The input is the natural language text and image data obtained in step 2, and the output is the labeled database entries. Data processing involves organizing the information extracted from the text and assigning labels according to location, emotion, and event.

[0120] Step 4:

[0121] The user provides voice commands to a physical device, which are sent to the server as search queries. The input for this step is the user's voice commands, which are generated as prompts. These generated prompts are then sent to the server.

[0122] Step 5:

[0123] The server searches the database based on the received prompt and extracts digital image data that matches the criteria. The input is the search query in the prompt, and the output is the matching image data and its label information. The data calculation involves parsing the received string and comparing it with the entries in the database. As a result, the relevant image data is identified.

[0124] Step 6:

[0125] The server outputs the selected image data to the terminal and presents it to the user via the display device. The input is the matching image data extracted in step 5, and the output is visual information in a visually verifiable format. In this step, the image is displayed using a display or projector. The user can view the presented image and re-experience the information as needed.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] This invention is a system for efficiently organizing users' digital image data and providing search results based on emotions. Users upload photos they have taken to a server via their terminal. The server stores the image data in cloud storage and then analyzes the photos using a generative model. In the analysis process, locations, people, objects, backgrounds, and emotions or events are extracted from the image content, and natural language text is generated.

[0128] Based on the transcribed data, the server assigns labels to the photos and stores them in a database. This enables quick searches based on specific criteria. The system also incorporates an emotion engine that recognizes the user's emotions, analyzing the user's past behavior and search history to infer their emotional state. Based on this emotional state, the search results are adjusted, prioritizing photos that are more relevant to the user.

[0129] For example, if a user searches for "fun memories at the beach," the server will present beach photos associated with fun based on past emotional data. The emotion engine selects the most suitable photos for the user's current mood, helping to recreate emotionally rich memories. This also makes it easier for users to rediscover emotionally resonant moments, rather than simply searching for images.

[0130] In this form, the invention is specifically implemented as a means to reconstruct photographs as valuable memories in a way that resonates with the user's emotions, to facilitate access to those memories, and to enrich individual experiences.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user uses their device to select the digital images they want to upload. After selection, the user presses the upload button, and the device sends the image data to the server.

[0134] Step 2:

[0135] The server saves the received digital image data to temporary storage. The server then migrates the data to cloud storage in preparation for long-term storage.

[0136] Step 3:

[0137] The server invokes a generative model in the cloud and requests analysis of the stored image data. The digital image is sent to the generative model to begin content analysis.

[0138] Step 4:

[0139] The generative model analyzes image data to identify people, objects, backgrounds, locations, emotions, and events, and generates natural language text based on this information. This information provides context and meaning to the photograph.

[0140] Step 5:

[0141] The server receives the generated text data and assigns labels such as location, emotion, and event based on it. The labeled data is stored in a database and organized to enable efficient searching.

[0142] Step 6:

[0143] The user enters a specific theme or keyword through their device and performs a search.

[0144] Step 7:

[0145] The server receives the user's search query and searches the database for image data with relevant labels. A sentiment engine is used in the search, which analyzes the user's past behavior and search history to infer their current emotional state.

[0146] Step 8:

[0147] The emotion engine adjusts search results, prioritizing and presenting images that are most relevant to the user's emotional state.

[0148] Step 9:

[0149] The server sends the selected search results to the user's device. The user can view the presented images and related information on their device, and emotionally re-experience memories through highly relevant photographs.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] The vast accumulation of digital image data makes it difficult to quickly and efficiently search for images related to specific emotions or events. Furthermore, technologies that present highly relevant images considering the user's current emotional state are still insufficient. To address this challenge, flexible and rapid searching based on image content and user emotions is necessary.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes means for receiving image data from a terminal and storing it in a storage device, means for analyzing the received image data and utilizing generation technology to convert the information into text, and means for adjusting search results based on the analyzed sentiment information and providing the user with the most suitable image data. This makes it possible to quickly and efficiently search for images related to specific emotions or events and present highly relevant images according to the user's current emotional state.

[0155] "Image data" refers to visual information stored in digital format, and is generally generated by cameras or digital devices.

[0156] A "storage device" is a medium or device for electronically storing and holding information.

[0157] "Generative technology" refers to techniques for analyzing received data and converting it into a specified format. This technology may include machine learning models and natural language processing techniques.

[0158] An "information tag" is additional information used to identify and classify specific digital data, and is usually expressed as a text label.

[0159] A "recording medium" is a physical or electronic medium used to store information, and includes databases and cloud storage.

[0160] "User" refers to a person or entity that uses this system to search for or view image data.

[0161] "Emotional state" refers to a user's psychological or emotional condition at a given point in time, and is inferred from data analysis and the user's behavioral history.

[0162] "Search results" refer to a list or set of information provided based on a user's request, including digital data that matches specified criteria.

[0163] This invention is a system that efficiently organizes digital image data captured by users and provides them with highly relevant search results based on their emotions. Users upload image data to the system using a device such as a smartphone or personal computer. The device sends this image data to the server via the HTTP / HTTPS protocol. The server receives the image data and stores it in cloud storage such as Amazon S3.

[0164] The server is equipped with a generative AI model for analyzing image data. This model uses technologies such as Google® Cloud Vision API and Azure® Image Analysis to extract text information from images. The generated text information includes location, emotions, events, people, objects, background, etc. Based on this information, the server creates information tags and stores them in a database. The database can use relational databases such as MySQL® or PostgreSQL.

[0165] This system also features an emotion engine that analyzes the user's past behavior data and search history. This analysis infers the user's current emotional state and selects the most relevant images for the search query. Based on these optimized search results, the server provides the user with highly relevant image data.

[0166] For example, if a user searches for "happy memories at the beach," the system will prioritize displaying beach photos associated with past emotional data. This search process allows users to instantly rediscover emotionally resonant memories.

[0167] An example of a prompt statement is as follows: "Give the user a photo of a beach and describe the image search process to recreate related, enjoyable memories based on the user's emotions."

[0168] This system allows users to go beyond simple image searches and reconstruct meaningful experiences related to their own emotions.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] Users select digital image data from devices such as smartphones and personal computers and upload it to the system. The input is image data stored on the user's device, and the output is the image data sent from the device to the server. This process is carried out using the HTTP / HTTPS protocol and encrypted communication is used to ensure data security.

[0172] Step 2:

[0173] The server processes image data received from the terminal and temporarily stores it in internal storage. The input is uploaded image data, and the output is image data uploaded to a cloud storage service. This process uses storage management software to store data on a cloud platform such as Amazon S3.

[0174] Step 3:

[0175] The server retrieves image data from cloud storage and begins analyzing the images using a generative AI model. The input is image data stored in the cloud, and the output is text information generated by the analysis. This analysis uses the Google Cloud Vision API and Azure Image Analysis to identify objects and context within the image and extract them as text.

[0176] Step 4:

[0177] The server assigns information tags to photos based on the generated text information, corresponding to emotions and events. The input is text information extracted through image analysis, and the output is image data with tags assigned to it. The assigned tags are stored in a database such as MySQL or PostgreSQL to support subsequent search processing.

[0178] Step 5:

[0179] The server uses an emotion engine to analyze the user's past data and infer their current emotional state. The input is the user's past behavior data and search history, and the output is information about the user's emotional state. Based on this inference, the server generates prompt statements relevant to the user's search query and applies the search process.

[0180] Step 6:

[0181] When a user specifies search criteria, the server searches the database and collects relevant image data. The input consists of the user's search query and prompts based on their emotional state, while the output is the retrieved images. The server adjusts the search results to match the user's emotional state and displays them in an appropriate order.

[0182] Step 7:

[0183] The user's device displays search results received from the server on its interface. The input is image data provided by the server as search results, and the output is a visual display through the user interface. The user can view the displayed images and easily recall memories that evoke specific emotions.

[0184] (Application Example 2)

[0185] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0186] The sheer volume of digital image information presents a challenge: it's difficult for users to quickly revisit past memories based on specific emotions or scenes. Furthermore, there's a lack of readily available ways to easily present emotionally relevant memories within the home.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0188] In this invention, the server includes means for receiving and storing digital image information; means for analyzing the digital image information and utilizing a generative model to convert its content into natural language; means for assigning labels related to place, emotion, and event based on the natural language and storing them in a storage device; means for searching the storage device in response to a search request from a user and outputting the corresponding digital image information; and means for presenting the outputted digital image information on an external display device and displaying the image information selected based on the user's emotional state. This enables the user to quickly revisit past memories that fit their emotions within their home and obtain an emotionally rich memory experience.

[0189] "Digital image information" refers to visual data files recorded electronically that can be displayed and analyzed by computers and other electronic devices.

[0190] A "generative model" is an artificial intelligence algorithm that has the ability to learn patterns from data and generate new data, and is used for analyzing images and text.

[0191] A "storage device" is hardware or software used to store and manage data, and is responsible for holding digital information.

[0192] An "external display device" is hardware connected to a system to provide digital information to the user visually, and includes monitors and displays.

[0193] "User emotional state" refers to the emotional tendencies and feelings of individual users at a specific time, and is analyzed and inferred by the system.

[0194] A "label" is an information tag assigned to classify or identify data, and is used to describe the characteristics of images or text.

[0195] In the system that implements this application, the server plays a central role. Users upload captured digital images from their terminals to the server. To efficiently receive and store large amounts of image information, the server requires a high-speed network interface and large-capacity storage. The server also analyzes the uploaded digital image information using generative models such as TENSORFLOW®. This analysis identifies people, objects, and backgrounds from the images and converts the content into natural language. The converted text data is stored in a database such as MongoDB.

[0196] Furthermore, the server utilizes a Python sentiment analysis library as its sentiment engine to analyze the user's past behavior data and search history to infer their emotional state. This allows for the labeling of images with information about location, emotion, and event. This labeled data is then used to quickly output appropriate digital images based on the user's search query.

[0197] A robot connected to an external display device shows image information provided by a server in a way that is tailored to the user's emotional state. For example, in response to a user request to "show me happy memories of the sea," search results based on past digital image information are displayed. This prompt allows the user to easily revisit emotionally rich memories within the comfort of their own home.

[0198] Example prompt: "Show me some photos of your fun beach memories."

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The system uploads digital images taken by the user from their device to a server. The input consists of multiple digital images taken with the user's device, and the output is an image file stored on the server's storage device. Specifically, the device uploads the files via a high-speed network connection, and the server stores the received files in a large-capacity storage device.

[0202] Step 2:

[0203] The server analyzes received digital images using TensorFlow, a generative AI model. The input is a digital image stored on the server, and the output is natural language text describing the analyzed content. Specifically, it identifies people, objects, and backgrounds from the image and describes them in natural language text.

[0204] Step 3:

[0205] The server assigns labels related to location, sentiment, and events based on the generated natural language text. The input is natural language text, and the output is text data with the label information attached. Specifically, it uses a sentiment engine to analyze the text and automatically assign appropriate labels.

[0206] Step 4:

[0207] The server stores label information in a database such as MongoDB. The input is labeled text data, and the output is the information stored in the database. Specifically, the information is inserted into the database in an appropriate format to enable efficient query searching.

[0208] Step 5:

[0209] The user makes a search request via their terminal. The input is a prompt message containing the user's criteria, and the output is the search result for images that match the criteria. Specifically, when the user enters "Show me pictures of fun beach memories," the server searches the database to identify the relevant image data.

[0210] Step 6:

[0211] The server sends search results to an external display device and displays the most suitable image according to the user's emotional state. The input is the image data of the search results, and the output is the visual displayed on the external display device. Specifically, the selected image is displayed on the screen, allowing the user to access emotionally rich memories.

[0212] 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.

[0213] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0219] 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.

[0220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0222] 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.

[0223] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0224] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0225] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0226] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0228] This invention is configured as a system for organizing and utilizing digital image data owned by users as valuable memories. Users can upload photos from their devices, and the server receives them. The received image data is securely stored in cloud storage.

[0229] The server then utilizes generative models to analyze the stored image data. These generative models convert digital images into natural language text, extracting key elements such as location, emotion, and events from the image content. This allows the context associated with the photographs to be assigned as labels and stored in a database.

[0230] Users can search from their devices using specific themes or keywords to recall their memories. The server quickly searches the database based on the user's search query and provides the user with relevant images and related information. This allows users to easily access their intended memories from a vast collection of photographs.

[0231] For example, if a user searches for "birthday party," the server will display all images with the relevant label. It is also possible to search based on emotions such as "fun," allowing users to easily relive photos and moments associated with that emotion. In this form, the invention transforms photographs from mere data into valuable memories, providing users with an emotionally rich experience.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The user uses their device to select their digital images and clicks the upload button. The device then sends the selected image data to the server.

[0235] Step 2:

[0236] The server stores the received digital image data in temporary storage. Furthermore, the data is moved to cloud storage in preparation for long-term storage.

[0237] Step 3:

[0238] The server invokes a generative model in the cloud and requests analysis of the stored image data. It generates a request for analysis and transfers the digital images to the model.

[0239] Step 4:

[0240] The generative model analyzes image data and generates natural language text based on that analysis. This text includes information about the image's location, people, objects, background, and emotions or events.

[0241] Step 5:

[0242] The server receives the generated text data and assigns labels based on its content. These labels include tags related to location, emotions, events, etc.

[0243] Step 6:

[0244] The server stores labeled information in a database and organizes it systematically so that users can search for it later.

[0245] Step 7:

[0246] The user uses the device's interface to enter a specific theme or keyword and perform a search.

[0247] Step 8:

[0248] The server searches the database based on the user's search query. It quickly identifies and organizes image data with the corresponding label.

[0249] Step 9:

[0250] The server sends search results to the terminal and presents the user with digital image data and related information that matches the criteria specified by the user.

[0251] Step 10:

[0252] Users can relive their memories by viewing the displayed search results and checking the images and accompanying information.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] A challenge exists in efficiently organizing and retrieving important memories and information buried within a vast amount of digital image data. Existing methods make it difficult to understand and tag image content in detail, preventing users from quickly obtaining the information they intend.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes means for receiving image data and storing it in a remote storage device, means for analyzing the image data and utilizing a generative model to convert its contents into language data, and means for assigning location information, emotion information, and event-related tags based on the language data and storing them in the storage device. This makes it possible for users to easily search for and retrieve images based on specific contexts or emotions from a vast amount of image data.

[0258] "Image data" refers to files that represent visual information acquired by a user in a digital format and can be processed by a computer.

[0259] "Remote storage" refers to a system or device for storing data in storage located at a physically distant location.

[0260] A "generative model" refers to an algorithm based on artificial intelligence technology that analyzes input data and generates a specific output.

[0261] "Linguistic data" refers to data that represents images and other information in natural language.

[0262] "Location information" refers to geographical information that indicates where specific data or events occurred.

[0263] "Emotional information" refers to information about the emotional state and nuances associated with data or events.

[0264] "Event" refers to the occurrences or activities that take place within the image data.

[0265] A "tag" refers to an identifier or label assigned to data to make it easier to classify and search for.

[0266] A "storage device" refers to hardware or software that stores data and allows that data to be retrieved as needed.

[0267] A "search request" refers to an instruction or query that a user sends to a system in order to retrieve specific information.

[0268] This invention is a system that makes it easier for users to organize and utilize large amounts of digital image data they possess, and its details are described below. First, users can upload their digital images using a terminal. The server stores the received image data in a physically distant, remote data storage. This storage can utilize a cloud-based storage service, and specifically, a general-purpose data storage platform is expected to be used.

[0269] The stored image data is analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms to convert the image content into natural language and extract location information, sentiment information, and event-related tags from it. For example, software incorporating open-source machine learning libraries or commercial APIs may be used.

[0270] This generates detailed linguistic data about the image data, which is then assigned as tags. The data, along with the generated tags, is managed in a storage device, allowing users to quickly find the desired image in subsequent searches.

[0271] Users can enter search queries from their terminal to invoke specific contexts. An example of a prompt might be, "Show me fun travel moments." Based on this search query, the server quickly extracts the relevant image data from the database and provides it to the user.

[0272] For example, when a user enters the search query "birthday party," the server selects images tagged with "birthday" and related emotions and displays them on the user's device. This system allows users to easily rediscover and experience richer memories from multiple image data.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] The user accesses the system interface using their device, selects a digital image file, and begins uploading. The input is image data stored on the user's device, and the output is the transmission of image data to the server. Specifically, when the user clicks the upload button, the device sends the image data to the server via an HTTP POST request.

[0276] Step 2:

[0277] The server receives image data sent by the user and verifies its format. The input is the image data sent by the user, and the output is the verified image data. The server verifies that the received image data is in the correct format and size, and if there are no problems, it proceeds to the next step.

[0278] Step 3:

[0279] The server stores the verified image data in a remote storage device. The input is the verified image data, and the output is the data stored in a data storage system such as cloud storage. As a specific operation, the server uses an API to store the image data in the cloud and obtain a unique identifier.

[0280] Step 4:

[0281] The server sends the stored image data to a generative AI model and starts the analysis. The input is the image data obtained from cloud storage, and the output is the generated text-formatted data. The server loads the image data into the generative AI model, generates language data based on it, and extracts tags related to location information, sentiment information, and events.

[0282] Step 5:

[0283] Based on the generated language data and tag information, the server organizes and stores the data in the storage device. The input is the analyzed language data and tag information, and the output is the information recorded in the database. Specifically, the server uses a database management system to efficiently store the tagged information.

[0284] Step 6:

[0285] The user enters a search query using a specific context or keyword from the terminal. The input is a text-formatted prompt sentence by the user, and the output is a list of related images obtained as search results. The user enters a keyword in the search box and clicks the search button to send the query.

[0286] Step 7:

[0287] The server receives search queries from users and searches the database. The input is the user's search query, and the output is the relevant image data and its tag information. Specifically, the server quickly extracts the relevant image data based on the tag information in the database and provides it to the user.

[0288] Step 8:

[0289] The user views the images and information provided as search results on their device. The input is the search results sent from the server, and the output is the displayed images and related information. The user can scroll through the displayed images and click to view more detailed information.

[0290] This allows users to effectively search for information based on specific emotions or themes from a vast amount of image data and easily access images related to memories.

[0291] (Application Example 1)

[0292] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0293] In recent years, the amount of digital image data has increased rapidly, making it difficult for users to effectively manage their memories and access them quickly when needed. Furthermore, conventional systems lack the means to efficiently organize images and easily search based on specific emotions or events, highlighting the need for improved user experience.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes means for receiving and storing digital image data, means for analyzing the digital image data and utilizing a generative model to convert its content into natural language, and means for outputting the relevant digital image data to a display device in response to a search query from the user. This enables the user to emotionally manage their memories and to quickly and intuitively retrieve related images and information.

[0296] "Digital image data" refers to a collection of visual information that is stored and managed electronically.

[0297] A "generative model" is a system equipped with a learning algorithm that analyzes the content of digital images and converts it into natural language.

[0298] "Natural language" refers to information expressed in the form of language or words that humans use on a daily basis.

[0299] A "label" is a tag or identifier associated with digital image data, and is information assigned to represent its content or attributes.

[0300] A "database" is a management system for storing a collection of data that is systematically organized according to a specific purpose.

[0301] A "search query" is a question or command that a user enters into a database to retrieve information.

[0302] A "display device" is a device used to visually represent information generated by computers or electronic devices.

[0303] "Voice instructions" are commands or requests that are communicated in the form of sound, which a machine interprets and responds to.

[0304] To implement this invention, a system for processing digital image data is required. The central element is a server, which is responsible for receiving and storing digital image data from users. The stored data is securely stored in cloud storage. In addition, the server has a generative AI model as a means of analyzing image data, which can convert digital images into natural language text and extract important elements related to locations, emotions, and events. As a result, the image data is labeled and organized and stored in a database.

[0305] In daily life, users can give voice instructions through physical devices. For example, a home assistant robot functions as part of this system and can present relevant images according to user requests. At this time, the robot processes the voice instructions received from the user with the help of the generative AI model, searches for the corresponding data, and displays it on the output device.

[0306] The specific hardware used includes a home robot, a digital display, and a camera. As software, an image processing system using PIL (Python Imaging Library) and a generative AI model developed independently are used. These are responsible for the process of analyzing images, generating the necessary text information, and storing it in the database.

[0307] As a specific example, when a user gives a voice instruction to the robot, such as "Show me the happy moments of last summer vacation", the robot analyzes all the stored images, searches for images that meet the specified conditions, and can display them on the display or projector. In this process, a prompt sentence such as "Please display the photos taken during the trip last summer. Please select and emphasize the happy moments in particular." is processed by the generative AI model. As a result, users can easily experience the intended memories from a vast number of digital images.

[0308] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0309] Step 1:

[0310] The server receives digital image data from the user's device. The received image data is securely stored in cloud storage. In this step, the input is the image file sent by the user via their device, and the output is the image data stored in cloud storage. No data processing is performed; the data is saved in its original format.

[0311] Step 2:

[0312] The server retrieves image data stored in cloud storage and performs analysis using a generative AI model. The input is stored digital image data, and the output is natural language text as the analysis result. The data calculation involves analyzing the content of the image data and extracting important elements (location, emotion, events, etc.). This model uses a neural network to convert the image into a multidimensional vector and analyze its features.

[0313] Step 3:

[0314] The server labels image data based on the generated natural language text and then records those labels in a database. The input is the natural language text and image data obtained in step 2, and the output is the labeled database entries. Data processing involves organizing the information extracted from the text and assigning labels according to location, emotion, and event.

[0315] Step 4:

[0316] The user provides voice commands to a physical device, which are sent to the server as search queries. The input for this step is the user's voice commands, which are generated as prompts. These generated prompts are then sent to the server.

[0317] Step 5:

[0318] The server searches the database based on the received prompt and extracts digital image data that matches the criteria. The input is the search query in the prompt, and the output is the matching image data and its label information. The data calculation involves parsing the received string and comparing it with the entries in the database. As a result, the relevant image data is identified.

[0319] Step 6:

[0320] The server outputs the selected image data to the terminal and presents it to the user via the display device. The input is the matching image data extracted in step 5, and the output is visual information in a visually verifiable format. In this step, the image is displayed using a display or projector. The user can view the presented image and re-experience the information as needed.

[0321] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0322] This invention is a system for efficiently organizing users' digital image data and providing search results based on emotions. Users upload photos they have taken to a server via their terminal. The server stores the image data in cloud storage and then analyzes the photos using a generative model. In the analysis process, locations, people, objects, backgrounds, and emotions or events are extracted from the image content, and natural language text is generated.

[0323] Based on the transcribed data, the server assigns labels to the photos and stores them in a database. This enables quick searches based on specific criteria. The system also incorporates an emotion engine that recognizes the user's emotions, analyzing the user's past behavior and search history to infer their emotional state. Based on this emotional state, the search results are adjusted, prioritizing photos that are more relevant to the user.

[0324] For example, if a user searches for "fun memories at the beach," the server will present beach photos associated with fun based on past emotional data. The emotion engine selects the most suitable photos for the user's current mood, helping to recreate emotionally rich memories. This also makes it easier for users to rediscover emotionally resonant moments, rather than simply searching for images.

[0325] In this form, the invention is specifically implemented as a means to reconstruct photographs as valuable memories in a way that resonates with the user's emotions, to facilitate access to those memories, and to enrich individual experiences.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] The user uses their device to select the digital images they want to upload. After selection, the user presses the upload button, and the device sends the image data to the server.

[0329] Step 2:

[0330] The server saves the received digital image data to temporary storage. The server then migrates the data to cloud storage in preparation for long-term storage.

[0331] Step 3:

[0332] The server invokes a generative model in the cloud and requests analysis of the stored image data. The digital image is sent to the generative model to begin content analysis.

[0333] Step 4:

[0334] The generative model analyzes image data to identify people, objects, backgrounds, locations, emotions, and events, and generates natural language text based on this information. This information provides context and meaning to the photograph.

[0335] Step 5:

[0336] The server receives the generated text data and assigns labels such as location, emotion, and event based on it. The labeled data is stored in a database and organized to enable efficient searching.

[0337] Step 6:

[0338] The user enters a specific theme or keyword through their device and performs a search.

[0339] Step 7:

[0340] The server receives the user's search query and searches the database for image data with relevant labels. A sentiment engine is used in the search, which analyzes the user's past behavior and search history to infer their current emotional state.

[0341] Step 8:

[0342] The emotion engine adjusts search results, prioritizing and presenting images that are most relevant to the user's emotional state.

[0343] Step 9:

[0344] The server sends the selected search results to the user's device. The user can view the presented images and related information on their device, and emotionally re-experience memories through highly relevant photographs.

[0345] (Example 2)

[0346] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0347] The vast accumulation of digital image data makes it difficult to quickly and efficiently search for images related to specific emotions or events. Furthermore, technologies that present highly relevant images considering the user's current emotional state are still insufficient. To address this challenge, flexible and rapid searching based on image content and user emotions is necessary.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes means for receiving image data from a terminal and storing it in a storage device, means for analyzing the received image data and utilizing generation technology to convert the information into text, and means for adjusting search results based on the analyzed sentiment information and providing the user with the most suitable image data. This makes it possible to quickly and efficiently search for images related to specific emotions or events and present highly relevant images according to the user's current emotional state.

[0350] "Image data" refers to visual information stored in digital format, and is generally generated by cameras or digital devices.

[0351] A "storage device" is a medium or device for electronically storing and holding information.

[0352] "Generative technology" refers to techniques for analyzing received data and converting it into a specified format. This technology may include machine learning models and natural language processing techniques.

[0353] An "information tag" is additional information used to identify and classify specific digital data, and is usually expressed as a text label.

[0354] A "recording medium" is a physical or electronic medium used to store information, and includes databases and cloud storage.

[0355] "User" refers to a person or entity that uses this system to search for or view image data.

[0356] "Emotional state" refers to a user's psychological or emotional condition at a given point in time, and is inferred from data analysis and the user's behavioral history.

[0357] "Search results" refer to a list or set of information provided based on a user's request, including digital data that matches specified criteria.

[0358] This invention is a system that efficiently organizes digital image data captured by users and provides them with highly relevant search results based on their emotions. Users upload image data to the system using a device such as a smartphone or personal computer. The device sends this image data to the server via the HTTP / HTTPS protocol. The server receives the image data and stores it in cloud storage such as Amazon S3.

[0359] The server is equipped with a generative AI model for analyzing image data. This model uses technologies such as Google Cloud Vision API and Azure Image Analysis to extract text information from images. The generated text information includes location, emotions, events, people, objects, background, etc. Based on this information, the server creates information tags and stores them in a database. The database can use relational databases such as MySQL or PostgreSQL.

[0360] This system also features an emotion engine that analyzes the user's past behavior data and search history. This analysis infers the user's current emotional state and selects the most relevant images for the search query. Based on these optimized search results, the server provides the user with highly relevant image data.

[0361] For example, if a user searches for "happy memories at the beach," the system will prioritize displaying beach photos associated with past emotional data. This search process allows users to instantly rediscover emotionally resonant memories.

[0362] An example of a prompt statement is as follows: "Give the user a photo of a beach and describe the image search process to recreate related, enjoyable memories based on the user's emotions."

[0363] This system allows users to go beyond simple image searches and reconstruct meaningful experiences related to their own emotions.

[0364] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0365] Step 1:

[0366] Users select digital image data from devices such as smartphones and personal computers and upload it to the system. The input is image data stored on the user's device, and the output is the image data sent from the device to the server. This process is carried out using the HTTP / HTTPS protocol and encrypted communication is used to ensure data security.

[0367] Step 2:

[0368] The server processes image data received from the terminal and temporarily stores it in internal storage. The input is uploaded image data, and the output is image data uploaded to a cloud storage service. This process uses storage management software to store data on a cloud platform such as Amazon S3.

[0369] Step 3:

[0370] The server retrieves image data from cloud storage and begins analyzing the images using a generative AI model. The input is image data stored in the cloud, and the output is text information generated by the analysis. This analysis uses the Google Cloud Vision API and Azure Image Analysis to identify objects and context within the image and extract them as text.

[0371] Step 4:

[0372] The server assigns information tags to photos based on the generated text information, corresponding to emotions and events. The input is text information extracted through image analysis, and the output is image data with tags assigned to it. The assigned tags are stored in a database such as MySQL or PostgreSQL to support subsequent search processing.

[0373] Step 5:

[0374] The server uses an emotion engine to analyze the user's past data and infer their current emotional state. The input is the user's past behavior data and search history, and the output is information about the user's emotional state. Based on this inference, the server generates prompt statements relevant to the user's search query and applies the search process.

[0375] Step 6:

[0376] When a user specifies search criteria, the server searches the database and collects relevant image data. The input consists of the user's search query and prompts based on their emotional state, while the output is the retrieved images. The server adjusts the search results to match the user's emotional state and displays them in an appropriate order.

[0377] Step 7:

[0378] The user's device displays search results received from the server on its interface. The input is image data provided by the server as search results, and the output is a visual display through the user interface. The user can view the displayed images and easily recall memories that evoke specific emotions.

[0379] (Application Example 2)

[0380] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0381] The sheer volume of digital image information presents a challenge: it's difficult for users to quickly revisit past memories based on specific emotions or scenes. Furthermore, there's a lack of readily available ways to easily present emotionally relevant memories within the home.

[0382] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0383] In this invention, the server includes means for receiving and storing digital image information; means for analyzing the digital image information and utilizing a generative model to convert its content into natural language; means for assigning labels related to place, emotion, and event based on the natural language and storing them in a storage device; means for searching the storage device in response to a search request from a user and outputting the corresponding digital image information; and means for presenting the outputted digital image information on an external display device and displaying the image information selected based on the user's emotional state. This enables the user to quickly revisit past memories that fit their emotions within their home and obtain an emotionally rich memory experience.

[0384] "Digital image information" refers to visual data files recorded electronically that can be displayed and analyzed by computers and other electronic devices.

[0385] A "generative model" is an artificial intelligence algorithm that has the ability to learn patterns from data and generate new data, and is used for analyzing images and text.

[0386] A "storage device" is hardware or software used to store and manage data, and is responsible for holding digital information.

[0387] An "external display device" is hardware connected to a system to provide digital information to the user visually, and includes monitors and displays.

[0388] "User emotional state" refers to the emotional tendencies and feelings of individual users at a specific time, and is analyzed and inferred by the system.

[0389] A "label" is an information tag assigned to classify or identify data, and is used to describe the characteristics of images or text.

[0390] In the system that implements this application, the server plays a central role. Users upload digital images they have taken from their terminals to the server. To efficiently receive and store large amounts of image information, the server requires a high-speed network interface and large-capacity storage. The server also analyzes the uploaded digital image information using generative models such as TensorFlow. This analysis identifies people, objects, and backgrounds from the images and converts the content into natural language. The converted text data is stored in a database such as MongoDB.

[0391] Furthermore, the server utilizes a Python sentiment analysis library as its sentiment engine to analyze the user's past behavior data and search history to infer their emotional state. This allows for the labeling of images with information about location, emotion, and event. This labeled data is then used to quickly output appropriate digital images based on the user's search query.

[0392] A robot connected to an external display device shows image information provided by a server in a way that is tailored to the user's emotional state. For example, in response to a user request to "show me happy memories of the sea," search results based on past digital image information are displayed. This prompt allows the user to easily revisit emotionally rich memories within the comfort of their own home.

[0393] Example prompt: "Show me some photos of your fun beach memories."

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The system uploads digital images taken by the user from their device to a server. The input consists of multiple digital images taken with the user's device, and the output is an image file stored on the server's storage device. Specifically, the device uploads the files via a high-speed network connection, and the server stores the received files in a large-capacity storage device.

[0397] Step 2:

[0398] The server analyzes received digital images using TensorFlow, a generative AI model. The input is a digital image stored on the server, and the output is natural language text describing the analyzed content. Specifically, it identifies people, objects, and backgrounds from the image and describes them in natural language text.

[0399] Step 3:

[0400] The server assigns labels related to location, sentiment, and events based on the generated natural language text. The input is natural language text, and the output is text data with the label information attached. Specifically, it uses a sentiment engine to analyze the text and automatically assign appropriate labels.

[0401] Step 4:

[0402] The server stores label information in a database such as MongoDB. The input is labeled text data, and the output is the information stored in the database. Specifically, the information is inserted into the database in an appropriate format to enable efficient query searching.

[0403] Step 5:

[0404] The user makes a search request via their terminal. The input is a prompt message containing the user's criteria, and the output is the search result for images that match the criteria. Specifically, when the user enters "Show me pictures of fun beach memories," the server searches the database to identify the relevant image data.

[0405] Step 6:

[0406] The server sends search results to an external display device and displays the most suitable image according to the user's emotional state. The input is the image data of the search results, and the output is the visual displayed on the external display device. Specifically, the selected image is displayed on the screen, allowing the user to access emotionally rich memories.

[0407] 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.

[0408] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0410] [Third Embodiment]

[0411] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0412] 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.

[0413] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] 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.

[0415] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0417] 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.

[0418] 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.

[0419] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0420] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0422] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0423] This invention is configured as a system for organizing and utilizing digital image data owned by users as valuable memories. Users can upload photos from their devices, and the server receives them. The received image data is securely stored in cloud storage.

[0424] The server then utilizes generative models to analyze the stored image data. These generative models convert digital images into natural language text, extracting key elements such as location, emotion, and events from the image content. This allows the context associated with the photographs to be assigned as labels and stored in a database.

[0425] Users can search from their devices using specific themes or keywords to recall their memories. The server quickly searches the database based on the user's search query and provides the user with relevant images and related information. This allows users to easily access their intended memories from a vast collection of photographs.

[0426] For example, if a user searches for "birthday party," the server will display all images with the relevant label. It is also possible to search based on emotions such as "fun," allowing users to easily relive photos and moments associated with that emotion. In this form, the invention transforms photographs from mere data into valuable memories, providing users with an emotionally rich experience.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The user uses their device to select their digital images and clicks the upload button. The device then sends the selected image data to the server.

[0430] Step 2:

[0431] The server stores the received digital image data in temporary storage. Furthermore, the data is moved to cloud storage in preparation for long-term storage.

[0432] Step 3:

[0433] The server invokes a generative model in the cloud and requests analysis of the stored image data. It generates a request for analysis and transfers the digital images to the model.

[0434] Step 4:

[0435] The generative model analyzes image data and generates natural language text based on that analysis. This text includes information about the image's location, people, objects, background, and emotions or events.

[0436] Step 5:

[0437] The server receives the generated text data and assigns labels based on its content. These labels include tags related to location, emotions, events, etc.

[0438] Step 6:

[0439] The server stores labeled information in a database and organizes it systematically so that users can search for it later.

[0440] Step 7:

[0441] The user uses the device's interface to enter a specific theme or keyword and perform a search.

[0442] Step 8:

[0443] The server searches the database based on the user's search query. It quickly identifies and organizes image data with the corresponding label.

[0444] Step 9:

[0445] The server sends search results to the terminal and presents the user with digital image data and related information that matches the criteria specified by the user.

[0446] Step 10:

[0447] Users can relive their memories by viewing the displayed search results and checking the images and accompanying information.

[0448] (Example 1)

[0449] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0450] A challenge exists in efficiently organizing and retrieving important memories and information buried within a vast amount of digital image data. Existing methods make it difficult to understand and tag image content in detail, preventing users from quickly obtaining the information they intend.

[0451] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0452] In this invention, the server includes means for receiving image data and storing it in a remote storage device, means for analyzing the image data and utilizing a generative model to convert its contents into language data, and means for assigning location information, emotion information, and event-related tags based on the language data and storing them in the storage device. This makes it possible for users to easily search for and retrieve images based on specific contexts or emotions from a vast amount of image data.

[0453] "Image data" refers to files that represent visual information acquired by a user in a digital format and can be processed by a computer.

[0454] "Remote storage" refers to a system or device for storing data in storage located at a physically distant location.

[0455] A "generative model" refers to an algorithm based on artificial intelligence technology that analyzes input data and generates a specific output.

[0456] "Linguistic data" refers to data that represents images and other information in natural language.

[0457] "Location information" refers to geographical information that indicates where specific data or events occurred.

[0458] "Emotional information" refers to information about the emotional state and nuances associated with data or events.

[0459] "Event" refers to the occurrences or activities that take place within the image data.

[0460] A "tag" refers to an identifier or label assigned to data to make it easier to classify and search for.

[0461] A "storage device" refers to hardware or software that stores data and allows that data to be retrieved as needed.

[0462] A "search request" refers to an instruction or query that a user sends to a system in order to retrieve specific information.

[0463] This invention is a system that makes it easier for users to organize and utilize large amounts of digital image data they possess, and its details are described below. First, users can upload their digital images using a terminal. The server stores the received image data in a physically distant, remote data storage. This storage can utilize a cloud-based storage service, and specifically, a general-purpose data storage platform is expected to be used.

[0464] The stored image data is analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms to convert the image content into natural language and extract location information, sentiment information, and event-related tags from it. For example, software incorporating open-source machine learning libraries or commercial APIs may be used.

[0465] This generates detailed linguistic data about the image data, which is then assigned as tags. The data, along with the generated tags, is managed in a storage device, allowing users to quickly find the desired image in subsequent searches.

[0466] Users can enter search queries from their terminal to invoke specific contexts. An example of a prompt might be, "Show me fun travel moments." Based on this search query, the server quickly extracts the relevant image data from the database and provides it to the user.

[0467] For example, when a user enters the search query "birthday party," the server selects images tagged with "birthday" and related emotions and displays them on the user's device. This system allows users to easily rediscover and experience richer memories from multiple image data.

[0468] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0469] Step 1:

[0470] The user accesses the system interface using their device, selects a digital image file, and begins uploading. The input is image data stored on the user's device, and the output is the transmission of image data to the server. Specifically, when the user clicks the upload button, the device sends the image data to the server via an HTTP POST request.

[0471] Step 2:

[0472] The server receives image data sent by the user and verifies its format. The input is the image data sent by the user, and the output is the verified image data. The server verifies that the received image data is in the correct format and size, and if there are no problems, it proceeds to the next step.

[0473] Step 3:

[0474] The server saves verified image data to remote storage. The input is verified image data, and the output is data stored in a data storage system such as cloud storage. Specifically, the server uses an API to save the image data to the cloud and obtain a unique identifier.

[0475] Step 4:

[0476] The server sends the stored image data to a generating AI model and begins analysis. The input is image data retrieved from cloud storage, and the output is generated text data. The server feeds the image data into the generating AI model, which generates linguistic data based on it and extracts location information, sentiment information, and event-related tags.

[0477] Step 5:

[0478] The server organizes and stores data in its storage device based on the generated language data and tag information. The input is the parsed language data and tag information, and the output is the information recorded in the database. Specifically, the server uses a database management system to efficiently store the tagged information.

[0479] Step 6:

[0480] The user enters a search query from their device using specific context and keywords. The input is a text-based prompt from the user, and the output is a list of related images obtained as search results. The user submits the query by entering keywords in the search box and clicking the search button.

[0481] Step 7:

[0482] The server receives search queries from users and searches the database. The input is the user's search query, and the output is the relevant image data and its tag information. Specifically, the server quickly extracts the relevant image data based on the tag information in the database and provides it to the user.

[0483] Step 8:

[0484] The user views the images and information provided as search results on their device. The input is the search results sent from the server, and the output is the displayed images and related information. The user can scroll through the displayed images and click to view more detailed information.

[0485] This allows users to effectively search for information based on specific emotions or themes from a vast amount of image data and easily access images related to memories.

[0486] (Application Example 1)

[0487] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0488] In recent years, the amount of digital image data has increased rapidly, making it difficult for users to effectively manage their memories and access them quickly when needed. Furthermore, conventional systems lack the means to efficiently organize images and easily search based on specific emotions or events, highlighting the need for improved user experience.

[0489] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0490] In this invention, the server includes means for receiving and storing digital image data, means for analyzing the digital image data and utilizing a generative model to convert its content into natural language, and means for outputting the relevant digital image data to a display device in response to a search query from the user. This enables the user to emotionally manage their memories and to quickly and intuitively retrieve related images and information.

[0491] "Digital image data" refers to a collection of visual information that is stored and managed electronically.

[0492] A "generative model" is a system equipped with a learning algorithm that analyzes the content of digital images and converts it into natural language.

[0493] "Natural language" refers to information expressed in the form of language or words that humans use on a daily basis.

[0494] A "label" is a tag or identifier associated with digital image data, and is information assigned to represent its content or attributes.

[0495] A "database" is a management system for storing a collection of data that is systematically organized according to a specific purpose.

[0496] A "search query" is a question or command that a user enters into a database to retrieve information.

[0497] A "display device" is a device used to visually represent information generated by computers or electronic devices.

[0498] "Voice instructions" are commands or requests that are communicated in the form of sound, which a machine interprets and responds to.

[0499] To implement this invention, a system for processing digital image data is required. The central element of this system is a server, which receives and stores digital image data from users. The stored data is securely stored in cloud storage. The server also includes a generative AI model for analyzing the image data, converting digital images into natural language text and extracting key elements related to location, emotions, and events. As a result, the image data is labeled and organized and stored in a database.

[0500] Users can issue voice commands through physical devices in their daily lives. For example, a home assistant robot can function as part of this system, presenting relevant images according to the user's requests. In this case, the robot processes the voice commands received from the user with the help of a generative AI model, searches for the corresponding data, and displays it on an output device.

[0501] The specific hardware used includes home robots, digital displays, and cameras. The software consists of an image processing system using PIL (Python Imaging Library) and a proprietary generative AI model. These are responsible for analyzing images, generating necessary text information, and storing it in a database.

[0502] As a concrete example, when a user gives a voice command to a robot saying, "Show me the fun moments from last summer's vacation," the robot can analyze all the stored images, find images that match the specified criteria, and display them on a screen or projector. In this process, the generative AI model processes prompts such as, "Show me the photos taken on last summer's trip. Please highlight the fun moments in particular." This makes it easy for the user to relive their intended memories from a vast amount of digital images.

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] The server receives digital image data from the user's device. The received image data is securely stored in cloud storage. In this step, the input is the image file sent by the user via their device, and the output is the image data stored in cloud storage. No data processing is performed; the data is saved in its original format.

[0506] Step 2:

[0507] The server retrieves image data stored in cloud storage and performs analysis using a generative AI model. The input is stored digital image data, and the output is natural language text as the analysis result. The data calculation involves analyzing the content of the image data and extracting important elements (location, emotion, events, etc.). This model uses a neural network to convert the image into a multidimensional vector and analyze its features.

[0508] Step 3:

[0509] The server labels image data based on the generated natural language text and then records those labels in a database. The input is the natural language text and image data obtained in step 2, and the output is the labeled database entries. Data processing involves organizing the information extracted from the text and assigning labels according to location, emotion, and event.

[0510] Step 4:

[0511] The user provides voice commands to a physical device, which are sent to the server as search queries. The input for this step is the user's voice commands, which are generated as prompts. These generated prompts are then sent to the server.

[0512] Step 5:

[0513] The server searches the database based on the received prompt and extracts digital image data that matches the criteria. The input is the search query in the prompt, and the output is the matching image data and its label information. The data calculation involves parsing the received string and comparing it with the entries in the database. As a result, the relevant image data is identified.

[0514] Step 6:

[0515] The server outputs the selected image data to the terminal and presents it to the user via the display device. The input is the matching image data extracted in step 5, and the output is visual information in a visually verifiable format. In this step, the image is displayed using a display or projector. The user can view the presented image and re-experience the information as needed.

[0516] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0517] This invention is a system for efficiently organizing users' digital image data and providing search results based on emotions. Users upload photos they have taken to a server via their terminal. The server stores the image data in cloud storage and then analyzes the photos using a generative model. In the analysis process, locations, people, objects, backgrounds, and emotions or events are extracted from the image content, and natural language text is generated.

[0518] Based on the transcribed data, the server assigns labels to the photos and stores them in a database. This enables quick searches based on specific criteria. The system also incorporates an emotion engine that recognizes the user's emotions, analyzing the user's past behavior and search history to infer their emotional state. Based on this emotional state, the search results are adjusted, prioritizing photos that are more relevant to the user.

[0519] For example, if a user searches for "fun memories at the beach," the server will present beach photos associated with fun based on past emotional data. The emotion engine selects the most suitable photos for the user's current mood, helping to recreate emotionally rich memories. This also makes it easier for users to rediscover emotionally resonant moments, rather than simply searching for images.

[0520] In this form, the invention is specifically implemented as a means to reconstruct photographs as valuable memories in a way that resonates with the user's emotions, to facilitate access to those memories, and to enrich individual experiences.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] The user uses their device to select the digital images they want to upload. After selection, the user presses the upload button, and the device sends the image data to the server.

[0524] Step 2:

[0525] The server saves the received digital image data to temporary storage. The server then migrates the data to cloud storage in preparation for long-term storage.

[0526] Step 3:

[0527] The server invokes a generative model in the cloud and requests analysis of the stored image data. The digital image is sent to the generative model to begin content analysis.

[0528] Step 4:

[0529] The generative model analyzes image data to identify people, objects, backgrounds, locations, emotions, and events, and generates natural language text based on this information. This information provides context and meaning to the photograph.

[0530] Step 5:

[0531] The server receives the generated text data and assigns labels such as location, emotion, and event based on it. The labeled data is stored in a database and organized to enable efficient searching.

[0532] Step 6:

[0533] The user enters a specific theme or keyword through their device and performs a search.

[0534] Step 7:

[0535] The server receives the user's search query and searches the database for image data with relevant labels. A sentiment engine is used in the search, which analyzes the user's past behavior and search history to infer their current emotional state.

[0536] Step 8:

[0537] The emotion engine adjusts search results, prioritizing and presenting images that are most relevant to the user's emotional state.

[0538] Step 9:

[0539] The server sends the selected search results to the user's device. The user can view the presented images and related information on their device, and emotionally re-experience memories through highly relevant photographs.

[0540] (Example 2)

[0541] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0542] The vast accumulation of digital image data makes it difficult to quickly and efficiently search for images related to specific emotions or events. Furthermore, technologies that present highly relevant images considering the user's current emotional state are still insufficient. To address this challenge, flexible and rapid searching based on image content and user emotions is necessary.

[0543] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0544] In this invention, the server includes means for receiving image data from a terminal and storing it in a storage device, means for analyzing the received image data and utilizing generation technology to convert the information into text, and means for adjusting search results based on the analyzed sentiment information and providing the user with the most suitable image data. This makes it possible to quickly and efficiently search for images related to specific emotions or events and present highly relevant images according to the user's current emotional state.

[0545] "Image data" refers to visual information stored in digital format, and is generally generated by cameras or digital devices.

[0546] A "storage device" is a medium or device for electronically storing and holding information.

[0547] "Generative technology" refers to techniques for analyzing received data and converting it into a specified format. This technology may include machine learning models and natural language processing techniques.

[0548] An "information tag" is additional information used to identify and classify specific digital data, and is usually expressed as a text label.

[0549] A "recording medium" is a physical or electronic medium used to store information, and includes databases and cloud storage.

[0550] "User" refers to a person or entity that uses this system to search for or view image data.

[0551] "Emotional state" refers to a user's psychological or emotional condition at a given point in time, and is inferred from data analysis and the user's behavioral history.

[0552] "Search results" refer to a list or set of information provided based on a user's request, including digital data that matches specified criteria.

[0553] This invention is a system that efficiently organizes digital image data captured by users and provides them with highly relevant search results based on their emotions. Users upload image data to the system using a device such as a smartphone or personal computer. The device sends this image data to the server via the HTTP / HTTPS protocol. The server receives the image data and stores it in cloud storage such as Amazon S3.

[0554] The server is equipped with a generative AI model for analyzing image data. This model uses technologies such as Google Cloud Vision API and Azure Image Analysis to extract text information from images. The generated text information includes location, emotions, events, people, objects, background, etc. Based on this information, the server creates information tags and stores them in a database. The database can use relational databases such as MySQL or PostgreSQL.

[0555] This system also features an emotion engine that analyzes the user's past behavior data and search history. This analysis infers the user's current emotional state and selects the most relevant images for the search query. Based on these optimized search results, the server provides the user with highly relevant image data.

[0556] For example, if a user searches for "happy memories at the beach," the system will prioritize displaying beach photos associated with past emotional data. This search process allows users to instantly rediscover emotionally resonant memories.

[0557] An example of a prompt statement is as follows: "Give the user a photo of a beach and describe the image search process to recreate related, enjoyable memories based on the user's emotions."

[0558] This system allows users to go beyond simple image searches and reconstruct meaningful experiences related to their own emotions.

[0559] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0560] Step 1:

[0561] Users select digital image data from devices such as smartphones and personal computers and upload it to the system. The input is image data stored on the user's device, and the output is the image data sent from the device to the server. This process is carried out using the HTTP / HTTPS protocol and encrypted communication is used to ensure data security.

[0562] Step 2:

[0563] The server processes image data received from the terminal and temporarily stores it in internal storage. The input is uploaded image data, and the output is image data uploaded to a cloud storage service. This process uses storage management software to store data on a cloud platform such as Amazon S3.

[0564] Step 3:

[0565] The server retrieves image data from cloud storage and begins analyzing the images using a generative AI model. The input is image data stored in the cloud, and the output is text information generated by the analysis. This analysis uses the Google Cloud Vision API and Azure Image Analysis to identify objects and context within the image and extract them as text.

[0566] Step 4:

[0567] The server assigns information tags to photos based on the generated text information, corresponding to emotions and events. The input is text information extracted through image analysis, and the output is image data with tags assigned to it. The assigned tags are stored in a database such as MySQL or PostgreSQL to support subsequent search processing.

[0568] Step 5:

[0569] The server uses an emotion engine to analyze the user's past data and infer their current emotional state. The input is the user's past behavior data and search history, and the output is information about the user's emotional state. Based on this inference, the server generates prompt statements relevant to the user's search query and applies the search process.

[0570] Step 6:

[0571] When a user specifies search criteria, the server searches the database and collects relevant image data. The input consists of the user's search query and prompts based on their emotional state, while the output is the retrieved images. The server adjusts the search results to match the user's emotional state and displays them in an appropriate order.

[0572] Step 7:

[0573] The user's device displays search results received from the server on its interface. The input is image data provided by the server as search results, and the output is a visual display through the user interface. The user can view the displayed images and easily recall memories that evoke specific emotions.

[0574] (Application Example 2)

[0575] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0576] The sheer volume of digital image information presents a challenge: it's difficult for users to quickly revisit past memories based on specific emotions or scenes. Furthermore, there's a lack of readily available ways to easily present emotionally relevant memories within the home.

[0577] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0578] In this invention, the server includes means for receiving and storing digital image information; means for analyzing the digital image information and utilizing a generative model to convert its content into natural language; means for assigning labels related to place, emotion, and event based on the natural language and storing them in a storage device; means for searching the storage device in response to a search request from a user and outputting the corresponding digital image information; and means for presenting the outputted digital image information on an external display device and displaying the image information selected based on the user's emotional state. This enables the user to quickly revisit past memories that fit their emotions within their home and obtain an emotionally rich memory experience.

[0579] "Digital image information" refers to visual data files recorded electronically that can be displayed and analyzed by computers and other electronic devices.

[0580] A "generative model" is an artificial intelligence algorithm that has the ability to learn patterns from data and generate new data, and is used for analyzing images and text.

[0581] A "storage device" is hardware or software used to store and manage data, and is responsible for holding digital information.

[0582] An "external display device" is hardware connected to a system to provide digital information to the user visually, and includes monitors and displays.

[0583] "User emotional state" refers to the emotional tendencies and feelings of individual users at a specific time, and is analyzed and inferred by the system.

[0584] A "label" is an information tag assigned to classify or identify data, and is used to describe the characteristics of images or text.

[0585] In the system that implements this application, the server plays a central role. Users upload digital images they have taken from their terminals to the server. To efficiently receive and store large amounts of image information, the server requires a high-speed network interface and large-capacity storage. The server also analyzes the uploaded digital image information using generative models such as TensorFlow. This analysis identifies people, objects, and backgrounds from the images and converts the content into natural language. The converted text data is stored in a database such as MongoDB.

[0586] Furthermore, the server utilizes a Python sentiment analysis library as its sentiment engine to analyze the user's past behavior data and search history to infer their emotional state. This allows for the labeling of images with information about location, emotion, and event. This labeled data is then used to quickly output appropriate digital images based on the user's search query.

[0587] A robot connected to an external display device shows image information provided by a server in a way that is tailored to the user's emotional state. For example, in response to a user request to "show me happy memories of the sea," search results based on past digital image information are displayed. This prompt allows the user to easily revisit emotionally rich memories within the comfort of their own home.

[0588] Example prompt: "Show me some photos of your fun beach memories."

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The system uploads digital images taken by the user from their device to a server. The input consists of multiple digital images taken with the user's device, and the output is an image file stored on the server's storage device. Specifically, the device uploads the files via a high-speed network connection, and the server stores the received files in a large-capacity storage device.

[0592] Step 2:

[0593] The server analyzes received digital images using TensorFlow, a generative AI model. The input is a digital image stored on the server, and the output is natural language text describing the analyzed content. Specifically, it identifies people, objects, and backgrounds from the image and describes them in natural language text.

[0594] Step 3:

[0595] The server assigns labels related to location, sentiment, and events based on the generated natural language text. The input is natural language text, and the output is text data with the label information attached. Specifically, it uses a sentiment engine to analyze the text and automatically assign appropriate labels.

[0596] Step 4:

[0597] The server stores label information in a database such as MongoDB. The input is labeled text data, and the output is the information stored in the database. Specifically, the information is inserted into the database in an appropriate format to enable efficient query searching.

[0598] Step 5:

[0599] The user makes a search request via their terminal. The input is a prompt message containing the user's criteria, and the output is the search result for images that match the criteria. Specifically, when the user enters "Show me pictures of fun beach memories," the server searches the database to identify the relevant image data.

[0600] Step 6:

[0601] The server sends search results to an external display device and displays the most suitable image according to the user's emotional state. The input is the image data of the search results, and the output is the visual displayed on the external display device. Specifically, the selected image is displayed on the screen, allowing the user to access emotionally rich memories.

[0602] 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.

[0603] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0604] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0605] [Fourth Embodiment]

[0606] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0607] 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.

[0608] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0609] 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.

[0610] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0611] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0612] 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.

[0613] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0614] 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.

[0615] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0616] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0617] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0618] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0619] This invention is configured as a system for organizing and utilizing digital image data owned by users as valuable memories. Users can upload photos from their devices, and the server receives them. The received image data is securely stored in cloud storage.

[0620] The server then utilizes generative models to analyze the stored image data. These generative models convert digital images into natural language text, extracting key elements such as location, emotion, and events from the image content. This allows the context associated with the photographs to be assigned as labels and stored in a database.

[0621] Users can search from their devices using specific themes or keywords to recall their memories. The server quickly searches the database based on the user's search query and provides the user with relevant images and related information. This allows users to easily access their intended memories from a vast collection of photographs.

[0622] For example, if a user searches for "birthday party," the server will display all images with the relevant label. It is also possible to search based on emotions such as "fun," allowing users to easily relive photos and moments associated with that emotion. In this form, the invention transforms photographs from mere data into valuable memories, providing users with an emotionally rich experience.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] The user uses their device to select their digital images and clicks the upload button. The device then sends the selected image data to the server.

[0626] Step 2:

[0627] The server stores the received digital image data in temporary storage. Furthermore, the data is moved to cloud storage in preparation for long-term storage.

[0628] Step 3:

[0629] The server invokes a generative model in the cloud and requests analysis of the stored image data. It generates a request for analysis and transfers the digital images to the model.

[0630] Step 4:

[0631] The generative model analyzes image data and generates natural language text based on that analysis. This text includes information about the image's location, people, objects, background, and emotions or events.

[0632] Step 5:

[0633] The server receives the generated text data and assigns labels based on its content. These labels include tags related to location, emotions, events, etc.

[0634] Step 6:

[0635] The server stores labeled information in a database and organizes it systematically so that users can search for it later.

[0636] Step 7:

[0637] The user uses the device's interface to enter a specific theme or keyword and perform a search.

[0638] Step 8:

[0639] The server searches the database based on the user's search query. It quickly identifies and organizes image data with the corresponding label.

[0640] Step 9:

[0641] The server sends search results to the terminal and presents the user with digital image data and related information that matches the criteria specified by the user.

[0642] Step 10:

[0643] Users can relive their memories by viewing the displayed search results and checking the images and accompanying information.

[0644] (Example 1)

[0645] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0646] A challenge exists in efficiently organizing and retrieving important memories and information buried within a vast amount of digital image data. Existing methods make it difficult to understand and tag image content in detail, preventing users from quickly obtaining the information they intend.

[0647] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0648] In this invention, the server includes means for receiving image data and storing it in a remote storage device, means for analyzing the image data and utilizing a generative model to convert its contents into language data, and means for assigning location information, emotion information, and event-related tags based on the language data and storing them in the storage device. This makes it possible for users to easily search for and retrieve images based on specific contexts or emotions from a vast amount of image data.

[0649] "Image data" refers to files that represent visual information acquired by a user in a digital format and can be processed by a computer.

[0650] "Remote storage" refers to a system or device for storing data in storage located at a physically distant location.

[0651] A "generative model" refers to an algorithm based on artificial intelligence technology that analyzes input data and generates a specific output.

[0652] "Linguistic data" refers to data that represents images and other information in natural language.

[0653] "Location information" refers to geographical information that indicates where specific data or events occurred.

[0654] "Emotional information" refers to information about the emotional state and nuances associated with data or events.

[0655] "Event" refers to the occurrences or activities that take place within the image data.

[0656] A "tag" refers to an identifier or label assigned to data to make it easier to classify and search for.

[0657] A "storage device" refers to hardware or software that stores data and allows that data to be retrieved as needed.

[0658] A "search request" refers to an instruction or query that a user sends to a system in order to retrieve specific information.

[0659] This invention is a system that makes it easier for users to organize and utilize large amounts of digital image data they possess, and its details are described below. First, users can upload their digital images using a terminal. The server stores the received image data in a physically distant, remote data storage. This storage can utilize a cloud-based storage service, and specifically, a general-purpose data storage platform is expected to be used.

[0660] The stored image data is analyzed by a generative AI model on the server. This generative AI model uses machine learning algorithms to convert the image content into natural language and extract location information, sentiment information, and event-related tags from it. For example, software incorporating open-source machine learning libraries or commercial APIs may be used.

[0661] This generates detailed linguistic data about the image data, which is then assigned as tags. The data, along with the generated tags, is managed in a storage device, allowing users to quickly find the desired image in subsequent searches.

[0662] Users can enter search queries from their terminal to invoke specific contexts. An example of a prompt might be, "Show me fun travel moments." Based on this search query, the server quickly extracts the relevant image data from the database and provides it to the user.

[0663] For example, when a user enters the search query "birthday party," the server selects images tagged with "birthday" and related emotions and displays them on the user's device. This system allows users to easily rediscover and experience richer memories from multiple image data.

[0664] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0665] Step 1:

[0666] The user accesses the system interface using their device, selects a digital image file, and begins uploading. The input is image data stored on the user's device, and the output is the transmission of image data to the server. Specifically, when the user clicks the upload button, the device sends the image data to the server via an HTTP POST request.

[0667] Step 2:

[0668] The server receives image data sent by the user and verifies its format. The input is the image data sent by the user, and the output is the verified image data. The server verifies that the received image data is in the correct format and size, and if there are no problems, it proceeds to the next step.

[0669] Step 3:

[0670] The server saves verified image data to remote storage. The input is verified image data, and the output is data stored in a data storage system such as cloud storage. Specifically, the server uses an API to save the image data to the cloud and obtain a unique identifier.

[0671] Step 4:

[0672] The server sends the stored image data to a generating AI model and begins analysis. The input is image data retrieved from cloud storage, and the output is generated text data. The server feeds the image data into the generating AI model, which generates linguistic data based on it and extracts location information, sentiment information, and event-related tags.

[0673] Step 5:

[0674] The server organizes and stores data in its storage device based on the generated language data and tag information. The input is the parsed language data and tag information, and the output is the information recorded in the database. Specifically, the server uses a database management system to efficiently store the tagged information.

[0675] Step 6:

[0676] The user enters a search query from their device using specific context and keywords. The input is a text-based prompt from the user, and the output is a list of related images obtained as search results. The user submits the query by entering keywords in the search box and clicking the search button.

[0677] Step 7:

[0678] The server receives search queries from users and searches the database. The input is the user's search query, and the output is the relevant image data and its tag information. Specifically, the server quickly extracts the relevant image data based on the tag information in the database and provides it to the user.

[0679] Step 8:

[0680] The user views the images and information provided as search results on their device. The input is the search results sent from the server, and the output is the displayed images and related information. The user can scroll through the displayed images and click to view more detailed information.

[0681] This allows users to effectively search for information based on specific emotions or themes from a vast amount of image data and easily access images related to memories.

[0682] (Application Example 1)

[0683] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] In recent years, the amount of digital image data has increased rapidly, making it difficult for users to effectively manage their memories and access them quickly when needed. Furthermore, conventional systems lack the means to efficiently organize images and easily search based on specific emotions or events, highlighting the need for improved user experience.

[0685] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0686] In this invention, the server includes means for receiving and storing digital image data, means for analyzing the digital image data and utilizing a generative model to convert its content into natural language, and means for outputting the relevant digital image data to a display device in response to a search query from the user. This enables the user to emotionally manage their memories and to quickly and intuitively retrieve related images and information.

[0687] "Digital image data" refers to a collection of visual information that is stored and managed electronically.

[0688] A "generative model" is a system equipped with a learning algorithm that analyzes the content of digital images and converts it into natural language.

[0689] "Natural language" refers to information expressed in the form of language or words that humans use on a daily basis.

[0690] A "label" is a tag or identifier associated with digital image data, and is information assigned to represent its content or attributes.

[0691] A "database" is a management system for storing a collection of data that is systematically organized according to a specific purpose.

[0692] A "search query" is a question or command that a user enters into a database to retrieve information.

[0693] A "display device" is a device used to visually represent information generated by computers or electronic devices.

[0694] "Voice instructions" are commands or requests that are communicated in the form of sound, which a machine interprets and responds to.

[0695] To implement this invention, a system for processing digital image data is required. The central element of this system is a server, which receives and stores digital image data from users. The stored data is securely stored in cloud storage. The server also includes a generative AI model for analyzing the image data, converting digital images into natural language text and extracting key elements related to location, emotions, and events. As a result, the image data is labeled and organized and stored in a database.

[0696] Users can issue voice commands through physical devices in their daily lives. For example, a home assistant robot can function as part of this system, presenting relevant images according to the user's requests. In this case, the robot processes the voice commands received from the user with the help of a generative AI model, searches for the corresponding data, and displays it on an output device.

[0697] The specific hardware used includes home robots, digital displays, and cameras. The software consists of an image processing system using PIL (Python Imaging Library) and a proprietary generative AI model. These are responsible for analyzing images, generating necessary text information, and storing it in a database.

[0698] As a concrete example, when a user gives a voice command to a robot saying, "Show me the fun moments from last summer's vacation," the robot can analyze all the stored images, find images that match the specified criteria, and display them on a screen or projector. In this process, the generative AI model processes prompts such as, "Show me the photos taken on last summer's trip. Please highlight the fun moments in particular." This makes it easy for the user to relive their intended memories from a vast amount of digital images.

[0699] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0700] Step 1:

[0701] The server receives digital image data from the user's device. The received image data is securely stored in cloud storage. In this step, the input is the image file sent by the user via their device, and the output is the image data stored in cloud storage. No data processing is performed; the data is saved in its original format.

[0702] Step 2:

[0703] The server retrieves image data stored in cloud storage and performs analysis using a generative AI model. The input is stored digital image data, and the output is natural language text as the analysis result. The data calculation involves analyzing the content of the image data and extracting important elements (location, emotion, events, etc.). This model uses a neural network to convert the image into a multidimensional vector and analyze its features.

[0704] Step 3:

[0705] The server labels image data based on the generated natural language text and then records those labels in a database. The input is the natural language text and image data obtained in step 2, and the output is the labeled database entries. Data processing involves organizing the information extracted from the text and assigning labels according to location, emotion, and event.

[0706] Step 4:

[0707] The user provides voice commands to a physical device, which are sent to the server as search queries. The input for this step is the user's voice commands, which are generated as prompts. These generated prompts are then sent to the server.

[0708] Step 5:

[0709] The server searches the database based on the received prompt and extracts digital image data that matches the criteria. The input is the search query in the prompt, and the output is the matching image data and its label information. The data calculation involves parsing the received string and comparing it with the entries in the database. As a result, the relevant image data is identified.

[0710] Step 6:

[0711] The server outputs the selected image data to the terminal and presents it to the user via the display device. The input is the matching image data extracted in step 5, and the output is visual information in a visually verifiable format. In this step, the image is displayed using a display or projector. The user can view the presented image and re-experience the information as needed.

[0712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0713] This invention is a system for efficiently organizing users' digital image data and providing search results based on emotions. Users upload photos they have taken to a server via their terminal. The server stores the image data in cloud storage and then analyzes the photos using a generative model. In the analysis process, locations, people, objects, backgrounds, and emotions or events are extracted from the image content, and natural language text is generated.

[0714] Based on the transcribed data, the server assigns labels to the photos and stores them in a database. This enables quick searches based on specific criteria. The system also incorporates an emotion engine that recognizes the user's emotions, analyzing the user's past behavior and search history to infer their emotional state. Based on this emotional state, the search results are adjusted, prioritizing photos that are more relevant to the user.

[0715] For example, if a user searches for "fun memories at the beach," the server will present beach photos associated with fun based on past emotional data. The emotion engine selects the most suitable photos for the user's current mood, helping to recreate emotionally rich memories. This also makes it easier for users to rediscover emotionally resonant moments, rather than simply searching for images.

[0716] In this form, the invention is specifically implemented as a means to reconstruct photographs as valuable memories in a way that resonates with the user's emotions, to facilitate access to those memories, and to enrich individual experiences.

[0717] The following describes the processing flow.

[0718] Step 1:

[0719] The user uses their device to select the digital images they want to upload. After selection, the user presses the upload button, and the device sends the image data to the server.

[0720] Step 2:

[0721] The server saves the received digital image data to temporary storage. The server then migrates the data to cloud storage in preparation for long-term storage.

[0722] Step 3:

[0723] The server invokes a generative model in the cloud and requests analysis of the stored image data. The digital image is sent to the generative model to begin content analysis.

[0724] Step 4:

[0725] The generative model analyzes image data to identify people, objects, backgrounds, locations, emotions, and events, and generates natural language text based on this information. This information provides context and meaning to the photograph.

[0726] Step 5:

[0727] The server receives the generated text data and assigns labels such as location, emotion, and event based on it. The labeled data is stored in a database and organized to enable efficient searching.

[0728] Step 6:

[0729] The user enters a specific theme or keyword through their device and performs a search.

[0730] Step 7:

[0731] The server receives the user's search query and searches the database for image data with relevant labels. A sentiment engine is used in the search, which analyzes the user's past behavior and search history to infer their current emotional state.

[0732] Step 8:

[0733] The emotion engine adjusts search results, prioritizing and presenting images that are most relevant to the user's emotional state.

[0734] Step 9:

[0735] The server sends the selected search results to the user's device. The user can view the presented images and related information on their device, and emotionally re-experience memories through highly relevant photographs.

[0736] (Example 2)

[0737] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0738] The vast accumulation of digital image data makes it difficult to quickly and efficiently search for images related to specific emotions or events. Furthermore, technologies that present highly relevant images considering the user's current emotional state are still insufficient. To address this challenge, flexible and rapid searching based on image content and user emotions is necessary.

[0739] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0740] In this invention, the server includes means for receiving image data from a terminal and storing it in a storage device, means for analyzing the received image data and utilizing generation technology to convert the information into text, and means for adjusting search results based on the analyzed sentiment information and providing the user with the most suitable image data. This makes it possible to quickly and efficiently search for images related to specific emotions or events and present highly relevant images according to the user's current emotional state.

[0741] "Image data" refers to visual information stored in digital format, and is generally generated by cameras or digital devices.

[0742] A "storage device" is a medium or device for electronically storing and holding information.

[0743] "Generative technology" refers to techniques for analyzing received data and converting it into a specified format. This technology may include machine learning models and natural language processing techniques.

[0744] An "information tag" is additional information used to identify and classify specific digital data, and is usually expressed as a text label.

[0745] A "recording medium" is a physical or electronic medium used to store information, and includes databases and cloud storage.

[0746] "User" refers to a person or entity that uses this system to search for or view image data.

[0747] "Emotional state" refers to a user's psychological or emotional condition at a given point in time, and is inferred from data analysis and the user's behavioral history.

[0748] "Search results" refer to a list or set of information provided based on a user's request, including digital data that matches specified criteria.

[0749] This invention is a system that efficiently organizes digital image data captured by users and provides them with highly relevant search results based on their emotions. Users upload image data to the system using a device such as a smartphone or personal computer. The device sends this image data to the server via the HTTP / HTTPS protocol. The server receives the image data and stores it in cloud storage such as Amazon S3.

[0750] The server is equipped with a generative AI model for analyzing image data. This model uses technologies such as Google Cloud Vision API and Azure Image Analysis to extract text information from images. The generated text information includes location, emotions, events, people, objects, background, etc. Based on this information, the server creates information tags and stores them in a database. The database can use relational databases such as MySQL or PostgreSQL.

[0751] This system also features an emotion engine that analyzes the user's past behavior data and search history. This analysis infers the user's current emotional state and selects the most relevant images for the search query. Based on these optimized search results, the server provides the user with highly relevant image data.

[0752] For example, if a user searches for "happy memories at the beach," the system will prioritize displaying beach photos associated with past emotional data. This search process allows users to instantly rediscover emotionally resonant memories.

[0753] An example of a prompt statement is as follows: "Give the user a photo of a beach and describe the image search process to recreate related, enjoyable memories based on the user's emotions."

[0754] This system allows users to go beyond simple image searches and reconstruct meaningful experiences related to their own emotions.

[0755] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0756] Step 1:

[0757] Users select digital image data from devices such as smartphones and personal computers and upload it to the system. The input is image data stored on the user's device, and the output is the image data sent from the device to the server. This process is carried out using the HTTP / HTTPS protocol and encrypted communication is used to ensure data security.

[0758] Step 2:

[0759] The server processes image data received from the terminal and temporarily stores it in internal storage. The input is uploaded image data, and the output is image data uploaded to a cloud storage service. This process uses storage management software to store data on a cloud platform such as Amazon S3.

[0760] Step 3:

[0761] The server retrieves image data from cloud storage and begins analyzing the images using a generative AI model. The input is image data stored in the cloud, and the output is text information generated by the analysis. This analysis uses the Google Cloud Vision API and Azure Image Analysis to identify objects and context within the image and extract them as text.

[0762] Step 4:

[0763] The server assigns information tags to photos based on the generated text information, corresponding to emotions and events. The input is text information extracted through image analysis, and the output is image data with tags assigned to it. The assigned tags are stored in a database such as MySQL or PostgreSQL to support subsequent search processing.

[0764] Step 5:

[0765] The server uses an emotion engine to analyze the user's past data and infer their current emotional state. The input is the user's past behavior data and search history, and the output is information about the user's emotional state. Based on this inference, the server generates prompt statements relevant to the user's search query and applies the search process.

[0766] Step 6:

[0767] When a user specifies search criteria, the server searches the database and collects relevant image data. The input consists of the user's search query and prompts based on their emotional state, while the output is the retrieved images. The server adjusts the search results to match the user's emotional state and displays them in an appropriate order.

[0768] Step 7:

[0769] The user's device displays search results received from the server on its interface. The input is image data provided by the server as search results, and the output is a visual display through the user interface. The user can view the displayed images and easily recall memories that evoke specific emotions.

[0770] (Application Example 2)

[0771] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0772] The sheer volume of digital image information presents a challenge: it's difficult for users to quickly revisit past memories based on specific emotions or scenes. Furthermore, there's a lack of readily available ways to easily present emotionally relevant memories within the home.

[0773] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0774] In this invention, the server includes means for receiving and storing digital image information; means for analyzing the digital image information and utilizing a generative model to convert its content into natural language; means for assigning labels related to place, emotion, and event based on the natural language and storing them in a storage device; means for searching the storage device in response to a search request from a user and outputting the corresponding digital image information; and means for presenting the outputted digital image information on an external display device and displaying the image information selected based on the user's emotional state. This enables the user to quickly revisit past memories that fit their emotions within their home and obtain an emotionally rich memory experience.

[0775] "Digital image information" refers to visual data files recorded electronically that can be displayed and analyzed by computers and other electronic devices.

[0776] A "generative model" is an artificial intelligence algorithm that has the ability to learn patterns from data and generate new data, and is used for analyzing images and text.

[0777] A "storage device" is hardware or software used to store and manage data, and is responsible for holding digital information.

[0778] An "external display device" is hardware connected to a system to provide digital information to the user visually, and includes monitors and displays.

[0779] "User emotional state" refers to the emotional tendencies and feelings of individual users at a specific time, and is analyzed and inferred by the system.

[0780] A "label" is an information tag assigned to classify or identify data, and is used to describe the characteristics of images or text.

[0781] In the system that implements this application, the server plays a central role. Users upload digital images they have taken from their terminals to the server. To efficiently receive and store large amounts of image information, the server requires a high-speed network interface and large-capacity storage. The server also analyzes the uploaded digital image information using generative models such as TensorFlow. This analysis identifies people, objects, and backgrounds from the images and converts the content into natural language. The converted text data is stored in a database such as MongoDB.

[0782] Furthermore, the server utilizes a Python sentiment analysis library as its sentiment engine to analyze the user's past behavior data and search history to infer their emotional state. This allows for the labeling of images with information about location, emotion, and event. This labeled data is then used to quickly output appropriate digital images based on the user's search query.

[0783] A robot connected to an external display device shows image information provided by a server in a way that is tailored to the user's emotional state. For example, in response to a user request to "show me happy memories of the sea," search results based on past digital image information are displayed. This prompt allows the user to easily revisit emotionally rich memories within the comfort of their own home.

[0784] Example prompt: "Show me some photos of your fun beach memories."

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The system uploads digital images taken by the user from their device to a server. The input consists of multiple digital images taken with the user's device, and the output is an image file stored on the server's storage device. Specifically, the device uploads the files via a high-speed network connection, and the server stores the received files in a large-capacity storage device.

[0788] Step 2:

[0789] The server analyzes received digital images using TensorFlow, a generative AI model. The input is a digital image stored on the server, and the output is natural language text describing the analyzed content. Specifically, it identifies people, objects, and backgrounds from the image and describes them in natural language text.

[0790] Step 3:

[0791] The server assigns labels related to location, sentiment, and events based on the generated natural language text. The input is natural language text, and the output is text data with the label information attached. Specifically, it uses a sentiment engine to analyze the text and automatically assign appropriate labels.

[0792] Step 4:

[0793] The server stores label information in a database such as MongoDB. The input is labeled text data, and the output is the information stored in the database. Specifically, the information is inserted into the database in an appropriate format to enable efficient query searching.

[0794] Step 5:

[0795] The user makes a search request via their terminal. The input is a prompt message containing the user's criteria, and the output is the search result for images that match the criteria. Specifically, when the user enters "Show me pictures of fun beach memories," the server searches the database to identify the relevant image data.

[0796] Step 6:

[0797] The server sends search results to an external display device and displays the most suitable image according to the user's emotional state. The input is the image data of the search results, and the output is the visual displayed on the external display device. Specifically, the selected image is displayed on the screen, allowing the user to access emotionally rich memories.

[0798] 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.

[0799] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0800] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0801] 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.

[0802] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0803] 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.

[0804] 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.

[0805] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0806] 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."

[0807] 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.

[0808] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0809] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0818] 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.

[0819] The following is further disclosed regarding the embodiments described above.

[0820] (Claim 1)

[0821] A means of receiving and storing digital image data,

[0822] A means for analyzing the aforementioned digital image data and utilizing a generative model to convert its content into natural language,

[0823] A means for assigning labels related to place, emotion, and event based on the aforementioned natural language and storing them in a database,

[0824] A means for searching the database in response to a user's search query and outputting the corresponding digital image data,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the generation model analyzes image data to identify people, objects, and backgrounds.

[0828] (Claim 3)

[0829] The system according to claim 1, which presents the search results of the aforementioned digital image data to the user along with the corresponding label and displays related information.

[0830] "Example 1"

[0831] (Claim 1)

[0832] A means for receiving image data and saving it to a remote storage device,

[0833] A means of using a generative model that analyzes the aforementioned image data and converts its contents into language data,

[0834] A means for assigning location information, emotional information, and event-related tags based on the aforementioned language data and storing them in a storage device,

[0835] A means for searching the storage device in response to a search request from a user and outputting the corresponding image data,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, wherein the generation model analyzes image data to identify people, objects, and backgrounds.

[0839] (Claim 3)

[0840] The system according to claim 1, which presents the search results of the aforementioned image data to the user along with the corresponding tags and displays related information.

[0841] "Application Example 1"

[0842] (Claim 1)

[0843] A means of receiving and storing digital image data,

[0844] A means for analyzing the aforementioned digital image data and utilizing a generative model to convert its content into natural language,

[0845] A means for assigning labels related to place, emotion, and event based on the aforementioned natural language and storing them in a database,

[0846] A means for searching the database in response to a user's search query and outputting the corresponding digital image data to a display device,

[0847] A means for receiving voice commands from a physical device and presenting related image data,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, wherein the generative model analyzes image data to identify people, objects, and backgrounds, and extracts corresponding emotions and events.

[0851] (Claim 3)

[0852] The system according to claim 1, which presents the search results of the digital image data to the user along with the corresponding label, and displays related information using audio output or a visual display device.

[0853] "Example 2 of combining an emotion engine"

[0854] (Claim 1)

[0855] A means for receiving image data from a terminal and saving it to a storage device,

[0856] A means of utilizing generation technology that analyzes received image data and converts the information into text,

[0857] A means for assigning information tags related to location information, emotional state, and event information based on the information extracted by the aforementioned generation technology, and storing them on a recording medium,

[0858] A means for searching the recording medium in response to an inquiry from a user and outputting the corresponding image data,

[0859] A means for adjusting the aforementioned search results based on analyzed sentiment information and providing the user with optimal image data,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, wherein the generation technology analyzes image data to identify a human figure, an object, and background information.

[0863] (Claim 3)

[0864] The system according to claim 1, which presents the search results of the aforementioned image data to the user along with the corresponding information tags and displays related information.

[0865] "Application example 2 when combining with an emotional engine"

[0866] (Claim 1)

[0867] A means for receiving and storing digital image information,

[0868] A means of utilizing a generative model that analyzes the aforementioned digital image information and converts its content into natural language,

[0869] A means for assigning labels related to place, emotion, and event based on the aforementioned natural language and storing them in a memory device,

[0870] A means for searching the storage device in response to a search request from a user and outputting the corresponding digital image information,

[0871] A means for displaying the outputted digital image information on an external display device and displaying image information selected based on the user's emotional state,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, wherein the generation model analyzes image information to identify people, objects, and backgrounds.

[0875] (Claim 3)

[0876] The system according to claim 1, which presents the search results of the aforementioned digital image information to the user along with the corresponding label, displays related information, and further includes an external device installed in the home that has the role of presenting memory information according to the user's emotions. [Explanation of symbols]

[0877] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving and storing digital image data, A means for analyzing the aforementioned digital image data and utilizing a generative model to convert its content into natural language, A means for assigning labels related to place, emotion, and event based on the aforementioned natural language and storing them in a database, A means for searching the database in response to a user's search query and outputting the corresponding digital image data, A system that includes this.

2. The system according to claim 1, wherein the generation model analyzes image data to identify people, objects, and backgrounds.

3. The system according to claim 1, which presents the search results of the aforementioned digital image data to the user along with the corresponding label and displays related information.

Images