system

Abstract

We provide the system. [Solution] A means for aggregating information data acquired by the imaging device, The means for analyzing the aforementioned information data and extracting time information, location information, and object identification information, A means for classifying the information data on an event basis based on the extracted information, A means of automatically recognizing and removing duplicate or low-quality information data, A means for notifying the user of the classification results and removal suggestions, and updating the information repository upon the user's approval, Using the analyzed information data, a means to function as a household work device for recording daily activities and events in the home, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern digital devices, especially in imaging devices, a large amount of media data is generated and stored. However, it is difficult to quickly extract necessary information from such huge data or efficiently manage unnecessary data. In such a situation, not only does it compress the storage capacity of the device, but there is also a problem that it takes time and effort for the user to find their own important data. Furthermore, manual management is required for the quality and duplication of media files, so low time efficiency has become an issue.

Means for Solving the Problems

[0005] This invention enables efficient data management by accurately extracting date and time information, geographical information, and object identification information from media data collected by a shooting device using analysis means, thereby achieving situation-based automatic classification. Furthermore, it avoids excessive data storage by automatically identifying duplicate or low-quality media data and notifying the user of deletion suggestions. In addition, it employs means to provide highly accurate classification by integrating speech recognition functionality to perform detailed event identification based on video content analysis. This system provides efficiency and a high level of user experience by uploading data at the optimal timing considering network connectivity.

[0006] A "recording device" is an electronic device used to record images or videos, and includes cameras, smartphones, and other similar devices.

[0007] "Media data" refers to digital content such as photographs and videos recorded by a camera or recording device.

[0008] "Analysis means" refers to a technical device or program used to extract information from a specific dataset and perform classification or identification.

[0009] "Date and time information" refers to the specific date and time when the media data was captured, and is recorded as a timestamp.

[0010] "Geographic information" refers to information that indicates the physical location where media footage was taken, and mainly consists of latitude and longitude data.

[0011] "Object identification information" refers to information used to detect and identify specific objects or people within images or videos.

[0012] "Automatic classification" is a classification process that uses AI or algorithms to sort data into specific categories, without requiring user intervention.

[0013] "Duplicate" refers to a state in which multiple identical or extremely similar media data exist.

[0014] "Low quality" refers to a visually or audibly unsuitable state due to reasons such as image quality being inferior to the standard.

[0015] A "deletion suggestion" is a process that notifies users of recommendations for removing data that is unnecessary or deemed unnecessary.

[0016] "Speech recognition" is a technology that converts speech data into text data and understands information conveyed through speech.

[0017] "Optimal timing" refers to the time when an operation or process is performed most effectively in order to maximize system efficiency and user experience. [Brief explanation of the drawing]

[0018] [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] Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be described.

[0021] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] The system of the present invention consists of a terminal as a shooting device, a server for data processing, and a user who operates it.

[0040] On the device, when a user takes photos or videos, the media data is automatically saved to the device and managed along with basic metadata. This includes initial information such as the date and time of shooting and location information. The device uploads this new media data to the server when a Wi-Fi connection is available or when specified by the user. This upload is performed as a differential synchronization according to pre-configured criteria for efficient data management.

[0041] On the server side, detailed analysis is performed on the received media data using a generative AI model. This model analyzes the content of images and videos and generates advanced metadata based on the information contained within. This metadata includes object identification, person recognition, background processing, and even text conversion of audio data, and is used to classify each media data into a category appropriate to the context.

[0042] Furthermore, the server has a function to automatically identify low-quality images and images that appear to be duplicates, and based on this, it makes specific deletion suggestions to the user. Users receive notifications through the application on their device and can check these classification results and deletion suggestions. By approving the suggestions, the server organizes the media according to the user's instructions and updates the library based on the results.

[0043] For example, if a user takes many photos and videos while traveling, the device sends them to the server. The server analyzes the data and categorizes it into "travel" categories based on the travel scenes. If the same scenery is photographed multiple times, it identifies it as a duplicate and suggests to the user that they select only one copy. If the user approves this suggestion, the server deletes the unnecessary data and updates the library to store only the necessary data.

[0044] Thus, this system aims to optimize storage and improve the user experience while helping users efficiently manage and search for necessary information from vast amounts of media data.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The device saves photos and videos taken by the user with the camera device to its internal storage. During saving, it retrieves basic metadata such as the date and time of shooting and location information, and adds it to each file.

[0048] Step 2:

[0049] The device sends unuploaded media data to the server when connected to Wi-Fi or when manually instructed by the user. During transmission, it efficiently uploads only the data that has been added or updated since the last synchronization, based on the differences detected.

[0050] Step 3:

[0051] When the server receives media data uploaded from a terminal, it immediately adds it to the analysis queue. As the data becomes ready for analysis, it begins content analysis of images and videos using a generative AI model.

[0052] Step 4:

[0053] The server extracts information about objects, people, and backgrounds from media data through analysis, and generates detailed metadata based on this information. Identification tags are assigned to images, and audio data from videos is converted to text using speech recognition.

[0054] Step 5:

[0055] The server automatically classifies each media data item based on the generated metadata, using the event or theme as a basis. The classified categories are diverse, such as "travel," "family," and "events."

[0056] Step 6:

[0057] The server identifies duplicate images and blurry, low-quality images detected during analysis and lists them as suitable candidates for deletion. While deletion suggestions are automatically generated, the final decision rests with the user.

[0058] Step 7:

[0059] Users are notified of classification results and deletion suggestions from the server through an application on their device. Users can review these suggestions and choose which media to delete or keep.

[0060] Step 8:

[0061] Upon receiving user instructions, the server classifies and deletes the specified media data and updates the library. As a result, the update information is synchronized on the terminal and reflected in the user's library.

[0062] This series of processes allows users to manage their media data efficiently and smartly.

[0063] (Example 1)

[0064] 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."

[0065] Modern information devices generate vast amounts of visual data, yet users lack adequate means to efficiently manage and store this data. This leads to problems such as data duplication, degraded quality, wasted storage capacity, and difficulty in quickly retrieving necessary information. Furthermore, the lack of sufficient mechanisms for thoroughly understanding and utilizing the information within visual data hinders its effective use.

[0066] 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.

[0067] In this invention, the server includes means for collecting visual data captured by a camera, means for analyzing the visual data to extract time information, location information, and object identification information, and means for highly analyzing the content of the visual data using a generative AI model to generate detailed metadata. This enables efficient management and processing of visual data, automates data duplication and classification, and allows users to efficiently search and utilize information.

[0068] "Photography equipment" refers to devices used to acquire visual data such as images and videos, and includes cameras, smartphones, and other similar devices.

[0069] "Visual data" refers to information expressed in image or video format, such as photographs and videos.

[0070] A "generative AI model" is a model that uses artificial intelligence technology to analyze the characteristics of data and generate advanced metadata.

[0071] "Time information" refers to information about the specific date and time when the visual data was acquired.

[0072] "Location information" refers to information about the geographical location from which visual data was acquired, and includes GPS data, among others.

[0073] "Object identification information" refers to information used to identify individual objects contained within visual data, such as landmarks and product names.

[0074] "Detailed metadata" refers to information about content and attributes that goes beyond ordinary metadata, obtained from visual data using generative AI models or similar methods.

[0075] "Users" refer to individuals who operate the system and manage and search for visual data.

[0076] An "information processing device" refers to a computer system used for data transfer, analysis, and storage.

[0077] This system consists of a terminal as an imaging device, a server for data analysis, and a user to operate them. A specific embodiment is shown below.

[0078] Users capture visual data using their devices. These devices include cameras and smartphones, all equipped with a camera function. The captured visual data is automatically saved on the device and managed along with metadata such as time and location information. Additionally, users can manually upload data from their devices to the server using synchronization settings as needed.

[0079] When the server receives visual data uploaded from a terminal, it performs advanced analysis using a generative AI model. This generative AI model may include image recognition technology (e.g., TENSORFLOW® object detection model) or speech analysis technology (e.g., natural language processing model). Using these technologies, the server analyzes object identification information and speech data within the visual data and generates detailed metadata based on the obtained information. The server then uses this metadata to classify the data into different categories based on the events that occurred.

[0080] Furthermore, the server evaluates the quality of the visual data and automatically identifies duplicate and low-quality data. Based on this identification, the server suggests deleting unnecessary data and notifies the user. Users can receive notifications through the application on their terminal and review the deletion suggestions and classification results. If the user approves the suggestion, the server deletes the specified visual data and updates the information management system.

[0081] As a concrete example, consider a scenario where a user takes numerous photos and videos during a trip. This data is transferred from the device to a server, which analyzes the travel scenes and categorizes them under "travel." If similar scenes are photographed multiple times, the server identifies them as duplicates and suggests to the user that only one copy be kept. If the user approves this suggestion, the server deletes the unnecessary data and optimizes the library.

[0082] An example of a prompt message is: "Analyze the newly synchronized media data, classify it based on landmarks and events, and suggest removing low-quality or duplicate images."

[0083] Thus, the present invention aims to enable efficient management of visual data, optimize storage, and improve the user experience.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The user captures visual data using the device. The input is image and video data acquired through the camera, and the output is visual data stored in the device's storage. Metadata such as the date and time of capture and location information are automatically added during this process.

[0087] Step 2:

[0088] The device uploads stored visual data to the server when a Wi-Fi connection becomes available or when explicitly instructed by the user. The input is the set of visual data stored on the device, and the output is this data sent to the server. In this process, only newly added or updated data is efficiently transferred based on a differential synchronization algorithm.

[0089] Step 3:

[0090] The server analyzes the received visual data using a generation AI model. The input is the visual data uploaded to the server, and the output is advanced metadata generated by the analysis. Specifically, the server uses image recognition technology to identify objects in the image and, if audio data is included, converts it into text.

[0091] Step 4:

[0092] The server classifies visual data based on the generated metadata. The input is analytical data containing advanced metadata, and the output is data classified based on events and scenes. Based on the results of the generating AI model, categories such as "travel" or "event" are assigned.

[0093] Step 5:

[0094] The server evaluates the quality of visual data and identifies duplicate and low-quality data. Input is parsed metadata and visual data, and output is a list of deletion suggestions. Specifically, quality is evaluated based on image resolution, noise level, and similarity groups of photographs.

[0095] Step 6:

[0096] The server notifies the user of deletion suggestions and data classification results. Inputs are the deletion suggestion list and classification results, while output is the notification to the user. Users can view this information through their terminal application.

[0097] Step 7:

[0098] The user reviews the deletion proposal from the server and chooses to approve or reject it. The input is the notification and proposal from the server, and the output is the instruction selected by the user. The specific operation is easily managed through the user interface.

[0099] Step 8:

[0100] The server, upon user approval, deletes the specified visual data and updates the information management system. The input is user instructions, and the output is the updated library of visual data. This eliminates duplicate and low-quality data and optimizes storage.

[0101] (Application Example 1)

[0102] 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."

[0103] In recent years, a vast amount of information data, including daily life and special events within the home, has been generated, making it difficult to effectively collect and organize it. Furthermore, the accumulation of low-quality and duplicate information data leads to wasted storage capacity and hinders efficient data management by users. There is a need for efficient and reliable management and preservation of family memories.

[0104] 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.

[0105] In this invention, the server includes means for aggregating information data acquired by a camera; means for analyzing the information data to extract time information, location information, and object identification information; means for classifying the information data on an event basis based on the extracted information; means for automatically recognizing and suggesting the removal of duplicate or low-quality information data; and means for functioning as a household work device that records daily activities and events in the home using the analyzed information data. This makes it possible to efficiently record important events in the home and automate the organization of duplicate and low-quality information.

[0106] A "shooting device" is a device used to acquire and store information data, and is equipped with sensors to capture images and videos.

[0107] "Information data" refers to digital data such as images, videos, and audio obtained by a recording device, which records individual events and situations.

[0108] "Aggregating" refers to the process of organizing multiple pieces of information and data into a single coherent unit for efficient management.

[0109] "Analyzing" refers to the process of thoroughly examining obtained information data, extracting its constituent elements and characteristics, and understanding them.

[0110] "Time information" refers to information about the date and time when the data was acquired, and is used for later reference and classification.

[0111] "Location information" refers to information that indicates the geographical location from which data was acquired, and may include map data and GPS data.

[0112] "Object identification information" refers to digital information used to identify objects contained within information data, and it is possible to identify the type and attributes of the object.

[0113] "Classifying based on events" means organizing information data according to its content and the events that occurred, and then assigning it to specific categories.

[0114] "Automatically recognizing and removing suggestions" refers to a system that uses machine learning and AI technology to detect duplicate or low-quality information data and then suggests ways to reduce it to the user.

[0115] "Functioning as a household work device" means a device that supports the user's activities within the home and has functions for recording and organizing tasks.

[0116] This system efficiently records and organizes daily activities and events using information data acquired within the home. In this system, a consumer robot records the user's daily routine and transmits the data to a server.

[0117] First, a consumer robot, acting as the terminal, uses its built-in camera and voice recognition system to capture and record events within the home. The robot's voice recognition function allows it to identify relevant events from the audio data within the video. This process utilizes a combination of Python and OpenCV to acquire data in real time. The information data collected by the robot simultaneously records metadata such as date, time, and location.

[0118] Next, the robot uploads data to the server via Wi-Fi at the optimal time. This communication is optimized based on the network connection status. The server uses a generative AI model to analyze the uploaded information data, understand its content, and extract object identification information. During this process, duplicate information and low-quality data are automatically identified, and suggestions for deletion are made.

[0119] The server uses the analysis results to classify information data by event and sends organizational suggestions to the user. The user can review the suggestions via the robot's display, and after approval, the data library is updated. This entire process makes it easier for the user to manage vast amounts of data, ensuring that important daily events are saved and optimizing storage.

[0120] As a concrete example, in a scenario where a user is hosting a family birthday party, the robot takes photos and videos, records audio, and provides a prompt to the AI ​​model saying, "This data is from a family birthday event. Identify important moments and organize the redundant data." Following this prompt, the data is organized on the server and saved in the optimal format.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] The terminal (a consumer robot) activates its camera and audio sensor to capture and record events within the home. This input acquires image and audio data. The data is processed in real time, and necessary metadata (date, time, location) is added. Next, image processing is performed using OpenCV to check basic image quality and detect anomalies.

[0124] Step 2:

[0125] The device sends the acquired data to a server connected via the network. Communication takes place at the optimal timing depending on the network connection status, and data uploads are performed while checking the Wi-Fi status. During this process, temporary data held locally is transferred.

[0126] Step 3:

[0127] The server receives the transmitted data and performs content analysis using a generative AI model. Object identification information is extracted from image data, and audio data is converted to text using speech recognition. Through this process, the data is organized by event. As a result of this analysis, useful metadata is generated from the data, and duplicate or low-quality data is identified as needed.

[0128] Step 4:

[0129] The server uses the generated metadata to produce data organization suggestions. This involves suggesting the removal of duplicate data while also performing data classification based on specific events. This results in the creation of datasets associated with each event.

[0130] Step 5:

[0131] Organization suggestions are sent from the server to the terminal and notified to the user. The user can view the suggestions through the interface of the home robot. The user's choice to approve or reject the suggestions is logged, and the final decision is recorded in the database.

[0132] Step 6:

[0133] Upon user approval, the server updates the library. Based on the approved suggestions, unnecessary data is deleted, and only necessary data is organized and stored. This efficiently stores important events within the home and optimizes data management.

[0134] 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.

[0135] This invention relates to a system consisting of a terminal equipped with a shooting device, a server that performs data analysis and emotion recognition, and a user who utilizes this system, and aims to efficiently manage vast amounts of media data.

[0136] When a user takes photos or videos, the device saves them to its internal storage. Simultaneously, basic metadata such as the date and time of capture and geographical information is added to the files. The device also uploads new or updated media data to the server at the appropriate time.

[0137] After receiving uploaded media data, the server uses a generative AI model to perform analysis. This analysis extracts and recognizes objects, people, background information, and audio data contained in the media files, and then classifies the media data based on events and scenes. Furthermore, it is equipped with an emotion engine that identifies the emotions of the user and subjects from the analyzed media data. This emotion data enables custom classification according to emotion categories such as smiles, surprise, and sadness.

[0138] The server automatically identifies low-quality or duplicate media and suggests their deletion. These suggestions are notified to the user via their device, who then reviews them through the application. Emotion-based classification detects and tags emotions contained in photos and videos, allowing for the creation of themed albums such as "Happy Memories" or "Touching Moments." Once the user approves the deletion suggestion or emotion classification, the server automatically updates the library, improving the efficiency of data management.

[0139] As a concrete example, consider a scenario where a user takes numerous photos during a family trip. The device sends these photos to a server, which not only categorizes them as travel photos but also tags photos with smiles as "happy memories." Duplicate images are suggested to the user as candidates for deletion, and the management process is completed once the user approves. In this way, the system aims to enable media management tailored to the user's emotional state and provide a more intuitive memory management experience.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] Users take photos and videos using the device's camera. The captured media data is immediately saved to the device's internal storage, and basic metadata such as the date and time of capture and location information is added at the same time.

[0143] Step 2:

[0144] The device uploads media data to the server based on its Wi-Fi connection status and user settings. During the upload process, efficiency is ensured by extracting newly added data since the last synchronization and sending only the differences.

[0145] Step 3:

[0146] Upon receiving media data from a terminal, the server immediately places it into the analysis queue. At this point, the generative AI model begins analyzing the content of the images and videos.

[0147] Step 4:

[0148] The server generates detailed metadata based on the object, person, background information, and audio data obtained through analysis. This data is then used to classify media data according to the corresponding event or scene.

[0149] Step 5:

[0150] The server uses an emotion engine to analyze facial expressions in images and audio tones in videos, detecting emotional states such as smiles, surprise, and sadness. Based on this, it assigns emotion categories and automatically generates albums based on emotional themes.

[0151] Step 6:

[0152] The server lists media data that it determines to be low quality or duplicate based on the analysis results, and generates suggestions for their deletion. These suggestions are sent to the user's terminal for review.

[0153] Step 7:

[0154] Users can review the suggestions and classifications displayed on their device and choose to approve deletion or retain some data as needed. They can also refer to album structures based on sentiment classifications.

[0155] Step 8:

[0156] Based on user requests, the server updates the media library. Unnecessary media is deleted, and organization based on the user's desired categories and sentiment themes is applied. The device receives the server updates to keep its local library up to date.

[0157] This series of processes allows the system to efficiently manage the user's media data and achieve intuitive data organization that takes emotions into consideration.

[0158] (Example 2)

[0159] 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".

[0160] In modern times, the amount of digital information captured by cameras has increased dramatically, and consequently, there is a need to efficiently manage this vast amount of information. Furthermore, users want to organize digital information from a wider range of perspectives, not just simple date and location information, and access it quickly as needed. Therefore, there is a demand for efficient management systems that organize digital information from perspectives such as emotion and redundancy, eliminating waste.

[0161] 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.

[0162] In this invention, the server includes means for collecting digital information captured by a camera; means for analyzing the digital information to extract time information, location information, and object identification information; means for determining emotional information from the digital information using emotion recognition technology and assigning emotion-based classification tags; means for automatically identifying and deleting duplicate or low-quality digital information; and means for notifying the user of the classification results, emotion-based classification tags, and deletion suggestions, and updating the database upon user approval. This makes it possible to manage digital information efficiently and intuitively, and to reduce the burden on the user.

[0163] "Photography equipment" refers to devices used to acquire digital information, such as cameras and video cameras.

[0164] "Digital information" refers to information including images and videos acquired by a camera, as well as the associated metadata.

[0165] "Analysis" refers to a series of processes that involve processing data contained in digital information to extract and classify specific information.

[0166] "Time information" refers to data about the date and time on which digital information is recorded.

[0167] "Location information" refers to data relating to the geographical location from which digital information is acquired.

[0168] "Object identification information" refers to data used to recognize objects and people contained within digital information and to identify their characteristics.

[0169] "Emotion recognition technology" refers to technology that analyzes visual information obtained from images and videos and estimates the emotions expressed therein.

[0170] "Emotion-based classification tags" refer to classification labels assigned to digital information based on emotions identified by emotion recognition technology.

[0171] "Duplicate" refers to the existence of multiple pieces of digital information that have similar or identical content.

[0172] "Low quality" refers to a state where digital information does not meet the required standards, such as lacking clarity or resolution.

[0173] A "deletion suggestion" refers to a notification or suggestion that encourages users to delete digital information deemed unnecessary or redundant.

[0174] "Users" refers to the people who operate and use the system.

[0175] "Notification" refers to an action taken to convey specific information or suggestions to users.

[0176] A "database" refers to an information system used to store and manage digital information in a structured format.

[0177] This invention provides a system for efficiently managing digital information captured by a user using a camera. This system consists of three components: a terminal, a server, and a user.

[0178] A terminal is a device used to acquire digital information, such as a smartphone or a digital camera. When a user takes a picture using a terminal, that digital information is stored on the terminal. Metadata such as the date and time of shooting and location information is automatically added during storage.

[0179] When the device detects a network connection, it uploads digital information to the server. To ensure data security, the upload is encrypted using the SSL / TLS protocol. By performing uploads at the optimal time, communication capacity can be used efficiently.

[0180] The server receives digital information using a high-performance processing unit and analyzes it. This analysis utilizes generative AI models such as TensorFlow to identify people, objects, and backgrounds within the digital information. Furthermore, emotion recognition technology is used to determine emotions from the analyzed digital information and assign emotion-based classification tags.

[0181] As a concrete example, consider a scenario where a user takes many photos during a family trip. The device sends this information to a server, which tags the smiles in the photos as "happy memories" and generates an album. Automatic classification based on emotion recognition helps efficiently organize the large amount of digital information that users take on a daily basis.

[0182] An example of a prompt would be, "Analyze the photos taken during your family trip and tag the ones with smiles." Using this prompt, the generative AI model can perform specific analyses.

[0183] This system aims to enable users to manage digital information intuitively and efficiently, making it easier to organize and access information.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The device activates the camera when the user presses the shutter button and acquires digital information. The captured image or video serves as input, and the device saves it to its internal storage. During saving, metadata such as the date and time of capture and location information is added to the data, resulting in a digital information file with metadata. Specific examples of this operation include recording location information using a GPS sensor.

[0187] Step 2:

[0188] The device detects the network connection status and uploads new or updated digital information to the server. Here, a digital information file with metadata is used as input. To ensure data security, the data is encrypted using the SSL / TLS protocol, and the encrypted data is sent to the server as output. Specifically, the upload begins immediately after Wi-Fi connection is detected.

[0189] Step 3:

[0190] The server analyzes the received digital information. The input is encrypted data, which is first decrypted. Based on the decrypted data, image recognition is performed using a generative AI model such as TensorFlow, and data calculations are performed to identify people, objects, and backgrounds within the image. The output is analyzed object information. Specifically, this includes the AI ​​model performing face recognition within the photograph.

[0191] Step 4:

[0192] The server applies emotion recognition technology based on the analysis results to identify emotions from digital information. In this process, the analyzed object information is used as input, and the emotion recognition engine performs data processing to identify emotions such as joy and sadness. As output, an emotion-based classification tag is generated. A concrete example of this operation is tagging "happy memories" based on the detection of smiles.

[0193] Step 5:

[0194] The server performs a quality assessment of digital information and automatically detects duplicate or low-quality data. In this step, the analyzed digital information file is used as input, a similar image search algorithm is used for quality assessment, and a list of deletion suggestions is generated as output. Specific actions include listing and presenting redundant data.

[0195] Step 6:

[0196] The server notifies the user of a list of suggested deletions and a classification result based on sentiment. This notification provides the user with the suggested deletions and classification result as input, allowing them to review, approve, or reject them through the application. As output, the data approved by the user is recorded in the database. A concrete example of this operation is when a user receives a notification, approves the deletion, and the library is updated.

[0197] (Application Example 2)

[0198] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0199] In managing vast amounts of digital data, users demand systems that efficiently classify and organize data, and allow for intuitive tagging based on emotional information. In particular, the ability to classify data according to emotions is essential for managing personal and family memories in a more valuable way.

[0200] 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.

[0201] In this invention, the server includes means for collecting digital data captured by a camera, means for analyzing the digital data to extract date and time information, location information, and object identification information, and means for identifying emotional information from the analyzed digital data, classifying it by emotion, and tagging it. This enables efficient classification of digital data and intuitive memory management based on emotions.

[0202] A "photography device" is a device used to acquire digital data such as images and videos.

[0203] "Digital data" refers to information in media format, such as photographs and videos, acquired by a camera or other imaging device.

[0204] "Analysis" is the process of extracting and evaluating useful information from digital data.

[0205] "Date and time information" refers to the specific date and time when the media data was acquired.

[0206] "Location information" refers to information about the specific geographical location from which the media data was acquired.

[0207] "Object identification information" refers to information used to identify subjects or objects contained within media data.

[0208] "Emotional information" refers to information that indicates the emotional state of the subject being photographed, as reflected in the digital data.

[0209] "Classification" is the process of grouping digital data that share common characteristics.

[0210] "Tagging" is the process of adding relevant information to digital data, making it easier to find that data intuitively.

[0211] This application example uses a consumer robot operating in a home environment. The robot captures everyday events and activities through its built-in camera and temporarily stores the digital data in its internal storage. The accumulated digital data is automatically transferred to a cloud server using the robot's communication module when a stable network connection is established.

[0212] The server uses TensorFlow, running on Amazon Web Services (AWS®), to perform image analysis in order to analyze the received digital data. The analysis process extracts date and time information, location information, and object identification information from the digital data. Next, it uses an emotion recognition engine called the Happiness Engine to detect emotional information from the facial expressions of people in the image.

[0213] Based on emotional information, the server classifies digital data by emotional theme and adds relevant tags. Duplicate and low-quality digital data are automatically identified, and suggestions for deletion are made. Once the user confirms the deletion suggestion, the server updates the library.

[0214] As a concrete example, imagine a robot taking photos of a family having a weekend barbecue, and the data being analyzed on a cloud server. If the analysis reveals a high number of photos tagged with "smiles," those photos will be grouped into an album titled "Fun Barbecue." On the other hand, if blurry photos are detected during processing, the user will be offered a suggestion to delete them.

[0215] An example of a prompt for the generating AI model would be, "Analyze the family's emotions from the photos and categorize the highlights of specific events with emotion tags." This enables intuitive data management and album creation that aligns with the user's emotions.

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The robotic terminal captures activities and events within the home. The captured digital data is saved to its built-in storage each time. The input data consists of images and videos, and the output is a media file containing both.

[0219] Step 2:

[0220] The device prepares to send the stored digital data to the cloud server. It checks for a stable network connection and sends the data at the optimal time. The input data consists of media files on the device, while the output is transferred to the cloud server.

[0221] Step 3:

[0222] The server analyzes the received digital data. This analysis uses a generative AI model based on TensorFlow to extract date / time information, location information, and object identification information. The input data consists of media files stored on the server, and the output is metadata for these files.

[0223] Step 4:

[0224] The server uses the Happiness Engine to recognize emotional information from people's facial expressions within media data. The input is image data, and the output is emotional tags such as smiles and surprises.

[0225] Step 5:

[0226] The server classifies and tags digital data by emotional theme based on metadata and emotional information obtained through analysis. The input is the data obtained in the previous step, and the output is a tagged digital library classified by emotion and event.

[0227] Step 6:

[0228] The server automatically identifies duplicate and low-quality digital data and generates suggestions for their deletion. The input data consists of all media files, and the output is a list of deletion candidates.

[0229] Step 7:

[0230] The user receives notifications from the server via their device and reviews deletion suggestions and classification results. Based on this, the user makes a final approval for deletion. The input is the notification from the server, and the output is the user's approval.

[0231] Step 8:

[0232] The server updates the library based on user approval, completing emotionally-driven, intuitively themed albums. The input is user approval, and the output is the updated digital library.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] [Second Embodiment]

[0237] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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".

[0249] The system of the present invention consists of a terminal as a shooting device, a server for data processing, and a user who operates it.

[0250] On the device, when a user takes photos or videos, the media data is automatically saved to the device and managed along with basic metadata. This includes initial information such as the date and time of shooting and location information. The device uploads this new media data to the server when a Wi-Fi connection is available or when specified by the user. This upload is performed as a differential synchronization according to pre-configured criteria for efficient data management.

[0251] On the server side, detailed analysis is performed on the received media data using a generative AI model. This model analyzes the content of images and videos and generates advanced metadata based on the information contained within. This metadata includes object identification, person recognition, background processing, and even text conversion of audio data, and is used to classify each media data into a category appropriate to the context.

[0252] Furthermore, the server has a function to automatically identify low-quality images and images that appear to be duplicates, and based on this, it makes specific deletion suggestions to the user. Users receive notifications through the application on their device and can check these classification results and deletion suggestions. By approving the suggestions, the server organizes the media according to the user's instructions and updates the library based on the results.

[0253] For example, if a user takes many photos and videos while traveling, the device sends them to the server. The server analyzes the data and categorizes it into "travel" categories based on the travel scenes. If the same scenery is photographed multiple times, it identifies it as a duplicate and suggests to the user that they select only one copy. If the user approves this suggestion, the server deletes the unnecessary data and updates the library to store only the necessary data.

[0254] Thus, this system aims to optimize storage and improve the user experience while helping users efficiently manage and search for necessary information from vast amounts of media data.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The device saves photos and videos taken by the user with the camera device to its internal storage. During saving, it retrieves basic metadata such as the date and time of shooting and location information, and adds it to each file.

[0258] Step 2:

[0259] The device sends unuploaded media data to the server when connected to Wi-Fi or when manually instructed by the user. During transmission, it efficiently uploads only the data that has been added or updated since the last synchronization, based on the differences detected.

[0260] Step 3:

[0261] When the server receives media data uploaded from a terminal, it immediately adds it to the analysis queue. As the data becomes ready for analysis, it begins content analysis of images and videos using a generative AI model.

[0262] Step 4:

[0263] The server extracts information about objects, people, and backgrounds from media data through analysis, and generates detailed metadata based on this information. Identification tags are assigned to images, and audio data from videos is converted to text using speech recognition.

[0264] Step 5:

[0265] The server automatically classifies each media data item based on the generated metadata, using the event or theme as a basis. The classified categories are diverse, such as "travel," "family," and "events."

[0266] Step 6:

[0267] The server identifies duplicate images and blurry, low-quality images detected during analysis and lists them as suitable candidates for deletion. While deletion suggestions are automatically generated, the final decision rests with the user.

[0268] Step 7:

[0269] Users are notified of classification results and deletion suggestions from the server through an application on their device. Users can review these suggestions and choose which media to delete or keep.

[0270] Step 8:

[0271] Upon receiving user instructions, the server classifies and deletes the specified media data and updates the library. As a result, the update information is synchronized on the terminal and reflected in the user's library.

[0272] This series of processes allows users to manage their media data efficiently and smartly.

[0273] (Example 1)

[0274] 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."

[0275] Modern information devices generate vast amounts of visual data, yet users lack adequate means to efficiently manage and store this data. This leads to problems such as data duplication, degraded quality, wasted storage capacity, and difficulty in quickly retrieving necessary information. Furthermore, the lack of sufficient mechanisms for thoroughly understanding and utilizing the information within visual data hinders its effective use.

[0276] 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.

[0277] In this invention, the server includes means for collecting visual data captured by imaging devices, means for analyzing the visual data to extract time information, location information, and object identification information, and means for highly analyzing the content of the visual data using a generation AI model to generate detailed meta-information. As a result, efficient management and processing of visual data become possible, duplicate removal and classification of data are automated, and users can efficiently search for and utilize information.

[0278] An "imaging device" is a device for acquiring visual data such as images and videos, and includes cameras, smartphones, and the like.

[0279] "Visual data" refers to information expressed in image format or video format, such as photos and videos.

[0280] A "generation AI model" is a model for analyzing data features using artificial intelligence technology to generate advanced metadata.

[0281] "Time information" refers to information regarding the specific date and time when visual data was acquired.

[0282] "Location information" refers to information regarding the geographical location where visual data was acquired, and includes GPS data and the like.

[0283] "Object identification information" refers to information for identifying individual objects included in visual data, and includes, for example, landmarks and product names.

[0284] "Detailed meta-information" refers to information regarding detailed content and attributes beyond normal metadata obtained from visual data using a generation AI model or the like.

[0285] A "user" refers to a person who operates the system and manages and searches for visual data.

[0286] The "information processing device" refers to a computer system for transferring, analyzing, storing, etc. data.

[0287] This system consists of a terminal as a photographing device, a server for data analysis, and a user who operates them. Specific embodiments are shown below.

[0288] The user takes visual data using the terminal. The terminal is equipped with a device having a photographing function, and cameras and smartphones correspond to this. The photographed visual data is automatically stored in the terminal and managed together with metadata such as time information and position information. Further, if necessary, the user manually uses the synchronization setting to upload the data in the terminal to the server.

[0289] When the server receives the visual data uploaded from the terminal, it performs advanced analysis using a generation AI model. As the generation AI model, image recognition technology (e.g., object detection model of TensorFlow) and voice analysis technology (e.g., natural language processing model) are used. By using these technologies, the server analyzes the object identification information and voice data in the visual data and generates detailed meta information based on the obtained information. The server uses this to classify the data into different categories based on events.

[0290] Furthermore, the server evaluates the quality of the visual data and automatically identifies duplicate data and low-quality data. By this identification, the server proposes deletion of unnecessary data and notifies the user. The user can receive the notification through the terminal application and check the deletion proposal and classification result. If the user approves the proposal, the server deletes the specified visual data and updates the information management system.

[0291] As a concrete example, consider a scenario where a user takes numerous photos and videos during a trip. This data is transferred from the device to a server, which analyzes the travel scenes and categorizes them under "travel." If similar scenes are photographed multiple times, the server identifies them as duplicates and suggests to the user that only one copy be kept. If the user approves this suggestion, the server deletes the unnecessary data and optimizes the library.

[0292] An example of a prompt message is: "Analyze the newly synchronized media data, classify it based on landmarks and events, and suggest removing low-quality or duplicate images."

[0293] Thus, the present invention aims to enable efficient management of visual data, optimize storage, and improve the user experience.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The user captures visual data using the device. The input is image and video data acquired through the camera, and the output is visual data stored in the device's storage. Metadata such as the date and time of capture and location information are automatically added during this process.

[0297] Step 2:

[0298] The device uploads stored visual data to the server when a Wi-Fi connection becomes available or when explicitly instructed by the user. The input is the set of visual data stored on the device, and the output is this data sent to the server. In this process, only newly added or updated data is efficiently transferred based on a differential synchronization algorithm.

[0299] Step 3:

[0300] The server analyzes the received visual data using a generative AI model. The input is the visual data uploaded to the server, and the output is the advanced metadata generated by the analysis. As a specific operation, the server uses image recognition technology to identify objects in the image and, if voice data is included, converts it into text.

[0301] Step 4:

[0302] The server classifies the visual data based on the generated metadata. The input is the analysis data containing advanced metadata, and the output is the data classified based on events or scenes. Based on the results of the generative AI model, categories such as "travel" or "event" are set.

[0303] Step 5:

[0304] The server evaluates the quality of the visual data and identifies duplicate data and low-quality data. The input is the analyzed metadata and the visual data, and the output is a list of deletion proposals. Specifically, the quality is evaluated based on the resolution of the image, the noise level, and groups of highly similar photos.

[0305] Step 6:

[0306] The server notifies the user of the deletion proposals and the data classification results. The input is the list of deletion proposals and the classification results, and the output is the notification to the user. The user can check this information through the application on the terminal.

[0307] Step 7:

[0308] The user checks the deletion proposals from the server and selects approval or rejection. The input is the notification and proposals from the server, and the output is the instruction selected by the user. As a specific operation, it can be easily operated through the user interface.

[0309] Step 8:

[0310] The server, upon user approval, deletes the specified visual data and updates the information management system. The input is user instructions, and the output is the updated library of visual data. This eliminates duplicate and low-quality data and optimizes storage.

[0311] (Application Example 1)

[0312] 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."

[0313] In recent years, a vast amount of information data, including daily life and special events within the home, has been generated, making it difficult to effectively collect and organize it. Furthermore, the accumulation of low-quality and duplicate information data leads to wasted storage capacity and hinders efficient data management by users. There is a need for efficient and reliable management and preservation of family memories.

[0314] 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.

[0315] In this invention, the server includes means for aggregating information data acquired by a camera; means for analyzing the information data to extract time information, location information, and object identification information; means for classifying the information data on an event basis based on the extracted information; means for automatically recognizing and suggesting the removal of duplicate or low-quality information data; and means for functioning as a household work device that records daily activities and events in the home using the analyzed information data. This makes it possible to efficiently record important events in the home and automate the organization of duplicate and low-quality information.

[0316] A "shooting device" is a device used to acquire and store information data, and is equipped with sensors to capture images and videos.

[0317] "Information data" refers to digital data such as images, videos, and audio obtained by a recording device, which records individual events and situations.

[0318] "Aggregating" refers to the process of organizing multiple pieces of information and data into a single coherent unit for efficient management.

[0319] "Analyzing" refers to the process of thoroughly examining obtained information data, extracting its constituent elements and characteristics, and understanding them.

[0320] "Time information" refers to information about the date and time when the data was acquired, and is used for later reference and classification.

[0321] "Location information" refers to information that indicates the geographical location from which data was acquired, and may include map data and GPS data.

[0322] "Object identification information" refers to digital information used to identify objects contained within information data, and it is possible to identify the type and attributes of the object.

[0323] "Classifying based on events" means organizing information data according to its content and the events that occurred, and then assigning it to specific categories.

[0324] "Automatically recognizing and removing suggestions" refers to a system that uses machine learning and AI technology to detect duplicate or low-quality information data and then suggests ways to reduce it to the user.

[0325] "Functioning as a household work device" means a device that supports the user's activities within the home and has functions for recording and organizing tasks.

[0326] This system efficiently records and organizes daily activities and events using information data acquired within the home. In this system, a consumer robot records the user's daily routine and transmits the data to a server.

[0327] First, a consumer robot, acting as the terminal, uses its built-in camera and voice recognition system to capture and record events within the home. The robot's voice recognition function allows it to identify relevant events from the audio data within the video. This process utilizes a combination of Python and OpenCV to acquire data in real time. The information data collected by the robot simultaneously records metadata such as date, time, and location.

[0328] Next, the robot uploads data to the server via Wi-Fi at the optimal time. This communication is optimized based on the network connection status. The server uses a generative AI model to analyze the uploaded information data, understand its content, and extract object identification information. During this process, duplicate information and low-quality data are automatically identified, and suggestions for deletion are made.

[0329] The server uses the analysis results to classify information data by event and sends organizational suggestions to the user. The user can review the suggestions via the robot's display, and after approval, the data library is updated. This entire process makes it easier for the user to manage vast amounts of data, ensuring that important daily events are saved and optimizing storage.

[0330] As a concrete example, in a scenario where a user is hosting a family birthday party, the robot takes photos and videos, records audio, and provides a prompt to the AI ​​model saying, "This data is from a family birthday event. Identify important moments and organize the redundant data." Following this prompt, the data is organized on the server and saved in the optimal format.

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The terminal (a consumer robot) activates its camera and audio sensor to capture and record events within the home. This input acquires image and audio data. The data is processed in real time, and necessary metadata (date, time, location) is added. Next, image processing is performed using OpenCV to check basic image quality and detect anomalies.

[0334] Step 2:

[0335] The device sends the acquired data to a server connected via the network. Communication takes place at the optimal timing depending on the network connection status, and data uploads are performed while checking the Wi-Fi status. During this process, temporary data held locally is transferred.

[0336] Step 3:

[0337] The server receives the transmitted data and performs content analysis using a generative AI model. Object identification information is extracted from image data, and audio data is converted to text using speech recognition. Through this process, the data is organized by event. As a result of this analysis, useful metadata is generated from the data, and duplicate or low-quality data is identified as needed.

[0338] Step 4:

[0339] The server uses the generated metadata to produce data organization suggestions. This involves suggesting the removal of duplicate data while also performing data classification based on specific events. This results in the creation of datasets associated with each event.

[0340] Step 5:

[0341] Organization suggestions are sent from the server to the terminal and notified to the user. The user can view the suggestions through the interface of the home robot. The user's choice to approve or reject the suggestions is logged, and the final decision is recorded in the database.

[0342] Step 6:

[0343] Upon user approval, the server updates the library. Based on the approved suggestions, unnecessary data is deleted, and only necessary data is organized and stored. This efficiently stores important events within the home and optimizes data management.

[0344] 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.

[0345] This invention relates to a system consisting of a terminal equipped with a shooting device, a server that performs data analysis and emotion recognition, and a user who utilizes this system, and aims to efficiently manage vast amounts of media data.

[0346] When a user takes photos or videos, the device saves them to its internal storage. Simultaneously, basic metadata such as the date and time of capture and geographical information is added to the files. The device also uploads new or updated media data to the server at the appropriate time.

[0347] After receiving uploaded media data, the server uses a generative AI model to perform analysis. This analysis extracts and recognizes objects, people, background information, and audio data contained in the media files, and then classifies the media data based on events and scenes. Furthermore, it is equipped with an emotion engine that identifies the emotions of the user and subjects from the analyzed media data. This emotion data enables custom classification according to emotion categories such as smiles, surprise, and sadness.

[0348] The server automatically identifies low-quality or duplicate media and suggests their deletion. These suggestions are notified to the user via their device, who then reviews them through the application. Emotion-based classification detects and tags emotions contained in photos and videos, allowing for the creation of themed albums such as "Happy Memories" or "Touching Moments." Once the user approves the deletion suggestion or emotion classification, the server automatically updates the library, improving the efficiency of data management.

[0349] As a concrete example, consider a scenario where a user takes numerous photos during a family trip. The device sends these photos to a server, which not only categorizes them as travel photos but also tags photos with smiles as "happy memories." Duplicate images are suggested to the user as candidates for deletion, and the management process is completed once the user approves. In this way, the system aims to enable media management tailored to the user's emotional state and provide a more intuitive memory management experience.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] Users take photos and videos using the device's camera. The captured media data is immediately saved to the device's internal storage, and basic metadata such as the date and time of capture and location information is added at the same time.

[0353] Step 2:

[0354] The device uploads media data to the server based on its Wi-Fi connection status and user settings. During the upload process, efficiency is ensured by extracting newly added data since the last synchronization and sending only the differences.

[0355] Step 3:

[0356] Upon receiving media data from a terminal, the server immediately places it into the analysis queue. At this point, the generative AI model begins analyzing the content of the images and videos.

[0357] Step 4:

[0358] The server generates detailed metadata based on the object, person, background information, and audio data obtained through analysis. This data is then used to classify media data according to the corresponding event or scene.

[0359] Step 5:

[0360] The server uses an emotion engine to analyze facial expressions in images and audio tones in videos, detecting emotional states such as smiles, surprise, and sadness. Based on this, it assigns emotion categories and automatically generates albums based on emotional themes.

[0361] Step 6:

[0362] The server lists media data that it determines to be low quality or duplicate based on the analysis results, and generates suggestions for their deletion. These suggestions are sent to the user's terminal for review.

[0363] Step 7:

[0364] Users can review the suggestions and classifications displayed on their device and choose to approve deletion or retain some data as needed. They can also refer to album structures based on sentiment classifications.

[0365] Step 8:

[0366] Based on user requests, the server updates the media library. Unnecessary media is deleted, and organization based on the user's desired categories and sentiment themes is applied. The device receives the server updates to keep its local library up to date.

[0367] This series of processes allows the system to efficiently manage the user's media data and achieve intuitive data organization that takes emotions into consideration.

[0368] (Example 2)

[0369] 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".

[0370] In modern times, the amount of digital information captured by cameras has increased dramatically, and consequently, there is a need to efficiently manage this vast amount of information. Furthermore, users want to organize digital information from a wider range of perspectives, not just simple date and location information, and access it quickly as needed. Therefore, there is a demand for efficient management systems that organize digital information from perspectives such as emotion and redundancy, eliminating waste.

[0371] 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.

[0372] In this invention, the server includes means for collecting digital information captured by a camera; means for analyzing the digital information to extract time information, location information, and object identification information; means for determining emotional information from the digital information using emotion recognition technology and assigning emotion-based classification tags; means for automatically identifying and deleting duplicate or low-quality digital information; and means for notifying the user of the classification results, emotion-based classification tags, and deletion suggestions, and updating the database upon user approval. This makes it possible to manage digital information efficiently and intuitively, and to reduce the burden on the user.

[0373] "Photography equipment" refers to devices used to acquire digital information, such as cameras and video cameras.

[0374] "Digital information" refers to information including images and videos acquired by a camera, as well as the associated metadata.

[0375] "Analysis" refers to a series of processes that involve processing data contained in digital information to extract and classify specific information.

[0376] "Time information" refers to data about the date and time on which digital information is recorded.

[0377] "Location information" refers to data relating to the geographical location from which digital information is acquired.

[0378] "Object identification information" refers to data used to recognize objects and people contained within digital information and to identify their characteristics.

[0379] "Emotion recognition technology" refers to technology that analyzes visual information obtained from images and videos and estimates the emotions expressed therein.

[0380] "Emotion-based classification tags" refer to classification labels assigned to digital information based on emotions identified by emotion recognition technology.

[0381] "Duplicate" refers to the existence of multiple pieces of digital information that have similar or identical content.

[0382] "Low quality" refers to a state where digital information does not meet the required standards, such as lacking clarity or resolution.

[0383] A "deletion suggestion" refers to a notification or suggestion that encourages users to delete digital information deemed unnecessary or redundant.

[0384] "Users" refers to the people who operate and use the system.

[0385] "Notification" refers to an action taken to convey specific information or suggestions to users.

[0386] A "database" refers to an information system used to store and manage digital information in a structured format.

[0387] This invention provides a system for efficiently managing digital information captured by a user using a camera. This system consists of three components: a terminal, a server, and a user.

[0388] A terminal is a device used to acquire digital information, such as a smartphone or a digital camera. When a user takes a picture using a terminal, that digital information is stored on the terminal. Metadata such as the date and time of shooting and location information is automatically added during storage.

[0389] When the device detects a network connection, it uploads digital information to the server. To ensure data security, the upload is encrypted using the SSL / TLS protocol. By performing uploads at the optimal time, communication capacity can be used efficiently.

[0390] The server receives digital information using a high-performance processing unit and analyzes it. This analysis utilizes generative AI models such as TensorFlow to identify people, objects, and backgrounds within the digital information. Furthermore, emotion recognition technology is used to determine emotions from the analyzed digital information and assign emotion-based classification tags.

[0391] As a concrete example, consider a scenario where a user takes many photos during a family trip. The device sends this information to a server, which tags the smiles in the photos as "happy memories" and generates an album. Automatic classification based on emotion recognition helps efficiently organize the large amount of digital information that users take on a daily basis.

[0392] An example of a prompt would be, "Analyze the photos taken during your family trip and tag the ones with smiles." Using this prompt, the generative AI model can perform specific analyses.

[0393] This system aims to enable users to manage digital information intuitively and efficiently, making it easier to organize and access information.

[0394] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0395] Step 1:

[0396] The device activates the camera when the user presses the shutter button and acquires digital information. The captured image or video serves as input, and the device saves it to its internal storage. During saving, metadata such as the date and time of capture and location information is added to the data, resulting in a digital information file with metadata. Specific examples of this operation include recording location information using a GPS sensor.

[0397] Step 2:

[0398] The device detects the network connection status and uploads new or updated digital information to the server. Here, a digital information file with metadata is used as input. To ensure data security, the data is encrypted using the SSL / TLS protocol, and the encrypted data is sent to the server as output. Specifically, the upload begins immediately after Wi-Fi connection is detected.

[0399] Step 3:

[0400] The server analyzes the received digital information. The input is encrypted data, which is first decrypted. Based on the decrypted data, image recognition is performed using a generative AI model such as TensorFlow, and data calculations are performed to identify people, objects, and backgrounds within the image. The output is analyzed object information. Specifically, this includes the AI ​​model performing face recognition within the photograph.

[0401] Step 4:

[0402] The server applies emotion recognition technology based on the analysis results to identify emotions from digital information. In this process, the analyzed object information is used as input, and the emotion recognition engine performs data processing to identify emotions such as joy and sadness. As output, an emotion-based classification tag is generated. A concrete example of this operation is tagging "happy memories" based on the detection of smiles.

[0403] Step 5:

[0404] The server performs a quality assessment of digital information and automatically detects duplicate or low-quality data. In this step, the analyzed digital information file is used as input, a similar image search algorithm is used for quality assessment, and a list of deletion suggestions is generated as output. Specific actions include listing and presenting redundant data.

[0405] Step 6:

[0406] The server notifies the user of a list of suggested deletions and a classification result based on sentiment. This notification provides the user with the suggested deletions and classification result as input, allowing them to review, approve, or reject them through the application. As output, the data approved by the user is recorded in the database. A concrete example of this operation is when a user receives a notification, approves the deletion, and the library is updated.

[0407] (Application Example 2)

[0408] 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 will be referred to as the "terminal."

[0409] In managing vast amounts of digital data, users demand systems that efficiently classify and organize data, and allow for intuitive tagging based on emotional information. In particular, the ability to classify data according to emotions is essential for managing personal and family memories in a more valuable way.

[0410] 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.

[0411] In this invention, the server includes means for collecting digital data captured by a camera, means for analyzing the digital data to extract date and time information, location information, and object identification information, and means for identifying emotional information from the analyzed digital data, classifying it by emotion, and tagging it. This enables efficient classification of digital data and intuitive memory management based on emotions.

[0412] A "photography device" is a device used to acquire digital data such as images and videos.

[0413] "Digital data" refers to information in media format, such as photographs and videos, acquired by a camera or other imaging device.

[0414] "Analysis" is the process of extracting and evaluating useful information from digital data.

[0415] "Date and time information" refers to the specific date and time when the media data was acquired.

[0416] "Location information" refers to information about the specific geographical location from which the media data was acquired.

[0417] "Object identification information" refers to information used to identify subjects or objects contained within media data.

[0418] "Emotional information" refers to information that indicates the emotional state of the subject being photographed, as reflected in the digital data.

[0419] "Classification" is the process of grouping digital data that share common characteristics.

[0420] "Tagging" is the process of adding relevant information to digital data, making it easier to find that data intuitively.

[0421] This application example uses a consumer robot operating in a home environment. The robot captures everyday events and activities through its built-in camera and temporarily stores the digital data in its internal storage. The accumulated digital data is automatically transferred to a cloud server using the robot's communication module when a stable network connection is established.

[0422] The server uses TensorFlow, running on Amazon Web Services (AWS), to perform image analysis on the received digital data. The analysis process extracts date and time information, location information, and object identification information from the digital data. Next, it uses an emotion recognition engine called the Happiness Engine to detect emotional information from the facial expressions of people in the images.

[0423] Based on emotional information, the server classifies digital data by emotional theme and adds relevant tags. Duplicate and low-quality digital data are automatically identified, and suggestions for deletion are made. Once the user confirms the deletion suggestion, the server updates the library.

[0424] As a concrete example, imagine a robot taking photos of a family having a weekend barbecue, and the data being analyzed on a cloud server. If the analysis reveals a high number of photos tagged with "smiles," those photos will be grouped into an album titled "Fun Barbecue." On the other hand, if blurry photos are detected during processing, the user will be offered a suggestion to delete them.

[0425] An example of a prompt for the generating AI model would be, "Analyze the family's emotions from the photos and categorize the highlights of specific events with emotion tags." This enables intuitive data management and album creation that aligns with the user's emotions.

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The robotic terminal captures activities and events within the home. The captured digital data is saved to its built-in storage each time. The input data consists of images and videos, and the output is a media file containing both.

[0429] Step 2:

[0430] The device prepares to send the stored digital data to the cloud server. It checks for a stable network connection and sends the data at the optimal time. The input data consists of media files on the device, while the output is transferred to the cloud server.

[0431] Step 3:

[0432] The server analyzes the received digital data. This analysis uses a generative AI model based on TensorFlow to extract date / time information, location information, and object identification information. The input data consists of media files stored on the server, and the output is metadata for these files.

[0433] Step 4:

[0434] The server uses the Happiness Engine to recognize emotional information from people's facial expressions within media data. The input is image data, and the output is emotional tags such as smiles and surprises.

[0435] Step 5:

[0436] The server classifies and tags digital data by emotional theme based on metadata and emotional information obtained through analysis. The input is the data obtained in the previous step, and the output is a tagged digital library classified by emotion and event.

[0437] Step 6:

[0438] The server automatically identifies duplicate and low-quality digital data and generates suggestions for their deletion. The input data consists of all media files, and the output is a list of deletion candidates.

[0439] Step 7:

[0440] The user receives notifications from the server via their device and reviews deletion suggestions and classification results. Based on this, the user makes a final approval for deletion. The input is the notification from the server, and the output is the user's approval.

[0441] Step 8:

[0442] The server updates the library based on user approval, completing emotionally-driven, intuitively themed albums. The input is user approval, and the output is the updated digital library.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] [Third Embodiment]

[0447] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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).

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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".

[0459] The system of the present invention consists of a terminal as a shooting device, a server for data processing, and a user who operates it.

[0460] On the device, when a user takes photos or videos, the media data is automatically saved to the device and managed along with basic metadata. This includes initial information such as the date and time of shooting and location information. The device uploads this new media data to the server when a Wi-Fi connection is available or when specified by the user. This upload is performed as a differential synchronization according to pre-configured criteria for efficient data management.

[0461] On the server side, detailed analysis is performed on the received media data using a generative AI model. This model analyzes the content of images and videos and generates advanced metadata based on the information contained within. This metadata includes object identification, person recognition, background processing, and even text conversion of audio data, and is used to classify each media data into a category appropriate to the context.

[0462] Furthermore, the server has a function to automatically identify low-quality images and images that appear to be duplicates, and based on this, it makes specific deletion suggestions to the user. Users receive notifications through the application on their device and can check these classification results and deletion suggestions. By approving the suggestions, the server organizes the media according to the user's instructions and updates the library based on the results.

[0463] For example, if a user takes many photos and videos while traveling, the device sends them to the server. The server analyzes the data and categorizes it into "travel" categories based on the travel scenes. If the same scenery is photographed multiple times, it identifies it as a duplicate and suggests to the user that they select only one copy. If the user approves this suggestion, the server deletes the unnecessary data and updates the library to store only the necessary data.

[0464] Thus, this system aims to optimize storage and improve the user experience while helping users efficiently manage and search for necessary information from vast amounts of media data.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] The device saves photos and videos taken by the user with the camera device to its internal storage. During saving, it retrieves basic metadata such as the date and time of shooting and location information, and adds it to each file.

[0468] Step 2:

[0469] The device sends unuploaded media data to the server when connected to Wi-Fi or when manually instructed by the user. During transmission, it efficiently uploads only the data that has been added or updated since the last synchronization, based on the differences detected.

[0470] Step 3:

[0471] When the server receives media data uploaded from a terminal, it immediately adds it to the analysis queue. As the data becomes ready for analysis, it begins content analysis of images and videos using a generative AI model.

[0472] Step 4:

[0473] The server extracts information about objects, people, and backgrounds from media data through analysis, and generates detailed metadata based on this information. Identification tags are assigned to images, and audio data from videos is converted to text using speech recognition.

[0474] Step 5:

[0475] The server automatically classifies each media data item based on the generated metadata, using the event or theme as a basis. The classified categories are diverse, such as "travel," "family," and "events."

[0476] Step 6:

[0477] The server identifies duplicate images and blurry, low-quality images detected during analysis and lists them as suitable candidates for deletion. While deletion suggestions are automatically generated, the final decision rests with the user.

[0478] Step 7:

[0479] Users are notified of classification results and deletion suggestions from the server through an application on their device. Users can review these suggestions and choose which media to delete or keep.

[0480] Step 8:

[0481] Upon receiving user instructions, the server classifies and deletes the specified media data and updates the library. As a result, the update information is synchronized on the terminal and reflected in the user's library.

[0482] This series of processes allows users to manage their media data efficiently and smartly.

[0483] (Example 1)

[0484] 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."

[0485] Modern information devices generate vast amounts of visual data, yet users lack adequate means to efficiently manage and store this data. This leads to problems such as data duplication, degraded quality, wasted storage capacity, and difficulty in quickly retrieving necessary information. Furthermore, the lack of sufficient mechanisms for thoroughly understanding and utilizing the information within visual data hinders its effective use.

[0486] 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.

[0487] In this invention, the server includes means for collecting visual data captured by a camera, means for analyzing the visual data to extract time information, location information, and object identification information, and means for highly analyzing the content of the visual data using a generative AI model to generate detailed metadata. This enables efficient management and processing of visual data, automates data duplication and classification, and allows users to efficiently search and utilize information.

[0488] "Photography equipment" refers to devices used to acquire visual data such as images and videos, and includes cameras, smartphones, and other similar devices.

[0489] "Visual data" refers to information expressed in image or video format, such as photographs and videos.

[0490] A "generative AI model" is a model that uses artificial intelligence technology to analyze the characteristics of data and generate advanced metadata.

[0491] "Time information" refers to information about the specific date and time when the visual data was acquired.

[0492] "Location information" refers to information about the geographical location from which visual data was acquired, and includes GPS data, among others.

[0493] "Object identification information" refers to information used to identify individual objects contained within visual data, such as landmarks and product names.

[0494] "Detailed metadata" refers to information about content and attributes that goes beyond ordinary metadata, obtained from visual data using generative AI models or similar methods.

[0495] "Users" refer to individuals who operate the system and manage and search for visual data.

[0496] An "information processing device" refers to a computer system used for data transfer, analysis, and storage.

[0497] This system consists of a terminal as an imaging device, a server for data analysis, and a user to operate them. A specific embodiment is shown below.

[0498] Users capture visual data using their devices. These devices include cameras and smartphones, all equipped with a camera function. The captured visual data is automatically saved on the device and managed along with metadata such as time and location information. Additionally, users can manually upload data from their devices to the server using synchronization settings as needed.

[0499] When the server receives visual data uploaded from a terminal, it performs advanced analysis using a generative AI model. This generative AI model may include image recognition technology (e.g., TensorFlow's object detection model) or speech analysis technology (e.g., natural language processing models). Using these technologies, the server analyzes object identification information and speech data within the visual data, generating detailed metadata based on the obtained information. The server then uses this metadata to classify the data into different categories based on the events that occurred.

[0500] Furthermore, the server evaluates the quality of the visual data and automatically identifies duplicate and low-quality data. Based on this identification, the server suggests deleting unnecessary data and notifies the user. Users can receive notifications through the application on their terminal and review the deletion suggestions and classification results. If the user approves the suggestion, the server deletes the specified visual data and updates the information management system.

[0501] As a concrete example, consider a scenario where a user takes numerous photos and videos during a trip. This data is transferred from the device to a server, which analyzes the travel scenes and categorizes them under "travel." If similar scenes are photographed multiple times, the server identifies them as duplicates and suggests to the user that only one copy be kept. If the user approves this suggestion, the server deletes the unnecessary data and optimizes the library.

[0502] An example of a prompt message is: "Analyze the newly synchronized media data, classify it based on landmarks and events, and suggest removing low-quality or duplicate images."

[0503] Thus, the present invention aims to enable efficient management of visual data, optimize storage, and improve the user experience.

[0504] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0505] Step 1:

[0506] The user captures visual data using the device. The input is image and video data acquired through the camera, and the output is visual data stored in the device's storage. Metadata such as the date and time of capture and location information are automatically added during this process.

[0507] Step 2:

[0508] The device uploads stored visual data to the server when a Wi-Fi connection becomes available or when explicitly instructed by the user. The input is the set of visual data stored on the device, and the output is this data sent to the server. In this process, only newly added or updated data is efficiently transferred based on a differential synchronization algorithm.

[0509] Step 3:

[0510] The server analyzes the received visual data using a generation AI model. The input is the visual data uploaded to the server, and the output is advanced metadata generated by the analysis. Specifically, the server uses image recognition technology to identify objects in the image and, if audio data is included, converts it into text.

[0511] Step 4:

[0512] The server classifies visual data based on the generated metadata. The input is analytical data containing advanced metadata, and the output is data classified based on events and scenes. Based on the results of the generating AI model, categories such as "travel" or "event" are assigned.

[0513] Step 5:

[0514] The server evaluates the quality of visual data and identifies duplicate and low-quality data. Input is parsed metadata and visual data, and output is a list of deletion suggestions. Specifically, quality is evaluated based on image resolution, noise level, and similarity groups of photographs.

[0515] Step 6:

[0516] The server notifies the user of deletion suggestions and data classification results. Inputs are the deletion suggestion list and classification results, while output is the notification to the user. Users can view this information through their terminal application.

[0517] Step 7:

[0518] The user reviews the deletion proposal from the server and chooses to approve or reject it. The input is the notification and proposal from the server, and the output is the instruction selected by the user. The specific operation is easily managed through the user interface.

[0519] Step 8:

[0520] The server, upon user approval, deletes the specified visual data and updates the information management system. The input is user instructions, and the output is the updated library of visual data. This eliminates duplicate and low-quality data and optimizes storage.

[0521] (Application Example 1)

[0522] 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."

[0523] In recent years, a vast amount of information data, including daily life and special events within the home, has been generated, making it difficult to effectively collect and organize it. Furthermore, the accumulation of low-quality and duplicate information data leads to wasted storage capacity and hinders efficient data management by users. There is a need for efficient and reliable management and preservation of family memories.

[0524] 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.

[0525] In this invention, the server includes means for aggregating information data acquired by a camera; means for analyzing the information data to extract time information, location information, and object identification information; means for classifying the information data on an event basis based on the extracted information; means for automatically recognizing and suggesting the removal of duplicate or low-quality information data; and means for functioning as a household work device that records daily activities and events in the home using the analyzed information data. This makes it possible to efficiently record important events in the home and automate the organization of duplicate and low-quality information.

[0526] A "shooting device" is a device used to acquire and store information data, and is equipped with sensors to capture images and videos.

[0527] "Information data" refers to digital data such as images, videos, and audio obtained by a recording device, which records individual events and situations.

[0528] "Aggregating" refers to the process of organizing multiple pieces of information and data into a single coherent unit for efficient management.

[0529] "Analyzing" refers to the process of thoroughly examining obtained information data, extracting its constituent elements and characteristics, and understanding them.

[0530] "Time information" refers to information about the date and time when the data was acquired, and is used for later reference and classification.

[0531] "Location information" refers to information that indicates the geographical location from which data was acquired, and may include map data and GPS data.

[0532] "Object identification information" refers to digital information used to identify objects contained within information data, and it is possible to identify the type and attributes of the object.

[0533] "Classifying based on events" means organizing information data according to its content and the events that occurred, and then assigning it to specific categories.

[0534] "Automatically recognizing and removing suggestions" refers to a system that uses machine learning and AI technology to detect duplicate or low-quality information data and then suggests ways to reduce it to the user.

[0535] "Functioning as a household work device" means a device that supports the user's activities within the home and has functions for recording and organizing tasks.

[0536] This system efficiently records and organizes daily activities and events using information data acquired within the home. In this system, a consumer robot records the user's daily routine and transmits the data to a server.

[0537] First, a consumer robot, acting as the terminal, uses its built-in camera and voice recognition system to capture and record events within the home. The robot's voice recognition function allows it to identify relevant events from the audio data within the video. This process utilizes a combination of Python and OpenCV to acquire data in real time. The information data collected by the robot simultaneously records metadata such as date, time, and location.

[0538] Next, the robot uploads data to the server via Wi-Fi at the optimal time. This communication is optimized based on the network connection status. The server uses a generative AI model to analyze the uploaded information data, understand its content, and extract object identification information. During this process, duplicate information and low-quality data are automatically identified, and suggestions for deletion are made.

[0539] The server uses the analysis results to classify information data by event and sends organizational suggestions to the user. The user can review the suggestions via the robot's display, and after approval, the data library is updated. This entire process makes it easier for the user to manage vast amounts of data, ensuring that important daily events are saved and optimizing storage.

[0540] As a concrete example, in a scenario where a user is hosting a family birthday party, the robot takes photos and videos, records audio, and provides a prompt to the AI ​​model saying, "This data is from a family birthday event. Identify important moments and organize the redundant data." Following this prompt, the data is organized on the server and saved in the optimal format.

[0541] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0542] Step 1:

[0543] The terminal (a consumer robot) activates its camera and audio sensor to capture and record events within the home. This input acquires image and audio data. The data is processed in real time, and necessary metadata (date, time, location) is added. Next, image processing is performed using OpenCV to check basic image quality and detect anomalies.

[0544] Step 2:

[0545] The device sends the acquired data to a server connected via the network. Communication takes place at the optimal timing depending on the network connection status, and data uploads are performed while checking the Wi-Fi status. During this process, temporary data held locally is transferred.

[0546] Step 3:

[0547] The server receives the transmitted data and performs content analysis using a generative AI model. Object identification information is extracted from image data, and audio data is converted to text using speech recognition. Through this process, the data is organized by event. As a result of this analysis, useful metadata is generated from the data, and duplicate or low-quality data is identified as needed.

[0548] Step 4:

[0549] The server uses the generated metadata to produce data organization suggestions. This involves suggesting the removal of duplicate data while also performing data classification based on specific events. This results in the creation of datasets associated with each event.

[0550] Step 5:

[0551] Organization suggestions are sent from the server to the terminal and notified to the user. The user can view the suggestions through the interface of the home robot. The user's choice to approve or reject the suggestions is logged, and the final decision is recorded in the database.

[0552] Step 6:

[0553] Upon user approval, the server updates the library. Based on the approved suggestions, unnecessary data is deleted, and only necessary data is organized and stored. This efficiently stores important events within the home and optimizes data management.

[0554] 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.

[0555] This invention relates to a system consisting of a terminal equipped with a shooting device, a server that performs data analysis and emotion recognition, and a user who utilizes this system, and aims to efficiently manage vast amounts of media data.

[0556] When a user takes photos or videos, the device saves them to its internal storage. Simultaneously, basic metadata such as the date and time of capture and geographical information is added to the files. The device also uploads new or updated media data to the server at the appropriate time.

[0557] After receiving uploaded media data, the server uses a generative AI model to perform analysis. This analysis extracts and recognizes objects, people, background information, and audio data contained in the media files, and then classifies the media data based on events and scenes. Furthermore, it is equipped with an emotion engine that identifies the emotions of the user and subjects from the analyzed media data. This emotion data enables custom classification according to emotion categories such as smiles, surprise, and sadness.

[0558] The server automatically identifies low-quality or duplicate media and suggests their deletion. These suggestions are notified to the user via their device, who then reviews them through the application. Emotion-based classification detects and tags emotions contained in photos and videos, allowing for the creation of themed albums such as "Happy Memories" or "Touching Moments." Once the user approves the deletion suggestion or emotion classification, the server automatically updates the library, improving the efficiency of data management.

[0559] As a concrete example, consider a scenario where a user takes numerous photos during a family trip. The device sends these photos to a server, which not only categorizes them as travel photos but also tags photos with smiles as "happy memories." Duplicate images are suggested to the user as candidates for deletion, and the management process is completed once the user approves. In this way, the system aims to enable media management tailored to the user's emotional state and provide a more intuitive memory management experience.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] Users take photos and videos using the device's camera. The captured media data is immediately saved to the device's internal storage, and basic metadata such as the date and time of capture and location information is added at the same time.

[0563] Step 2:

[0564] The device uploads media data to the server based on its Wi-Fi connection status and user settings. During the upload process, efficiency is ensured by extracting newly added data since the last synchronization and sending only the differences.

[0565] Step 3:

[0566] Upon receiving media data from a terminal, the server immediately places it into the analysis queue. At this point, the generative AI model begins analyzing the content of the images and videos.

[0567] Step 4:

[0568] The server generates detailed metadata based on the object, person, background information, and audio data obtained through analysis. This data is then used to classify media data according to the corresponding event or scene.

[0569] Step 5:

[0570] The server uses an emotion engine to analyze facial expressions in images and audio tones in videos, detecting emotional states such as smiles, surprise, and sadness. Based on this, it assigns emotion categories and automatically generates albums based on emotional themes.

[0571] Step 6:

[0572] The server lists media data that it determines to be low quality or duplicate based on the analysis results, and generates suggestions for their deletion. These suggestions are sent to the user's terminal for review.

[0573] Step 7:

[0574] Users can review the suggestions and classifications displayed on their device and choose to approve deletion or retain some data as needed. They can also refer to album structures based on sentiment classifications.

[0575] Step 8:

[0576] Based on user requests, the server updates the media library. Unnecessary media is deleted, and organization based on the user's desired categories and sentiment themes is applied. The device receives the server updates to keep its local library up to date.

[0577] This series of processes allows the system to efficiently manage the user's media data and achieve intuitive data organization that takes emotions into consideration.

[0578] (Example 2)

[0579] 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."

[0580] In modern times, the amount of digital information captured by cameras has increased dramatically, and consequently, there is a need to efficiently manage this vast amount of information. Furthermore, users want to organize digital information from a wider range of perspectives, not just simple date and location information, and access it quickly as needed. Therefore, there is a demand for efficient management systems that organize digital information from perspectives such as emotion and redundancy, eliminating waste.

[0581] 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.

[0582] In this invention, the server includes means for collecting digital information captured by a camera; means for analyzing the digital information to extract time information, location information, and object identification information; means for determining emotional information from the digital information using emotion recognition technology and assigning emotion-based classification tags; means for automatically identifying and deleting duplicate or low-quality digital information; and means for notifying the user of the classification results, emotion-based classification tags, and deletion suggestions, and updating the database upon user approval. This makes it possible to manage digital information efficiently and intuitively, and to reduce the burden on the user.

[0583] "Photography equipment" refers to devices used to acquire digital information, such as cameras and video cameras.

[0584] "Digital information" refers to information including images and videos acquired by a camera, as well as the associated metadata.

[0585] "Analysis" refers to a series of processes that involve processing data contained in digital information to extract and classify specific information.

[0586] "Time information" refers to data about the date and time on which digital information is recorded.

[0587] "Location information" refers to data relating to the geographical location from which digital information is acquired.

[0588] "Object identification information" refers to data used to recognize objects and people contained within digital information and to identify their characteristics.

[0589] "Emotion recognition technology" refers to technology that analyzes visual information obtained from images and videos and estimates the emotions expressed therein.

[0590] "Emotion-based classification tags" refer to classification labels assigned to digital information based on emotions identified by emotion recognition technology.

[0591] "Duplicate" refers to the existence of multiple pieces of digital information that have similar or identical content.

[0592] "Low quality" refers to a state where digital information does not meet the required standards, such as lacking clarity or resolution.

[0593] A "deletion suggestion" refers to a notification or suggestion that encourages users to delete digital information deemed unnecessary or redundant.

[0594] "Users" refers to the people who operate and use the system.

[0595] "Notification" refers to an action taken to convey specific information or suggestions to users.

[0596] A "database" refers to an information system used to store and manage digital information in a structured format.

[0597] This invention provides a system for efficiently managing digital information captured by a user using a camera. This system consists of three components: a terminal, a server, and a user.

[0598] A terminal is a device used to acquire digital information, such as a smartphone or a digital camera. When a user takes a picture using a terminal, that digital information is stored on the terminal. Metadata such as the date and time of shooting and location information is automatically added during storage.

[0599] When the device detects a network connection, it uploads digital information to the server. To ensure data security, the upload is encrypted using the SSL / TLS protocol. By performing uploads at the optimal time, communication capacity can be used efficiently.

[0600] The server receives digital information using a high-performance processing unit and analyzes it. This analysis utilizes generative AI models such as TensorFlow to identify people, objects, and backgrounds within the digital information. Furthermore, emotion recognition technology is used to determine emotions from the analyzed digital information and assign emotion-based classification tags.

[0601] As a concrete example, consider a scenario where a user takes many photos during a family trip. The device sends this information to a server, which tags the smiles in the photos as "happy memories" and generates an album. Automatic classification based on emotion recognition helps efficiently organize the large amount of digital information that users take on a daily basis.

[0602] An example of a prompt would be, "Analyze the photos taken during your family trip and tag the ones with smiles." Using this prompt, the generative AI model can perform specific analyses.

[0603] This system aims to enable users to manage digital information intuitively and efficiently, making it easier to organize and access information.

[0604] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0605] Step 1:

[0606] The device activates the camera when the user presses the shutter button and acquires digital information. The captured image or video serves as input, and the device saves it to its internal storage. During saving, metadata such as the date and time of capture and location information is added to the data, resulting in a digital information file with metadata. Specific examples of this operation include recording location information using a GPS sensor.

[0607] Step 2:

[0608] The device detects the network connection status and uploads new or updated digital information to the server. Here, a digital information file with metadata is used as input. To ensure data security, the data is encrypted using the SSL / TLS protocol, and the encrypted data is sent to the server as output. Specifically, the upload begins immediately after Wi-Fi connection is detected.

[0609] Step 3:

[0610] The server analyzes the received digital information. The input is encrypted data, which is first decrypted. Based on the decrypted data, image recognition is performed using a generative AI model such as TensorFlow, and data calculations are performed to identify people, objects, and backgrounds within the image. The output is analyzed object information. Specifically, this includes the AI ​​model performing face recognition within the photograph.

[0611] Step 4:

[0612] The server applies emotion recognition technology based on the analysis results to identify emotions from digital information. In this process, the analyzed object information is used as input, and the emotion recognition engine performs data processing to identify emotions such as joy and sadness. As output, an emotion-based classification tag is generated. A concrete example of this operation is tagging "happy memories" based on the detection of smiles.

[0613] Step 5:

[0614] The server performs a quality assessment of digital information and automatically detects duplicate or low-quality data. In this step, the analyzed digital information file is used as input, a similar image search algorithm is used for quality assessment, and a list of deletion suggestions is generated as output. Specific actions include listing and presenting redundant data.

[0615] Step 6:

[0616] The server notifies the user of a list of suggested deletions and a classification result based on sentiment. This notification provides the user with the suggested deletions and classification result as input, allowing them to review, approve, or reject them through the application. As output, the data approved by the user is recorded in the database. A concrete example of this operation is when a user receives a notification, approves the deletion, and the library is updated.

[0617] (Application Example 2)

[0618] 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."

[0619] In managing vast amounts of digital data, users demand systems that efficiently classify and organize data, and allow for intuitive tagging based on emotional information. In particular, the ability to classify data according to emotions is essential for managing personal and family memories in a more valuable way.

[0620] 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.

[0621] In this invention, the server includes means for collecting digital data captured by a camera, means for analyzing the digital data to extract date and time information, location information, and object identification information, and means for identifying emotional information from the analyzed digital data, classifying it by emotion, and tagging it. This enables efficient classification of digital data and intuitive memory management based on emotions.

[0622] A "photography device" is a device used to acquire digital data such as images and videos.

[0623] "Digital data" refers to information in media format, such as photographs and videos, acquired by a camera or other imaging device.

[0624] "Analysis" is the process of extracting and evaluating useful information from digital data.

[0625] "Date and time information" refers to the specific date and time when the media data was acquired.

[0626] "Location information" refers to information about the specific geographical location from which the media data was acquired.

[0627] "Object identification information" refers to information used to identify subjects or objects contained within media data.

[0628] "Emotional information" refers to information that indicates the emotional state of the subject being photographed, as reflected in the digital data.

[0629] "Classification" is the process of grouping digital data that share common characteristics.

[0630] "Tagging" is the process of adding relevant information to digital data, making it easier to find that data intuitively.

[0631] This application example uses a consumer robot operating in a home environment. The robot captures everyday events and activities through its built-in camera and temporarily stores the digital data in its internal storage. The accumulated digital data is automatically transferred to a cloud server using the robot's communication module when a stable network connection is established.

[0632] The server uses TensorFlow, running on Amazon Web Services (AWS), to perform image analysis on the received digital data. The analysis process extracts date and time information, location information, and object identification information from the digital data. Next, it uses an emotion recognition engine called the Happiness Engine to detect emotional information from the facial expressions of people in the images.

[0633] Based on emotional information, the server classifies digital data by emotional theme and adds relevant tags. Duplicate and low-quality digital data are automatically identified, and suggestions for deletion are made. Once the user confirms the deletion suggestion, the server updates the library.

[0634] As a concrete example, imagine a robot taking photos of a family having a weekend barbecue, and the data being analyzed on a cloud server. If the analysis reveals a high number of photos tagged with "smiles," those photos will be grouped into an album titled "Fun Barbecue." On the other hand, if blurry photos are detected during processing, the user will be offered a suggestion to delete them.

[0635] An example of a prompt for the generating AI model would be, "Analyze the family's emotions from the photos and categorize the highlights of specific events with emotion tags." This enables intuitive data management and album creation that aligns with the user's emotions.

[0636] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0637] Step 1:

[0638] The robotic terminal captures activities and events within the home. The captured digital data is saved to its built-in storage each time. The input data consists of images and videos, and the output is a media file containing both.

[0639] Step 2:

[0640] The device prepares to send the stored digital data to the cloud server. It checks for a stable network connection and sends the data at the optimal time. The input data consists of media files on the device, while the output is transferred to the cloud server.

[0641] Step 3:

[0642] The server analyzes the received digital data. This analysis uses a generative AI model based on TensorFlow to extract date / time information, location information, and object identification information. The input data consists of media files stored on the server, and the output is metadata for these files.

[0643] Step 4:

[0644] The server uses the Happiness Engine to recognize emotional information from people's facial expressions within media data. The input is image data, and the output is emotional tags such as smiles and surprises.

[0645] Step 5:

[0646] The server classifies and tags digital data by emotional theme based on metadata and emotional information obtained through analysis. The input is the data obtained in the previous step, and the output is a tagged digital library classified by emotion and event.

[0647] Step 6:

[0648] The server automatically identifies duplicate and low-quality digital data and generates suggestions for their deletion. The input data consists of all media files, and the output is a list of deletion candidates.

[0649] Step 7:

[0650] The user receives notifications from the server via their device and reviews deletion suggestions and classification results. Based on this, the user makes a final approval for deletion. The input is the notification from the server, and the output is the user's approval.

[0651] Step 8:

[0652] The server updates the library based on user approval, completing emotionally-driven, intuitively themed albums. The input is user approval, and the output is the updated digital library.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] [Fourth Embodiment]

[0657] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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).

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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".

[0670] The system of the present invention consists of a terminal as a shooting device, a server for data processing, and a user who operates it.

[0671] On the device, when a user takes photos or videos, the media data is automatically saved to the device and managed along with basic metadata. This includes initial information such as the date and time of shooting and location information. The device uploads this new media data to the server when a Wi-Fi connection is available or when specified by the user. This upload is performed as a differential synchronization according to pre-configured criteria for efficient data management.

[0672] On the server side, detailed analysis is performed on the received media data using a generative AI model. This model analyzes the content of images and videos and generates advanced metadata based on the information contained within. This metadata includes object identification, person recognition, background processing, and even text conversion of audio data, and is used to classify each media data into a category appropriate to the context.

[0673] Furthermore, the server has a function to automatically identify low-quality images and images that appear to be duplicates, and based on this, it makes specific deletion suggestions to the user. Users receive notifications through the application on their device and can check these classification results and deletion suggestions. By approving the suggestions, the server organizes the media according to the user's instructions and updates the library based on the results.

[0674] For example, if a user takes many photos and videos while traveling, the device sends them to the server. The server analyzes the data and categorizes it into "travel" categories based on the travel scenes. If the same scenery is photographed multiple times, it identifies it as a duplicate and suggests to the user that they select only one copy. If the user approves this suggestion, the server deletes the unnecessary data and updates the library to store only the necessary data.

[0675] Thus, this system aims to optimize storage and improve the user experience while helping users efficiently manage and search for necessary information from vast amounts of media data.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The device saves photos and videos taken by the user with the camera device to its internal storage. During saving, it retrieves basic metadata such as the date and time of shooting and location information, and adds it to each file.

[0679] Step 2:

[0680] The device sends unuploaded media data to the server when connected to Wi-Fi or when manually instructed by the user. During transmission, it efficiently uploads only the data that has been added or updated since the last synchronization, based on the differences detected.

[0681] Step 3:

[0682] When the server receives media data uploaded from a terminal, it immediately adds it to the analysis queue. As the data becomes ready for analysis, it begins content analysis of images and videos using a generative AI model.

[0683] Step 4:

[0684] The server extracts information about objects, people, and backgrounds from media data through analysis, and generates detailed metadata based on this information. Identification tags are assigned to images, and audio data from videos is converted to text using speech recognition.

[0685] Step 5:

[0686] The server automatically classifies each media data item based on the generated metadata, using the event or theme as a basis. The classified categories are diverse, such as "travel," "family," and "events."

[0687] Step 6:

[0688] The server identifies duplicate images and blurry, low-quality images detected during analysis and lists them as suitable candidates for deletion. While deletion suggestions are automatically generated, the final decision rests with the user.

[0689] Step 7:

[0690] Users are notified of classification results and deletion suggestions from the server through an application on their device. Users can review these suggestions and choose which media to delete or keep.

[0691] Step 8:

[0692] Upon receiving user instructions, the server classifies and deletes the specified media data and updates the library. As a result, the update information is synchronized on the terminal and reflected in the user's library.

[0693] This series of processes allows users to manage their media data efficiently and smartly.

[0694] (Example 1)

[0695] 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".

[0696] Modern information devices generate vast amounts of visual data, yet users lack adequate means to efficiently manage and store this data. This leads to problems such as data duplication, degraded quality, wasted storage capacity, and difficulty in quickly retrieving necessary information. Furthermore, the lack of sufficient mechanisms for thoroughly understanding and utilizing the information within visual data hinders its effective use.

[0697] 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.

[0698] In this invention, the server includes means for collecting visual data captured by a camera, means for analyzing the visual data to extract time information, location information, and object identification information, and means for highly analyzing the content of the visual data using a generative AI model to generate detailed metadata. This enables efficient management and processing of visual data, automates data duplication and classification, and allows users to efficiently search and utilize information.

[0699] "Photography equipment" refers to devices used to acquire visual data such as images and videos, and includes cameras, smartphones, and other similar devices.

[0700] "Visual data" refers to information expressed in image or video format, such as photographs and videos.

[0701] A "generative AI model" is a model that uses artificial intelligence technology to analyze the characteristics of data and generate advanced metadata.

[0702] "Time information" refers to information about the specific date and time when the visual data was acquired.

[0703] "Location information" refers to information about the geographical location from which visual data was acquired, and includes GPS data, among others.

[0704] "Object identification information" refers to information used to identify individual objects contained within visual data, such as landmarks and product names.

[0705] "Detailed metadata" refers to information about content and attributes that goes beyond ordinary metadata, obtained from visual data using generative AI models or similar methods.

[0706] "Users" refer to individuals who operate the system and manage and search for visual data.

[0707] An "information processing device" refers to a computer system used for data transfer, analysis, and storage.

[0708] This system consists of a terminal as an imaging device, a server for data analysis, and a user to operate them. A specific embodiment is shown below.

[0709] Users capture visual data using their devices. These devices include cameras and smartphones, all equipped with a camera function. The captured visual data is automatically saved on the device and managed along with metadata such as time and location information. Additionally, users can manually upload data from their devices to the server using synchronization settings as needed.

[0710] When the server receives visual data uploaded from a terminal, it performs advanced analysis using a generative AI model. This generative AI model may include image recognition technology (e.g., TensorFlow's object detection model) or speech analysis technology (e.g., natural language processing models). Using these technologies, the server analyzes object identification information and speech data within the visual data, generating detailed metadata based on the obtained information. The server then uses this metadata to classify the data into different categories based on the events that occurred.

[0711] Furthermore, the server evaluates the quality of the visual data and automatically identifies duplicate and low-quality data. Based on this identification, the server suggests deleting unnecessary data and notifies the user. Users can receive notifications through the application on their terminal and review the deletion suggestions and classification results. If the user approves the suggestion, the server deletes the specified visual data and updates the information management system.

[0712] As a concrete example, consider a scenario where a user takes numerous photos and videos during a trip. This data is transferred from the device to a server, which analyzes the travel scenes and categorizes them under "travel." If similar scenes are photographed multiple times, the server identifies them as duplicates and suggests to the user that only one copy be kept. If the user approves this suggestion, the server deletes the unnecessary data and optimizes the library.

[0713] An example of a prompt message is: "Analyze the newly synchronized media data, classify it based on landmarks and events, and suggest removing low-quality or duplicate images."

[0714] Thus, the present invention aims to enable efficient management of visual data, optimize storage, and improve the user experience.

[0715] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0716] Step 1:

[0717] The user captures visual data using the device. The input is image and video data acquired through the camera, and the output is visual data stored in the device's storage. Metadata such as the date and time of capture and location information are automatically added during this process.

[0718] Step 2:

[0719] The device uploads stored visual data to the server when a Wi-Fi connection becomes available or when explicitly instructed by the user. The input is the set of visual data stored on the device, and the output is this data sent to the server. In this process, only newly added or updated data is efficiently transferred based on a differential synchronization algorithm.

[0720] Step 3:

[0721] The server analyzes the received visual data using a generation AI model. The input is the visual data uploaded to the server, and the output is advanced metadata generated by the analysis. Specifically, the server uses image recognition technology to identify objects in the image and, if audio data is included, converts it into text.

[0722] Step 4:

[0723] The server classifies visual data based on the generated metadata. The input is analytical data containing advanced metadata, and the output is data classified based on events and scenes. Based on the results of the generating AI model, categories such as "travel" or "event" are assigned.

[0724] Step 5:

[0725] The server evaluates the quality of visual data and identifies duplicate and low-quality data. Input is parsed metadata and visual data, and output is a list of deletion suggestions. Specifically, quality is evaluated based on image resolution, noise level, and similarity groups of photographs.

[0726] Step 6:

[0727] The server notifies the user of deletion suggestions and data classification results. Inputs are the deletion suggestion list and classification results, while output is the notification to the user. Users can view this information through their terminal application.

[0728] Step 7:

[0729] The user reviews the deletion proposal from the server and chooses to approve or reject it. The input is the notification and proposal from the server, and the output is the instruction selected by the user. The specific operation is easily managed through the user interface.

[0730] Step 8:

[0731] The server, upon user approval, deletes the specified visual data and updates the information management system. The input is user instructions, and the output is the updated library of visual data. This eliminates duplicate and low-quality data and optimizes storage.

[0732] (Application Example 1)

[0733] 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".

[0734] In recent years, a vast amount of information data, including daily life and special events within the home, has been generated, making it difficult to effectively collect and organize it. Furthermore, the accumulation of low-quality and duplicate information data leads to wasted storage capacity and hinders efficient data management by users. There is a need for efficient and reliable management and preservation of family memories.

[0735] 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.

[0736] In this invention, the server includes means for aggregating information data acquired by a camera; means for analyzing the information data to extract time information, location information, and object identification information; means for classifying the information data on an event basis based on the extracted information; means for automatically recognizing and suggesting the removal of duplicate or low-quality information data; and means for functioning as a household work device that records daily activities and events in the home using the analyzed information data. This makes it possible to efficiently record important events in the home and automate the organization of duplicate and low-quality information.

[0737] A "shooting device" is a device used to acquire and store information data, and is equipped with sensors to capture images and videos.

[0738] "Information data" refers to digital data such as images, videos, and audio obtained by a recording device, which records individual events and situations.

[0739] "Aggregating" refers to the process of organizing multiple pieces of information and data into a single coherent unit for efficient management.

[0740] "Analyzing" refers to the process of thoroughly examining obtained information data, extracting its constituent elements and characteristics, and understanding them.

[0741] "Time information" refers to information about the date and time when the data was acquired, and is used for later reference and classification.

[0742] "Location information" refers to information that indicates the geographical location from which data was acquired, and may include map data and GPS data.

[0743] "Object identification information" refers to digital information used to identify objects contained within information data, and it is possible to identify the type and attributes of the object.

[0744] "Classifying based on events" means organizing information data according to its content and the events that occurred, and then assigning it to specific categories.

[0745] "Automatically recognizing and removing suggestions" refers to a system that uses machine learning and AI technology to detect duplicate or low-quality information data and then suggests ways to reduce it to the user.

[0746] "Functioning as a household work device" means a device that supports the user's activities within the home and has functions for recording and organizing tasks.

[0747] This system efficiently records and organizes daily activities and events using information data acquired within the home. In this system, a consumer robot records the user's daily routine and transmits the data to a server.

[0748] First, a consumer robot, acting as the terminal, uses its built-in camera and voice recognition system to capture and record events within the home. The robot's voice recognition function allows it to identify relevant events from the audio data within the video. This process utilizes a combination of Python and OpenCV to acquire data in real time. The information data collected by the robot simultaneously records metadata such as date, time, and location.

[0749] Next, the robot uploads data to the server via Wi-Fi at the optimal time. This communication is optimized based on the network connection status. The server uses a generative AI model to analyze the uploaded information data, understand its content, and extract object identification information. During this process, duplicate information and low-quality data are automatically identified, and suggestions for deletion are made.

[0750] The server uses the analysis results to classify information data by event and sends organizational suggestions to the user. The user can review the suggestions via the robot's display, and after approval, the data library is updated. This entire process makes it easier for the user to manage vast amounts of data, ensuring that important daily events are saved and optimizing storage.

[0751] As a concrete example, in a scenario where a user is hosting a family birthday party, the robot takes photos and videos, records audio, and provides a prompt to the AI ​​model saying, "This data is from a family birthday event. Identify important moments and organize the redundant data." Following this prompt, the data is organized on the server and saved in the optimal format.

[0752] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0753] Step 1:

[0754] The terminal (a consumer robot) activates its camera and audio sensor to capture and record events within the home. This input acquires image and audio data. The data is processed in real time, and necessary metadata (date, time, location) is added. Next, image processing is performed using OpenCV to check basic image quality and detect anomalies.

[0755] Step 2:

[0756] The device sends the acquired data to a server connected via the network. Communication takes place at the optimal timing depending on the network connection status, and data uploads are performed while checking the Wi-Fi status. During this process, temporary data held locally is transferred.

[0757] Step 3:

[0758] The server receives the transmitted data and performs content analysis using a generative AI model. Object identification information is extracted from image data, and audio data is converted to text using speech recognition. Through this process, the data is organized by event. As a result of this analysis, useful metadata is generated from the data, and duplicate or low-quality data is identified as needed.

[0759] Step 4:

[0760] The server uses the generated metadata to produce data organization suggestions. This involves suggesting the removal of duplicate data while also performing data classification based on specific events. This results in the creation of datasets associated with each event.

[0761] Step 5:

[0762] Organization suggestions are sent from the server to the terminal and notified to the user. The user can view the suggestions through the interface of the home robot. The user's choice to approve or reject the suggestions is logged, and the final decision is recorded in the database.

[0763] Step 6:

[0764] Upon user approval, the server updates the library. Based on the approved suggestions, unnecessary data is deleted, and only necessary data is organized and stored. This efficiently stores important events within the home and optimizes data management.

[0765] 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.

[0766] This invention relates to a system consisting of a terminal equipped with a shooting device, a server that performs data analysis and emotion recognition, and a user who utilizes this system, and aims to efficiently manage vast amounts of media data.

[0767] When a user takes photos or videos, the device saves them to its internal storage. Simultaneously, basic metadata such as the date and time of capture and geographical information is added to the files. The device also uploads new or updated media data to the server at the appropriate time.

[0768] After receiving uploaded media data, the server uses a generative AI model to perform analysis. This analysis extracts and recognizes objects, people, background information, and audio data contained in the media files, and then classifies the media data based on events and scenes. Furthermore, it is equipped with an emotion engine that identifies the emotions of the user and subjects from the analyzed media data. This emotion data enables custom classification according to emotion categories such as smiles, surprise, and sadness.

[0769] The server automatically identifies low-quality or duplicate media and suggests their deletion. These suggestions are notified to the user via their device, who then reviews them through the application. Emotion-based classification detects and tags emotions contained in photos and videos, allowing for the creation of themed albums such as "Happy Memories" or "Touching Moments." Once the user approves the deletion suggestion or emotion classification, the server automatically updates the library, improving the efficiency of data management.

[0770] As a concrete example, consider a scenario where a user takes numerous photos during a family trip. The device sends these photos to a server, which not only categorizes them as travel photos but also tags photos with smiles as "happy memories." Duplicate images are suggested to the user as candidates for deletion, and the management process is completed once the user approves. In this way, the system aims to enable media management tailored to the user's emotional state and provide a more intuitive memory management experience.

[0771] The following describes the processing flow.

[0772] Step 1:

[0773] Users take photos and videos using the device's camera. The captured media data is immediately saved to the device's internal storage, and basic metadata such as the date and time of capture and location information is added at the same time.

[0774] Step 2:

[0775] The device uploads media data to the server based on its Wi-Fi connection status and user settings. During the upload process, efficiency is ensured by extracting newly added data since the last synchronization and sending only the differences.

[0776] Step 3:

[0777] Upon receiving media data from a terminal, the server immediately places it into the analysis queue. At this point, the generative AI model begins analyzing the content of the images and videos.

[0778] Step 4:

[0779] The server generates detailed metadata based on the object, person, background information, and audio data obtained through analysis. This data is then used to classify media data according to the corresponding event or scene.

[0780] Step 5:

[0781] The server uses an emotion engine to analyze facial expressions in images and audio tones in videos, detecting emotional states such as smiles, surprise, and sadness. Based on this, it assigns emotion categories and automatically generates albums based on emotional themes.

[0782] Step 6:

[0783] The server lists media data that it determines to be low quality or duplicate based on the analysis results, and generates suggestions for their deletion. These suggestions are sent to the user's terminal for review.

[0784] Step 7:

[0785] Users can review the suggestions and classifications displayed on their device and choose to approve deletion or retain some data as needed. They can also refer to album structures based on sentiment classifications.

[0786] Step 8:

[0787] Based on user requests, the server updates the media library. Unnecessary media is deleted, and organization based on the user's desired categories and sentiment themes is applied. The device receives the server updates to keep its local library up to date.

[0788] This series of processes allows the system to efficiently manage the user's media data and achieve intuitive data organization that takes emotions into consideration.

[0789] (Example 2)

[0790] 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".

[0791] In modern times, the amount of digital information captured by cameras has increased dramatically, and consequently, there is a need to efficiently manage this vast amount of information. Furthermore, users want to organize digital information from a wider range of perspectives, not just simple date and location information, and access it quickly as needed. Therefore, there is a demand for efficient management systems that organize digital information from perspectives such as emotion and redundancy, eliminating waste.

[0792] 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.

[0793] In this invention, the server includes means for collecting digital information captured by a camera; means for analyzing the digital information to extract time information, location information, and object identification information; means for determining emotional information from the digital information using emotion recognition technology and assigning emotion-based classification tags; means for automatically identifying and deleting duplicate or low-quality digital information; and means for notifying the user of the classification results, emotion-based classification tags, and deletion suggestions, and updating the database upon user approval. This makes it possible to manage digital information efficiently and intuitively, and to reduce the burden on the user.

[0794] "Photography equipment" refers to devices used to acquire digital information, such as cameras and video cameras.

[0795] "Digital information" refers to information including images and videos acquired by a camera, as well as the associated metadata.

[0796] "Analysis" refers to a series of processes that involve processing data contained in digital information to extract and classify specific information.

[0797] "Time information" refers to data about the date and time on which digital information is recorded.

[0798] "Location information" refers to data relating to the geographical location from which digital information is acquired.

[0799] "Object identification information" refers to data used to recognize objects and people contained within digital information and to identify their characteristics.

[0800] "Emotion recognition technology" refers to technology that analyzes visual information obtained from images and videos and estimates the emotions expressed therein.

[0801] "Emotion-based classification tags" refer to classification labels assigned to digital information based on emotions identified by emotion recognition technology.

[0802] "Duplicate" refers to the existence of multiple pieces of digital information that have similar or identical content.

[0803] "Low quality" refers to a state where digital information does not meet the required standards, such as lacking clarity or resolution.

[0804] A "deletion suggestion" refers to a notification or suggestion that encourages users to delete digital information deemed unnecessary or redundant.

[0805] "Users" refers to the people who operate and use the system.

[0806] "Notification" refers to an action taken to convey specific information or suggestions to users.

[0807] A "database" refers to an information system used to store and manage digital information in a structured format.

[0808] This invention provides a system for efficiently managing digital information captured by a user using a camera. This system consists of three components: a terminal, a server, and a user.

[0809] A terminal is a device used to acquire digital information, such as a smartphone or a digital camera. When a user takes a picture using a terminal, that digital information is stored on the terminal. Metadata such as the date and time of shooting and location information is automatically added during storage.

[0810] When the device detects a network connection, it uploads digital information to the server. To ensure data security, the upload is encrypted using the SSL / TLS protocol. By performing uploads at the optimal time, communication capacity can be used efficiently.

[0811] The server receives digital information using a high-performance processing unit and analyzes it. This analysis utilizes generative AI models such as TensorFlow to identify people, objects, and backgrounds within the digital information. Furthermore, emotion recognition technology is used to determine emotions from the analyzed digital information and assign emotion-based classification tags.

[0812] As a concrete example, consider a scenario where a user takes many photos during a family trip. The device sends this information to a server, which tags the smiles in the photos as "happy memories" and generates an album. Automatic classification based on emotion recognition helps efficiently organize the large amount of digital information that users take on a daily basis.

[0813] An example of a prompt would be, "Analyze the photos taken during your family trip and tag the ones with smiles." Using this prompt, the generative AI model can perform specific analyses.

[0814] This system aims to enable users to manage digital information intuitively and efficiently, making it easier to organize and access information.

[0815] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0816] Step 1:

[0817] The device activates the camera when the user presses the shutter button and acquires digital information. The captured image or video serves as input, and the device saves it to its internal storage. During saving, metadata such as the date and time of capture and location information is added to the data, resulting in a digital information file with metadata. Specific examples of this operation include recording location information using a GPS sensor.

[0818] Step 2:

[0819] The device detects the network connection status and uploads new or updated digital information to the server. Here, a digital information file with metadata is used as input. To ensure data security, the data is encrypted using the SSL / TLS protocol, and the encrypted data is sent to the server as output. Specifically, the upload begins immediately after Wi-Fi connection is detected.

[0820] Step 3:

[0821] The server analyzes the received digital information. The input is encrypted data, which is first decrypted. Based on the decrypted data, image recognition is performed using a generative AI model such as TensorFlow, and data calculations are performed to identify people, objects, and backgrounds within the image. The output is analyzed object information. Specifically, this includes the AI ​​model performing face recognition within the photograph.

[0822] Step 4:

[0823] The server applies emotion recognition technology based on the analysis results to identify emotions from digital information. In this process, the analyzed object information is used as input, and the emotion recognition engine performs data processing to identify emotions such as joy and sadness. As output, an emotion-based classification tag is generated. A concrete example of this operation is tagging "happy memories" based on the detection of smiles.

[0824] Step 5:

[0825] The server performs a quality assessment of digital information and automatically detects duplicate or low-quality data. In this step, the analyzed digital information file is used as input, a similar image search algorithm is used for quality assessment, and a list of deletion suggestions is generated as output. Specific actions include listing and presenting redundant data.

[0826] Step 6:

[0827] The server notifies the user of a list of suggested deletions and a classification result based on sentiment. This notification provides the user with the suggested deletions and classification result as input, allowing them to review, approve, or reject them through the application. As output, the data approved by the user is recorded in the database. A concrete example of this operation is when a user receives a notification, approves the deletion, and the library is updated.

[0828] (Application Example 2)

[0829] 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".

[0830] In managing vast amounts of digital data, users demand systems that efficiently classify and organize data, and allow for intuitive tagging based on emotional information. In particular, the ability to classify data according to emotions is essential for managing personal and family memories in a more valuable way.

[0831] 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.

[0832] In this invention, the server includes means for collecting digital data captured by a camera, means for analyzing the digital data to extract date and time information, location information, and object identification information, and means for identifying emotional information from the analyzed digital data, classifying it by emotion, and tagging it. This enables efficient classification of digital data and intuitive memory management based on emotions.

[0833] A "photography device" is a device used to acquire digital data such as images and videos.

[0834] "Digital data" refers to information in media format, such as photographs and videos, acquired by a camera or other imaging device.

[0835] "Analysis" is the process of extracting and evaluating useful information from digital data.

[0836] "Date and time information" refers to the specific date and time when the media data was acquired.

[0837] "Location information" refers to information about the specific geographical location from which the media data was acquired.

[0838] "Object identification information" refers to information used to identify subjects or objects contained within media data.

[0839] "Emotional information" refers to information that indicates the emotional state of the subject being photographed, as reflected in the digital data.

[0840] "Classification" is the process of grouping digital data that share common characteristics.

[0841] "Tagging" is the process of adding relevant information to digital data, making it easier to find that data intuitively.

[0842] This application example uses a consumer robot operating in a home environment. The robot captures everyday events and activities through its built-in camera and temporarily stores the digital data in its internal storage. The accumulated digital data is automatically transferred to a cloud server using the robot's communication module when a stable network connection is established.

[0843] The server uses TensorFlow, running on Amazon Web Services (AWS), to perform image analysis on the received digital data. The analysis process extracts date and time information, location information, and object identification information from the digital data. Next, it uses an emotion recognition engine called the Happiness Engine to detect emotional information from the facial expressions of people in the images.

[0844] Based on emotional information, the server classifies digital data by emotional theme and adds relevant tags. Duplicate and low-quality digital data are automatically identified, and suggestions for deletion are made. Once the user confirms the deletion suggestion, the server updates the library.

[0845] As a concrete example, imagine a robot taking photos of a family having a weekend barbecue, and the data being analyzed on a cloud server. If the analysis reveals a high number of photos tagged with "smiles," those photos will be grouped into an album titled "Fun Barbecue." On the other hand, if blurry photos are detected during processing, the user will be offered a suggestion to delete them.

[0846] An example of a prompt for the generating AI model would be, "Analyze the family's emotions from the photos and categorize the highlights of specific events with emotion tags." This enables intuitive data management and album creation that aligns with the user's emotions.

[0847] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0848] Step 1:

[0849] The robotic terminal captures activities and events within the home. The captured digital data is saved to its built-in storage each time. The input data consists of images and videos, and the output is a media file containing both.

[0850] Step 2:

[0851] The device prepares to send the stored digital data to the cloud server. It checks for a stable network connection and sends the data at the optimal time. The input data consists of media files on the device, while the output is transferred to the cloud server.

[0852] Step 3:

[0853] The server analyzes the received digital data. This analysis uses a generative AI model based on TensorFlow to extract date / time information, location information, and object identification information. The input data consists of media files stored on the server, and the output is metadata for these files.

[0854] Step 4:

[0855] The server uses the Happiness Engine to recognize emotional information from people's facial expressions within media data. The input is image data, and the output is emotional tags such as smiles and surprises.

[0856] Step 5:

[0857] The server classifies and tags digital data by emotional theme based on metadata and emotional information obtained through analysis. The input is the data obtained in the previous step, and the output is a tagged digital library classified by emotion and event.

[0858] Step 6:

[0859] The server automatically identifies duplicate and low-quality digital data and generates suggestions for their deletion. The input data consists of all media files, and the output is a list of deletion candidates.

[0860] Step 7:

[0861] The user receives notifications from the server via their device and reviews deletion suggestions and classification results. Based on this, the user makes a final approval for deletion. The input is the notification from the server, and the output is the user's approval.

[0862] Step 8:

[0863] The server updates the library based on user approval, completing emotionally-driven, intuitively themed albums. The input is user approval, and the output is the updated digital library.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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."

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] The following is further disclosed regarding the embodiments described above.

[0886] (Claim 1)

[0887] A means of collecting media data captured by a shooting device,

[0888] A means for analyzing the aforementioned media data to extract date and time information, geographical information, and object identification information,

[0889] A means for classifying the media data based on the events, based on the extracted information,

[0890] A means of automatically identifying and suggesting the deletion of duplicate or low-quality media data,

[0891] A means for notifying the user of the classification results and deletion suggestions, and updating the library upon user approval,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, wherein the analysis means analyzes audio data in a video using a speech recognition function and identifies related events.

[0895] (Claim 3)

[0896] The system according to claim 1, wherein the data upload means transmits the data to the server at an optimal timing based on the network connection status.

[0897] "Example 1"

[0898] (Claim 1)

[0899] A means of collecting visual data captured by a camera,

[0900] A means for analyzing the aforementioned visual data to extract time information, location information, and object identification information,

[0901] A means for classifying the visual data based on events, based on the extracted information,

[0902] A means of automatically identifying and suggesting the deletion of duplicate or low-quality visual data,

[0903] A means for highly analyzing the content of visual data using a generative AI model and generating detailed metadata,

[0904] A means for notifying the user of the classification results and deletion proposals, and updating the information management system after obtaining the user's approval,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, wherein the analysis means analyzes audio data in the video using a speech recognition function and identifies related events.

[0908] (Claim 3)

[0909] The system according to claim 1, wherein the data transfer means transmits the data to the information processing device at an optimal timing based on the communication status.

[0910] "Application Example 1"

[0911] (Claim 1)

[0912] A means for aggregating information data acquired by the imaging device,

[0913] The means for analyzing the aforementioned information data and extracting time information, location information, and object identification information,

[0914] A means for classifying the information data on an event basis based on the extracted information,

[0915] A means of automatically recognizing and removing duplicate or low-quality information data,

[0916] A means for notifying the user of the classification results and removal suggestions, and updating the information repository upon the user's approval,

[0917] Using the analyzed information data, a means to function as a household work device for recording daily activities and events in the home,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, wherein the analysis means analyzes audio information in video data using a speech recognition function and identifies related events.

[0921] (Claim 3)

[0922] The system according to claim 1, wherein the information data upload means transmits the data to the data server at an optimal timing based on the communication network connection status.

[0923] "Example 2 of combining an emotion engine"

[0924] (Claim 1)

[0925] A means for collecting digital information captured by a camera,

[0926] Means for analyzing the aforementioned digital information to extract time information, location information, and object identification information,

[0927] A means for classifying the digital information based on the phenomena, based on the extracted information,

[0928] A means for using emotion recognition technology to identify emotional information from the aforementioned digital information and assign an emotion-based classification tag,

[0929] A means of automatically identifying and deleting duplicate or low-quality digital information,

[0930] A means for notifying users of the classification results, sentiment-based classification tags, and deletion suggestions, and updating the database with user approval,

[0931] A system that includes this.

[0932] (Claim 2)

[0933] The system according to claim 1, wherein the analysis means analyzes audio data in a video using an audio analysis means and identifies related phenomena.

[0934] (Claim 3)

[0935] The system according to claim 1, wherein the data transmission means transmits data to the processing device at an optimal timing based on the communication status.

[0936] "Application example 2 when combining with an emotional engine"

[0937] (Claim 1)

[0938] A means of collecting digital data captured by a camera,

[0939] A means for analyzing the aforementioned digital data to extract date and time information, location information, and object identification information,

[0940] A means for classifying the digital data based on the extracted information,

[0941] A means of automatically identifying and deleting duplicate or low-quality digital data,

[0942] A means for notifying the user of the classification results and deletion proposals, and updating the storage system upon the user's approval,

[0943] A method for identifying emotional information from analyzed digital data, classifying and tagging it by emotion,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, wherein the analysis means analyzes audio data in the video using a speech recognition function and identifies related events.

[0947] (Claim 3)

[0948] The system according to claim 1, wherein the data transfer means transmits data to the server at an optimal timing based on the communication connection status. [Explanation of symbols]

[0949] 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 for aggregating information data acquired by the imaging device, The means for analyzing the aforementioned information data and extracting time information, location information, and object identification information, A means for classifying the information data on an event basis based on the extracted information, A means of automatically recognizing and removing duplicate or low-quality information data, A means for notifying the user of the classification results and removal suggestions, and updating the information repository upon the user's approval, Using the analyzed information data, a means to function as a household work device for recording daily activities and events in the home, A system that includes this.

2. The system according to claim 1, wherein the analysis means analyzes audio information in video data using a speech recognition function and identifies related events.

3. The system according to claim 1, wherein the information data upload means transmits the data to the data server at an optimal timing based on the communication network connection status.

Images