system

Abstract

We provide the system. [Solution] A means of collecting preference data based on user interests, A means for generating a profile that determines viewing priority based on the aforementioned preference data, An analytical method for analyzing the importance of each scene from the input video, A system that includes means for selecting scenes to be viewed based on their importance and for continuously playing only the selected scenes.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

[0006] "User" refers to an individual or group that uses the system to view video content.

[0007] "Preference data" refers to information about a user's viewing behavior and preferences, such as their interests, viewing history, and genre preferences.

[0008] A "profile" refers to a collection of information generated based on a user's preference data, used to determine viewing priorities.

[0009] "Analysis means" refers to technology or equipment for receiving video and audio data, analyzing their content, and scoring the importance of each scene.

[0010] "Scoring" refers to the act of numerically evaluating the importance of analyzed scenes in relation to the user's profile.

[0011] A "viewing target scene" refers to the portion of a video that has been selected as a highly important scene and is played by the user.

[0012] "Means of continuous playback" refers to methods or technologies for playing selected viewing scenes without interruption. [Brief explanation of the drawing]

[0013] [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] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It 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.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, a numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is designed to streamline the user's video viewing experience. The system includes a program that creates a profile reflecting the user's preferences and interests, and automatically selects and plays important portions of video content.

[0035] The server receives preference data and viewing history from the user's device and uses machine learning algorithms to build a user profile based on this information. The profile includes information about specific genres, themes, and preferences. Based on this profile, the server analyzes videos that the user wishes to watch and evaluates the importance of each scene.

[0036] In video analysis, speech recognition technology is used to convert audio into text, and the analysis is performed by detecting actions and scene changes within the video. Based on this, the server assigns an importance score to each scene. The parts deemed important based on the scoring results are aggregated and designated as the scenes to be viewed.

[0037] On the device, content is provided that plays only the scenes the user is interested in, using a skip list sent from the server. This allows the user to efficiently watch only the parts that interest them in a short amount of time. In addition, new data obtained through this viewing experience is also sent to the server, and the user profile is continuously updated.

[0038] For example, if a user is particularly interested in sports, they could be provided with videos that compile only the highlights and decisive moments from weekly matches. This user can enjoy the important scenes in a short amount of time without having to watch the entire long match, resulting in a highly efficient viewing experience.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users access their account settings screen and enter their interests, viewing preferences, and genre preferences. This data is sent to the server via their device.

[0042] Step 2:

[0043] The server analyzes the received user preference data and viewing history, and uses machine learning algorithms to create a user profile. This profile indicates the types of content the user is predicted to be interested in.

[0044] Step 3:

[0045] When a user selects a video they want to watch, the server begins processing that video for analysis. The server uses speech recognition technology to convert the video's audio data into text and detects action and scene changes from the video data.

[0046] Step 4:

[0047] The server uses the analyzed data to score the importance of each scene, associating it with the user profile. Higher scores are assigned to scenes that are more likely to interest the user.

[0048] Step 5:

[0049] Once high-priority scenes are identified, the server groups them as scenes to be viewed and generates a list of timestamps indicating the time ranges that should be skipped.

[0050] Step 6:

[0051] The device receives a list of timestamps sent from the server and uses this list when the user plays a video to automatically skip unnecessary parts and play only the important scenes consecutively.

[0052] Step 7:

[0053] Users can efficiently watch only the parts that interest them in a short amount of time. This viewing data is then sent back to the server and used to update the user profile.

[0054] (Example 1)

[0055] 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."

[0056] In today's world, a vast amount of video content is available, and users are expected to select and watch content that matches their interests and preferences. However, there is a lack of efficient means to view the necessary information and interesting scenes, and users often get overwhelmed by a large amount of irrelevant information. This problem should be solved by developing a system that supports effective video selection and viewing based on user interests.

[0057] 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.

[0058] In this invention, the server includes means for collecting attribute data based on user preferences, means for generating user information that determines display priority based on the attribute data, and a processing device for analyzing the importance of each scene from the acquired video footage. This enables users to efficiently view content that matches their interests in a short amount of time.

[0059] "User preference-based attribute data" refers to information obtained from users' interests, preferences, past viewing history, etc., and is used to characterize the characteristics of individual users.

[0060] "User information that determines display priority" is information generated based on user attribute data, and it is an indicator that shows which content should be prioritized for viewing by the user.

[0061] A "processing device for analyzing the importance of each scene from video footage" is a hardware or software device used to divide video content into individual scenes, evaluate them, and determine their importance.

[0062] "Speech recognition technology" is a technology that analyzes audio signals as digital data and converts them into text information, and is used to understand audio within videos.

[0063] "Visual information analysis technology" is a technology used to analyze image data and understand its content, and is used to detect motion and scene changes within a video.

[0064] "Evaluation technology" refers to techniques that use transcribed audio and visual information to measure the value of each scene, and is a method used in scoring and other applications.

[0065] The system of this invention is designed to optimize the user's video viewing experience. Specifically, the server collects attribute data based on the user's preferences from the user's terminal and generates user information that determines the display priority based on this data. This process utilizes machine learning models (e.g., TENSORFLOW® or PyTorch).

[0066] The server then analyzes the video the user wishes to watch. This analysis uses speech recognition technology (e.g., a common speech recognition API) to convert the audio in the video into text. This text data is then combined with visual information analysis technology (e.g., OpenCV) to extract changes in actions and scenes, and the analysis is performed accordingly.

[0067] To assess the importance of each scene, the server performs a comprehensive evaluation. This assigns an importance score to each scene in the video, determining which scenes are most important. The evaluated information is compiled into a skip list generated by the server and sent to the terminal.

[0068] On the device, only important scenes aligned with the user's interests are played consecutively based on the received skip list. This allows users to efficiently view content of interest in a short amount of time. Additionally, data obtained during viewing is returned to the server, updating the user profile.

[0069] For example, if a user enters the prompt "I want to see highlights from a new movie," the server can process this information and extract and provide action scenes or climactic moments from the relevant movie. This allows the user to quickly experience the overall atmosphere of the film.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The server collects attribute data based on user preferences from the user's device. This data includes the user's past viewing history, preferred genres, and themes. The server uses this information to build a data structure that provides a detailed understanding of the user's interests. Specifically, it receives data from the device using a data acquisition API and stores it in a database.

[0073] Step 2:

[0074] The server generates user information to determine display priority based on the collected attribute data, using a generative AI model. The input here is the user data collected in step 1, which is processed to generate a user profile, and the prioritized information is output as an analysis result. Specifically, the operation involves updating the profile based on user preferences using a machine learning algorithm.

[0075] Step 3:

[0076] The server analyzes the importance of each scene in a video that the user wishes to watch. It takes user-selected video data as input, converts the audio to text using speech recognition technology, and detects scene changes using visual information analysis technology. The output is an importance score assigned to each scene. Specifically, it uses a speech recognition API to convert the audio to text and video processing technology to analyze the scenes.

[0077] Step 4:

[0078] The server generates a skip list based on the analysis results. The input is the importance score for each scene provided in step 3. Using this, the server selects the scenes with high importance and outputs a list of scenes that the user should watch. Specifically, the scene selection algorithm generates the list based on the scoring results.

[0079] Step 5:

[0080] The device plays the video based on the skip list sent from the server. In this step, it receives input regarding the user's viewing preferences and outputs only the selected scenes sequentially. Specifically, this involves implementing a video playback function using a skip list.

[0081] Step 6:

[0082] The server receives viewing data from the terminal and updates the user profile. The input includes new data about the user's viewing behavior, which is used to update the user profile and supply the improved output with enhanced analytical accuracy to the next process. Specifically, the operation involves analyzing viewing history data and dynamically updating the profile.

[0083] (Application Example 1)

[0084] 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."

[0085] Modern content streaming services offer a vast amount of content, but users often spend a lot of time finding the important scenes that interest them. Therefore, there is a need for a system that efficiently selects the most important parts of a video according to the user's preferences, allowing for quick viewing. In particular, in their busy daily lives, users need a way to quickly consume content directly related to their interests.

[0086] 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.

[0087] In this invention, the server includes means for collecting preference information based on the user's interests, means for generating individual information to determine viewing priorities based on the preference information, means for analyzing the importance of each scene from the input video, means for providing application functions that operate on an electronic device to play back only the important scenes based on the analysis results, means for predicting new interests based on viewing history using a generation artificial intelligence model, and means for generating prompt sentences to interact with the user. As a result, the user can not only efficiently watch parts of interest in a short amount of time, but also constantly discover new interests.

[0088] "User-based preference information" refers to data that reflects a user's viewing history and preferences.

[0089] "Generating individual information to determine viewing priorities" refers to the process of determining the priority of scenes that should be viewed based on the user's preference information and generating that information.

[0090] "Analysis methods for analyzing the importance of each scene from input video" refers to methods and techniques for evaluating and analyzing the importance of each scene based on video data.

[0091] "Providing an application function that operates on an electronic device to play back only important scenes based on the analysis results" means realizing a function that uses the results of video analysis to play back selected important scenes on a specific electronic device.

[0092] "Predicting new interests based on viewing history using generative artificial intelligence models" refers to the process of using machine learning models to infer a user's potential interests from their past viewing history.

[0093] "Generating prompts to interact with the user" refers to creating interactive inquiries and instructions for the user, and using this as a means of communication.

[0094] The embodiments for carrying out this invention are shown below.

[0095] The server collects preference information and viewing history data based on user interests transmitted from the user's terminal. It then analyzes this data using a generative artificial intelligence model to generate a user profile. This profile includes individual information for determining viewing priorities. The analysis also includes a process of predicting new interests based on viewing history data. Furthermore, the server analyzes video data, utilizes speech recognition technology to convert audio data into text data to evaluate the importance of each scene, and integrates this with the visual data. This results in higher scores being assigned to scenes deemed important.

[0096] Next, the server uses the analysis results to select important scenes and creates a skip list for playback. This list is sent to the user's electronic device, and actual playback takes place on that device. As a result, the user can efficiently watch only the important scenes that are relevant to their interests.

[0097] For example, when a user who enjoys traveling watches a travel documentary, the generative AI model analyzes the user's past viewing patterns and determines that scenes related to specific regions or cultures are important. Based on this analysis, the user can automatically enjoy scenes that match their interests.

[0098] Examples of prompts for a generative AI model:

[0099] "Based on data from travel documentaries the user has previously watched, predict potential new regions they might be interested in and identify relevant scenes."

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server receives preference information and viewing history data transmitted from the user's terminal. This data indicates the user's interests and is the input data necessary for the server to generate the next profile. The preference information and viewing history are integrated and stored in a database.

[0103] Step 2:

[0104] The server uses a generative artificial intelligence model to analyze received preference information and viewing history data. In this process, machine learning algorithms are used to learn the user's interest patterns, and a profile is generated based on the results. The output is a user profile including viewing priorities. This profile is used for future video selection.

[0105] Step 3:

[0106] The server utilizes viewing priority information obtained from pre-configured profiles to analyze video content. It receives video data as input, converts the audio data into text data using speech recognition technology, and analyzes the emotional or visual content of each scene. This analysis calculates an importance score for each scene.

[0107] Step 4:

[0108] The server generates a skip list based on the analysis results. It creates a skip list that includes only high-priority scenes and sends this list to the device. This skip list serves as a guide to optimize the user's viewing experience.

[0109] Step 5:

[0110] The device uses a skip list received from the server to play only the scenes deemed important. Users can streamline their viewing experience by continuously playing pre-selected, interesting scenes via the device. The user's viewing results are then fed back to the server as new preference information.

[0111] 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.

[0112] This invention provides a video playback system that further personalizes the viewing experience by combining it with an emotion engine that recognizes user emotions. This system comprehensively utilizes user preference data, viewing history, and real-time emotion data to select and play the most optimal viewing scenes.

[0113] When a user watches a video, the device's emotion engine analyzes the user's facial expressions and voice tone through the camera and microphone to recognize their emotions in real time. The device then sends data about the user's current emotional state to a server. The server uses this emotion data to further refine the user profile and adjust viewing priorities.

[0114] The server analyzes the user's desired video content based on their profile and emotional data, and evaluates the importance of each scene. Importance is scored based on the characteristics of scenes the user has previously enjoyed watching and their real-time emotional state. As a result, scenes with high importance are selected for viewing.

[0115] The device smoothly plays the scenes provided by the server, efficiently delivering scenes that the user is likely to find interesting. This allows the user to enjoy an emotionally enriching video experience. In particular, if the user is clearly in a positive emotional state, the server will take full advantage of that state and prioritize selecting content that the user will enjoy more. On the other hand, if the user is in a negative emotional state, it will present content that promotes relaxation or mood improvement.

[0116] For example, if a user watching a movie displays a sad expression, the emotion engine can immediately detect this, and the server can adjust the next scene to be more positive and encouraging, thereby continuously personalizing the viewing experience.

[0117] The following describes the processing flow.

[0118] Step 1:

[0119] The user launches a video viewing application and selects the content they want to watch. At this time, the device notifies the user that it will use the camera and microphone and obtains permission for emotion recognition.

[0120] Step 2:

[0121] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time to determine their emotional state. This analysis detects emotional states such as positive, negative, and neutral.

[0122] Step 3:

[0123] The device sends recognized emotion data to the server. This data includes the type and intensity of the emotion, which the server can use to adjust the user's viewing experience.

[0124] Step 4:

[0125] The server combines emotional data and profiles received from the user to perform video analysis. It scores the importance of each scene and reprioritizes content according to the user's emotional state.

[0126] Step 5:

[0127] The server generates a skip list that reflects emotional data and selects scenes to watch. If positive emotions are detected, adjustments are made, such as selecting scenes that maintain the user's mood.

[0128] Step 6:

[0129] The device receives a skip list sent from the server and begins playback only of the specified scenes. This allows the user to have a video experience that matches their real-time emotions.

[0130] Step 7:

[0131] While the video is playing, the device continues to monitor the user's emotions and automatically provides feedback to the server as new emotion data becomes available. Based on this feedback, the server continuously updates the skip list as needed.

[0132] (Example 2)

[0133] 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".

[0134] Traditional video playback systems have limitations in personalizing content based on users' fixed preferences and viewing history, making it difficult to provide flexible video content that responds to users' changing emotions in real time. As a result, they fail to provide a viewing experience optimized for users' interests and emotions, leading to decreased viewer satisfaction.

[0135] 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.

[0136] In this invention, the server includes means for recognizing the user's emotional state, means for updating the user profile, and means for adjusting viewing priorities. This makes it possible to provide video scenes that respond to the user's changing emotions in real time.

[0137] "User emotional state" refers to information that identifies the user's emotions, acquired in real time through input devices such as cameras and microphones.

[0138] A "user profile" is a collection of personalized information that is continuously updated based on the user's preferences, viewing history, and sentiment data.

[0139] "Viewing priority" refers to the criteria used to determine the order and priority of video scenes presented to a user, based on user profiles and real-time sentiment data.

[0140] An "analysis tool" is a system component that analyzes the characteristics of each scene in the input video and calculates its importance.

[0141] "Importance" is an indicator that is evaluated by analytical methods and shows how valuable each video scene is to the user.

[0142] A "selected scene" is a specific portion of a video that has been deemed highly important through analysis and chosen for viewing.

[0143] This invention utilizes sentiment data and user profiles between the terminal and the server to personalize the user's viewing experience. Specifically, it consists of the following elements:

[0144] The device uses its camera and microphone to capture facial expressions and voice in real time while the user is watching video content. The collected data is analyzed by an emotion engine to calculate the user's emotional state. This emotional data is securely transmitted to a server.

[0145] The server integrates sentiment data submitted by the user with existing user profiles and updates the profile accordingly. Machine learning algorithms are used to update the user profile, allowing for highly accurate predictions of user preferences and emotional tendencies. Based on this profile, the server analyzes the importance of the video scenes being watched and generates viewing priorities based on real-time emotions.

[0146] The device selects and plays streaming viewing scenes based on instructions sent from the server. This allows users to enjoy content that best suits their mood at the time. In particular, if a positive emotional state is detected, content that further enhances the user's mood can be prioritized.

[0147] For example, if a user smiles slightly while watching a movie, the device detects this emotion and sends the data to the server. The server then selects a brighter scene to watch next and changes the viewing scene to provide the user with a richer viewing experience.

[0148] Appropriate prompts might include: "Please describe the design of a system that uses real-time user sentiment data to customize the video viewing experience. Please explain in detail the process for selecting viewing scenes based on the user's emotional state."

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] The device uses its camera and microphone to acquire facial expression and voice data while the user is watching a video. This is the input, from which the emotion engine collects the data necessary for processing. Specifically, the camera analyzes facial feature points, and the microphone records the pitch and tone of the voice. This data is sent to the emotion engine, which then provides an output that identifies the user's emotional state.

[0152] Step 2:

[0153] The device sends real-time sentiment data analyzed by the sentiment engine to the server. This transmission process uses a secure network protocol. The input is sentiment data output by the sentiment engine, and data consistency and privacy are maintained when it is sent to the server. The server receives this data and uses it for further profile updates.

[0154] Step 3:

[0155] The server updates the user profile based on the received sentiment data. Specifically, it integrates existing profile information, viewing history, and preference data, and generates a new profile using a machine learning algorithm. The input is new and old user data, and this data is integrated and analyzed to obtain the output of a personalized profile.

[0156] Step 4:

[0157] The server uses updated user profiles and real-time sentiment data to analyze the importance of desired viewing scenes in each video. The analysis evaluates the characteristics of each scene and assigns an importance score. The input is data about each scene in the video, and based on this, it generates output that selects the scenes with the highest importance.

[0158] Step 5:

[0159] The device receives an optimized viewing scene provided by the server and plays it back to the user without interruption. Buffering technology is used to ensure smooth playback. The final input is scene data from the server, which is then presented to the user as media output. This process provides a personalized experience tailored to the user.

[0160] (Application Example 2)

[0161] 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".

[0162] When users watch video content, there is a challenge in providing a viewing experience that is tailored to their individual tastes and emotional state. Conventional systems have been unable to appropriately adjust the content they watch based on their interests and emotions, resulting in a limited user experience.

[0163] 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.

[0164] In this invention, the server includes means for generating information to determine viewing priorities based on user preference information, means for recognizing the user's emotions in real time, and means for dynamically adjusting viewing content based on the user's emotions and preferences. This makes it possible to personalize viewing content according to the user's emotional state.

[0165] A "user" is an individual who is watching video content.

[0166] "Preference information" refers to data collected based on a user's viewing history and interests.

[0167] "Viewing priority" is an indicator that determines the order in which videos are played based on the user's preferences.

[0168] "Information" refers to the components of a user's viewing profile generated on the server.

[0169] A "scene" refers to an individual scene or segment within video content.

[0170] "Importance" is an indicator that evaluates the value each scene holds for the user's viewing experience.

[0171] "Analysis means" refers to technologies and devices for analyzing audio and visual information within video content.

[0172] "Emotional state" refers to the real-time psychological condition perceived from the user's facial expressions and tone of voice.

[0173] "Real-time recognition methods" refer to technologies that instantly detect emotions by analyzing the user's facial expressions and voice.

[0174] "A means of dynamically adjusting" refers to a function that changes the content played according to the user's emotions and viewing history.

[0175] "Personalization" means optimizing content to suit the individual user's characteristics and preferences.

[0176] To implement this invention, a system is constructed in which the user uses a smartphone or smart glasses. This system consists of an emotion engine for recognizing emotions in real time, a database for storing user preference information, and a server for analyzing and playing videos.

[0177] The system uses the smartphone's camera and microphone to collect the user's facial expressions and voice tone. This data is analyzed by an emotion engine (e.g., using image and audio analysis libraries such as OpenCV or TensorFlow) to evaluate the user's emotional state in real time. This emotional state data is then sent to a server.

[0178] The server generates a profile based on the user's preferences and viewing history. This profile is built upon an analysis of the user's past viewing history and emotional data, and this information is used to determine viewing priorities. Each scene in the content is analyzed by converting audio and visual information into text, and its importance is scored. Based on this scoring data, personalized videos are provided to the user.

[0179] For example, when a user smiles while watching a comedy film, the system prioritizes playing highly entertaining scenes. Conversely, if the user appears sad, it presents relaxing scenes to adjust the viewing experience.

[0180] An example of a prompt to a generative AI model is, "To determine the user's smile and maximize the humor level of the scene, what next scene would you recommend?" This makes it possible to automatically select the optimal content structure for the viewer.

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The device uses its camera and microphone to acquire real-time video and audio data of the user. The input consists of video and audio data, and the output is the transfer of this data to an analysis tool. Specifically, the device's internal sensors are activated to collect samples of the user's face and voice.

[0184] Step 2:

[0185] The device transmits the acquired video and audio data to an emotion engine for analysis of the emotional state. The input data includes the user's facial expressions and voice tone, and the output generates an emotional state (e.g., happiness, sadness). Specifically, a facial recognition algorithm (e.g., OpenCV) classifies the user's facial expressions, and a voice analysis engine (e.g., TensorFlow) evaluates the voice tone.

[0186] Step 3:

[0187] The terminal sends the analyzed emotional state data to the server. The input is the output data from the emotion engine, which is then transmitted to the server via the communication network. Specifically, the terminal's network interface is activated, and the data is securely sent to the server.

[0188] Step 4:

[0189] The server updates the profile using the user's emotional state data and preference information. The input is emotional data and the existing user profile, and the output is the updated profile. Specifically, the database management system updates the user information using the new data.

[0190] Step 5:

[0191] The server uses the updated profile to recalculate viewing priorities and scores the importance of each scene in the video. Inputs include the profile and viewing history, and output is an importance score for each scene. Specifically, a machine learning algorithm evaluates each scene and assigns a score.

[0192] Step 6:

[0193] The server selects the most suitable scenes for the user based on the scene importance score of the video and sends that information to the terminal. The input data is the score for each scene, and the output is a list of selected scenes. Specifically, the server's scheduling system works to create and send the scene list.

[0194] Step 7:

[0195] The terminal plays a video based on a scene list received from the server. The input is a scene list, and the output is continuous playback of the video for the user. Specifically, the video player selectively plays the instructed scenes, delivering the video and audio to the user.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] [Second Embodiment]

[0200] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0201] 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.

[0202] 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).

[0203] 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.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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".

[0212] This invention is designed to streamline the user's video viewing experience. The system includes a program that creates a profile reflecting the user's preferences and interests, and automatically selects and plays important portions of video content.

[0213] The server receives preference data and viewing history from the user's device and uses machine learning algorithms to build a user profile based on this information. The profile includes information about specific genres, themes, and preferences. Based on this profile, the server analyzes videos that the user wishes to watch and evaluates the importance of each scene.

[0214] In video analysis, speech recognition technology is used to convert audio into text, and the analysis is performed by detecting actions and scene changes within the video. Based on this, the server assigns an importance score to each scene. The parts deemed important based on the scoring results are aggregated and designated as the scenes to be viewed.

[0215] On the device, content is provided that plays only the scenes the user is interested in, using a skip list sent from the server. This allows the user to efficiently watch only the parts that interest them in a short amount of time. In addition, new data obtained through this viewing experience is also sent to the server, and the user profile is continuously updated.

[0216] For example, if a user is particularly interested in sports, they could be provided with videos that compile only the highlights and decisive moments from weekly matches. This user can enjoy the important scenes in a short amount of time without having to watch the entire long match, resulting in a highly efficient viewing experience.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] Users access their account settings screen and enter their interests, viewing preferences, and genre preferences. This data is sent to the server via their device.

[0220] Step 2:

[0221] The server analyzes the received user preference data and viewing history, and uses machine learning algorithms to create a user profile. This profile indicates the types of content the user is predicted to be interested in.

[0222] Step 3:

[0223] When a user selects a video they want to watch, the server begins processing that video for analysis. The server uses speech recognition technology to convert the video's audio data into text and detects action and scene changes from the video data.

[0224] Step 4:

[0225] The server uses the analyzed data to score the importance of each scene, associating it with the user profile. Higher scores are assigned to scenes that are more likely to interest the user.

[0226] Step 5:

[0227] Once high-priority scenes are identified, the server groups them as scenes to be viewed and generates a list of timestamps indicating the time ranges that should be skipped.

[0228] Step 6:

[0229] The device receives a list of timestamps sent from the server and uses this list when the user plays a video to automatically skip unnecessary parts and play only the important scenes consecutively.

[0230] Step 7:

[0231] Users can efficiently watch only the parts that interest them in a short amount of time. This viewing data is then sent back to the server and used to update the user profile.

[0232] (Example 1)

[0233] 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."

[0234] In today's world, a vast amount of video content is available, and users are expected to select and watch content that matches their interests and preferences. However, there is a lack of efficient means to view the necessary information and interesting scenes, and users often get overwhelmed by a large amount of irrelevant information. This problem should be solved by developing a system that supports effective video selection and viewing based on user interests.

[0235] 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.

[0236] In this invention, the server includes means for collecting attribute data based on user preferences, means for generating user information that determines display priority based on the attribute data, and a processing device for analyzing the importance of each scene from the acquired video footage. This enables users to efficiently view content that matches their interests in a short amount of time.

[0237] "User preference-based attribute data" refers to information obtained from users' interests, preferences, past viewing history, etc., and is used to characterize the characteristics of individual users.

[0238] "User information that determines display priority" is information generated based on user attribute data, and it is an indicator that shows which content should be prioritized for viewing by the user.

[0239] A "processing device for analyzing the importance of each scene from video footage" is a hardware or software device used to divide video content into individual scenes, evaluate them, and determine their importance.

[0240] "Speech recognition technology" is a technology that analyzes audio signals as digital data and converts them into text information, and is used to understand audio within videos.

[0241] "Visual information analysis technology" is a technology used to analyze image data and understand its content, and is used to detect motion and scene changes within a video.

[0242] "Evaluation technology" refers to techniques that use transcribed audio and visual information to measure the value of each scene, and is a method used in scoring and other applications.

[0243] The system of this invention is designed to optimize the user's video viewing experience. Specifically, the server collects attribute data based on the user's preferences from the user's terminal and generates user information that determines the display priority based on this data. This process utilizes machine learning models (e.g., TensorFlow or PyTorch).

[0244] The server then analyzes the video the user wishes to watch. This analysis uses speech recognition technology (e.g., a common speech recognition API) to convert the audio in the video into text. This text data is then combined with visual information analysis technology (e.g., OpenCV) to extract changes in actions and scenes, and the analysis is performed accordingly.

[0245] To assess the importance of each scene, the server performs a comprehensive evaluation. This assigns an importance score to each scene in the video, determining which scenes are most important. The evaluated information is compiled into a skip list generated by the server and sent to the terminal.

[0246] On the device, only important scenes aligned with the user's interests are played consecutively based on the received skip list. This allows users to efficiently view content of interest in a short amount of time. Additionally, data obtained during viewing is returned to the server, updating the user profile.

[0247] For example, if a user enters the prompt "I want to see highlights from a new movie," the server can process this information and extract and provide action scenes or climactic moments from the relevant movie. This allows the user to quickly experience the overall atmosphere of the film.

[0248] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0249] Step 1:

[0250] The server collects attribute data based on user preferences from the user's device. This data includes the user's past viewing history, preferred genres, and themes. The server uses this information to build a data structure that provides a detailed understanding of the user's interests. Specifically, it receives data from the device using a data acquisition API and stores it in a database.

[0251] Step 2:

[0252] The server generates user information to determine display priority based on the collected attribute data, using a generative AI model. The input here is the user data collected in step 1, which is processed to generate a user profile, and the prioritized information is output as an analysis result. Specifically, the operation involves updating the profile based on user preferences using a machine learning algorithm.

[0253] Step 3:

[0254] The server analyzes the importance of each scene in a video that the user wishes to watch. It takes user-selected video data as input, converts the audio to text using speech recognition technology, and detects scene changes using visual information analysis technology. The output is an importance score assigned to each scene. Specifically, it uses a speech recognition API to convert the audio to text and video processing technology to analyze the scenes.

[0255] Step 4:

[0256] The server generates a skip list based on the analysis results. The input is the importance score for each scene provided in step 3. Using this, the server selects the scenes with high importance and outputs a list of scenes that the user should watch. Specifically, the scene selection algorithm generates the list based on the scoring results.

[0257] Step 5:

[0258] The device plays the video based on the skip list sent from the server. In this step, it receives input regarding the user's viewing preferences and outputs only the selected scenes sequentially. Specifically, this involves implementing a video playback function using a skip list.

[0259] Step 6:

[0260] The server receives viewing data from the terminal and updates the user profile. The input includes new data about the user's viewing behavior, which is used to update the user profile and supply the improved output with enhanced analytical accuracy to the next process. Specifically, the operation involves analyzing viewing history data and dynamically updating the profile.

[0261] (Application Example 1)

[0262] 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."

[0263] Modern content streaming services offer a vast amount of content, but users often spend a lot of time finding the important scenes that interest them. Therefore, there is a need for a system that efficiently selects the most important parts of a video according to the user's preferences, allowing for quick viewing. In particular, in their busy daily lives, users need a way to quickly consume content directly related to their interests.

[0264] 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.

[0265] In this invention, the server includes means for collecting preference information based on the user's interests, means for generating individual information to determine viewing priorities based on the preference information, means for analyzing the importance of each scene from the input video, means for providing application functions that operate on an electronic device to play back only the important scenes based on the analysis results, means for predicting new interests based on viewing history using a generation artificial intelligence model, and means for generating prompt sentences to interact with the user. As a result, the user can not only efficiently watch parts of interest in a short amount of time, but also constantly discover new interests.

[0266] "User-based preference information" refers to data that reflects a user's viewing history and preferences.

[0267] "Generating individual information to determine viewing priorities" refers to the process of determining the priority of scenes that should be viewed based on the user's preference information and generating that information.

[0268] "Analysis methods for analyzing the importance of each scene from input video" refers to methods and techniques for evaluating and analyzing the importance of each scene based on video data.

[0269] "Providing an application function that operates on an electronic device to play back only important scenes based on the analysis results" means realizing a function that uses the results of video analysis to play back selected important scenes on a specific electronic device.

[0270] "Predicting new interests based on viewing history using generative artificial intelligence models" refers to the process of using machine learning models to infer a user's potential interests from their past viewing history.

[0271] "Generating prompts to interact with the user" refers to creating interactive inquiries and instructions for the user, and using this as a means of communication.

[0272] The embodiments for carrying out this invention are shown below.

[0273] The server collects preference information and viewing history data based on user interests transmitted from the user's terminal. It then analyzes this data using a generative artificial intelligence model to generate a user profile. This profile includes individual information for determining viewing priorities. The analysis also includes a process of predicting new interests based on viewing history data. Furthermore, the server analyzes video data, utilizes speech recognition technology to convert audio data into text data to evaluate the importance of each scene, and integrates this with the visual data. This results in higher scores being assigned to scenes deemed important.

[0274] Next, the server uses the analysis results to select important scenes and creates a skip list for playback. This list is sent to the user's electronic device, and actual playback takes place on that device. As a result, the user can efficiently watch only the important scenes that are relevant to their interests.

[0275] For example, when a user who enjoys traveling watches a travel documentary, the generative AI model analyzes the user's past viewing patterns and determines that scenes related to specific regions or cultures are important. Based on this analysis, the user can automatically enjoy scenes that match their interests.

[0276] Examples of prompts for a generative AI model:

[0277] "Based on data from travel documentaries the user has previously watched, predict potential new regions they might be interested in and identify relevant scenes."

[0278] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0279] Step 1:

[0280] The server receives the preference information and viewing history data transmitted from the user terminal. These data indicate the user's interests and are the input data required by the server for the next profile generation. The preference information and viewing history are integrated and stored in a database.

[0281] Step 2:

[0282] The server analyzes the received preference information and viewing history data using a generated artificial intelligence model. In this process, a machine learning algorithm is used to learn the user's interest trends, and a profile is generated based on the results. As output, a user profile including viewing priorities is obtained. This profile is used for future video selection.

[0283] Step 3:

[0284] The server utilizes the viewing priority information obtained from the profile in advance to analyze video content. It receives video data as input, converts the audio data into text data using speech recognition technology, and analyzes the emotional or visual content for each scene. Through this analysis, an importance score for each scene is calculated.

[0285] Step 4:

[0286] The server generates a skip list based on the analysis results. The skip list is generated to include only the scenes with high importance and is transmitted to the terminal. This skip list functions as a guide to optimize the user's viewing experience.

[0287] Step 5:

[0288] The device uses a skip list received from the server to play only the scenes deemed important. Users can streamline their viewing experience by continuously playing pre-selected, interesting scenes via the device. The user's viewing results are then fed back to the server as new preference information.

[0289] 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.

[0290] This invention provides a video playback system that further personalizes the viewing experience by combining it with an emotion engine that recognizes user emotions. This system comprehensively utilizes user preference data, viewing history, and real-time emotion data to select and play the most optimal viewing scenes.

[0291] When a user watches a video, the device's emotion engine analyzes the user's facial expressions and voice tone through the camera and microphone to recognize their emotions in real time. The device then sends data about the user's current emotional state to a server. The server uses this emotion data to further refine the user profile and adjust viewing priorities.

[0292] The server analyzes the user's desired video content based on their profile and emotional data, and evaluates the importance of each scene. Importance is scored based on the characteristics of scenes the user has previously enjoyed watching and their real-time emotional state. As a result, scenes with high importance are selected for viewing.

[0293] The device smoothly plays the scenes provided by the server, efficiently delivering scenes that the user is likely to find interesting. This allows the user to enjoy an emotionally enriching video experience. In particular, if the user is clearly in a positive emotional state, the server will take full advantage of that state and prioritize selecting content that the user will enjoy more. On the other hand, if the user is in a negative emotional state, it will present content that promotes relaxation or mood improvement.

[0294] For example, if a user watching a movie displays a sad expression, the emotion engine can immediately detect this, and the server can adjust the next scene to be more positive and encouraging, thereby continuously personalizing the viewing experience.

[0295] The following describes the processing flow.

[0296] Step 1:

[0297] The user launches a video viewing application and selects the content they want to watch. At this time, the device notifies the user that it will use the camera and microphone and obtains permission for emotion recognition.

[0298] Step 2:

[0299] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time to determine their emotional state. This analysis detects emotional states such as positive, negative, and neutral.

[0300] Step 3:

[0301] The device sends recognized emotion data to the server. This data includes the type and intensity of the emotion, which the server can use to adjust the user's viewing experience.

[0302] Step 4:

[0303] The server combines the emotion data and profile received from the user and performs video analysis. It scores the importance of each scene and resets the priority of the content according to the emotional state.

[0304] Step 5:

[0305] The server generates a skip list reflecting the emotion data and selects the scenes to be viewed. When positive emotions are detected, adjustments are made such as selecting scenes that maintain the user's mood.

[0306] Step 6:

[0307] The terminal receives the skip list sent from the server and starts playing only the specified scenes. As a result, the user can obtain a video experience that fits their real-time emotions.

[0308] Step 7:

[0309] During the playback of the video, the terminal continues to monitor the user's emotions and automatically feedbacks to the server as soon as new emotion data is obtained. Based on this feedback, the server continues to update the skip list as needed.

[0310] (Example 2)

[0311] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] The conventional video playback system has limitations in personalization based on the fixed preferences and history of the user, and it is difficult to provide flexible videos according to the user's emotions that change in real time. As a result, there is a problem that an optimized viewing experience for the user's interests and emotions cannot be provided, and the viewing satisfaction decreases.

[0313] 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.

[0314] In this invention, the server includes means for recognizing the user's emotional state, means for updating the user profile, and means for adjusting viewing priorities. This makes it possible to provide video scenes that respond to the user's changing emotions in real time.

[0315] "User emotional state" refers to information that identifies the user's emotions, acquired in real time through input devices such as cameras and microphones.

[0316] A "user profile" is a collection of personalized information that is continuously updated based on the user's preferences, viewing history, and sentiment data.

[0317] "Viewing priority" refers to the criteria used to determine the order and priority of video scenes presented to a user, based on user profiles and real-time sentiment data.

[0318] An "analysis tool" is a system component that analyzes the characteristics of each scene in the input video and calculates its importance.

[0319] "Importance" is an indicator that is evaluated by analytical methods and shows how valuable each video scene is to the user.

[0320] A "selected scene" is a specific portion of a video that has been deemed highly important through analysis and chosen for viewing.

[0321] This invention utilizes sentiment data and user profiles between the terminal and the server to personalize the user's viewing experience. Specifically, it consists of the following elements:

[0322] The device uses its camera and microphone to capture facial expressions and voice in real time while the user is watching video content. The collected data is analyzed by an emotion engine to calculate the user's emotional state. This emotional data is securely transmitted to a server.

[0323] The server integrates sentiment data submitted by the user with existing user profiles and updates the profile accordingly. Machine learning algorithms are used to update the user profile, allowing for highly accurate predictions of user preferences and emotional tendencies. Based on this profile, the server analyzes the importance of the video scenes being watched and generates viewing priorities based on real-time emotions.

[0324] The device selects and plays streaming viewing scenes based on instructions sent from the server. This allows users to enjoy content that best suits their mood at the time. In particular, if a positive emotional state is detected, content that further enhances the user's mood can be prioritized.

[0325] For example, if a user smiles slightly while watching a movie, the device detects this emotion and sends the data to the server. The server then selects a brighter scene to watch next and changes the viewing scene to provide the user with a richer viewing experience.

[0326] Appropriate prompts might include: "Please describe the design of a system that uses real-time user sentiment data to customize the video viewing experience. Please explain in detail the process for selecting viewing scenes based on the user's emotional state."

[0327] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0328] Step 1:

[0329] The device uses its camera and microphone to acquire facial expression and voice data while the user is watching a video. This is the input, from which the emotion engine collects the data necessary for processing. Specifically, the camera analyzes facial feature points, and the microphone records the pitch and tone of the voice. This data is sent to the emotion engine, which then provides an output that identifies the user's emotional state.

[0330] Step 2:

[0331] The device sends real-time sentiment data analyzed by the sentiment engine to the server. This transmission process uses a secure network protocol. The input is sentiment data output by the sentiment engine, and data consistency and privacy are maintained when it is sent to the server. The server receives this data and uses it for further profile updates.

[0332] Step 3:

[0333] The server updates the user profile based on the received sentiment data. Specifically, it integrates existing profile information, viewing history, and preference data, and generates a new profile using a machine learning algorithm. The input is new and old user data, and this data is integrated and analyzed to obtain the output of a personalized profile.

[0334] Step 4:

[0335] The server uses updated user profiles and real-time sentiment data to analyze the importance of desired viewing scenes in each video. The analysis evaluates the characteristics of each scene and assigns an importance score. The input is data about each scene in the video, and based on this, it generates output that selects the scenes with the highest importance.

[0336] Step 5:

[0337] The device receives an optimized viewing scene provided by the server and plays it back to the user without interruption. Buffering technology is used to ensure smooth playback. The final input is scene data from the server, which is then presented to the user as media output. This process provides a personalized experience tailored to the user.

[0338] (Application Example 2)

[0339] 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."

[0340] When users watch video content, there is a challenge in providing a viewing experience that is tailored to their individual tastes and emotional state. Conventional systems have been unable to appropriately adjust the content they watch based on their interests and emotions, resulting in a limited user experience.

[0341] 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.

[0342] In this invention, the server includes means for generating information to determine viewing priorities based on user preference information, means for recognizing the user's emotions in real time, and means for dynamically adjusting viewing content based on the user's emotions and preferences. This makes it possible to personalize viewing content according to the user's emotional state.

[0343] A "user" is an individual who is watching video content.

[0344] "Preference information" refers to data collected based on a user's viewing history and interests.

[0345] "Viewing priority" is an indicator that determines the order in which videos are played based on the user's preferences.

[0346] "Information" refers to the components of a user's viewing profile generated on the server.

[0347] A "scene" refers to an individual scene or segment within video content.

[0348] "Importance" is an indicator that evaluates the value each scene holds for the user's viewing experience.

[0349] "Analysis means" refers to technologies and devices for analyzing audio and visual information within video content.

[0350] "Emotional state" refers to the real-time psychological condition perceived from the user's facial expressions and tone of voice.

[0351] "Real-time recognition methods" refer to technologies that instantly detect emotions by analyzing the user's facial expressions and voice.

[0352] "A means of dynamically adjusting" refers to a function that changes the content played according to the user's emotions and viewing history.

[0353] "Personalization" means optimizing content to suit the individual user's characteristics and preferences.

[0354] To implement this invention, a system is constructed in which the user uses a smartphone or smart glasses. This system consists of an emotion engine for recognizing emotions in real time, a database for storing user preference information, and a server for analyzing and playing videos.

[0355] The system uses the smartphone's camera and microphone to collect the user's facial expressions and voice tone. This data is analyzed by an emotion engine (e.g., using image and audio analysis libraries such as OpenCV or TensorFlow) to evaluate the user's emotional state in real time. This emotional state data is then sent to a server.

[0356] The server generates a profile based on the user's preferences and viewing history. This profile is built upon an analysis of the user's past viewing history and emotional data, and this information is used to determine viewing priorities. Each scene in the content is analyzed by converting audio and visual information into text, and its importance is scored. Based on this scoring data, personalized videos are provided to the user.

[0357] For example, when a user smiles while watching a comedy film, the system prioritizes playing highly entertaining scenes. Conversely, if the user appears sad, it presents relaxing scenes to adjust the viewing experience.

[0358] An example of a prompt to a generative AI model is, "To determine the user's smile and maximize the humor level of the scene, what next scene would you recommend?" This makes it possible to automatically select the optimal content structure for the viewer.

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The device uses its camera and microphone to acquire real-time video and audio data of the user. The input consists of video and audio data, and the output is the transfer of this data to an analysis tool. Specifically, the device's internal sensors are activated to collect samples of the user's face and voice.

[0362] Step 2:

[0363] The device transmits the acquired video and audio data to an emotion engine for analysis of the emotional state. The input data includes the user's facial expressions and voice tone, and the output generates an emotional state (e.g., happiness, sadness). Specifically, a facial recognition algorithm (e.g., OpenCV) classifies the user's facial expressions, and a voice analysis engine (e.g., TensorFlow) evaluates the voice tone.

[0364] Step 3:

[0365] The terminal sends the analyzed emotional state data to the server. The input is the output data from the emotion engine, which is then transmitted to the server via the communication network. Specifically, the terminal's network interface is activated, and the data is securely sent to the server.

[0366] Step 4:

[0367] The server updates the profile using the user's emotional state data and preference information. The input is emotional data and the existing user profile, and the output is the updated profile. Specifically, the database management system updates the user information using the new data.

[0368] Step 5:

[0369] The server uses the updated profile to recalculate viewing priorities and scores the importance of each scene in the video. Inputs include the profile and viewing history, and output is an importance score for each scene. Specifically, a machine learning algorithm evaluates each scene and assigns a score.

[0370] Step 6:

[0371] The server selects the most suitable scenes for the user based on the scene importance score of the video and sends that information to the terminal. The input data is the score for each scene, and the output is a list of selected scenes. Specifically, the server's scheduling system works to create and send the scene list.

[0372] Step 7:

[0373] The terminal plays a video based on a scene list received from the server. The input is a scene list, and the output is continuous playback of the video for the user. Specifically, the video player selectively plays the instructed scenes, delivering the video and audio to the user.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] [Third Embodiment]

[0378] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] 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".

[0390] This invention is designed to streamline the user's video viewing experience. The system includes a program that creates a profile reflecting the user's preferences and interests, and automatically selects and plays important portions of video content.

[0391] The server receives preference data and viewing history from the user's device and uses machine learning algorithms to build a user profile based on this information. The profile includes information about specific genres, themes, and preferences. Based on this profile, the server analyzes videos that the user wishes to watch and evaluates the importance of each scene.

[0392] In video analysis, speech recognition technology is used to convert audio into text, and the analysis is performed by detecting actions and scene changes within the video. Based on this, the server assigns an importance score to each scene. The parts deemed important based on the scoring results are aggregated and designated as the scenes to be viewed.

[0393] On the device, content is provided that plays only the scenes the user is interested in, using a skip list sent from the server. This allows the user to efficiently watch only the parts that interest them in a short amount of time. In addition, new data obtained through this viewing experience is also sent to the server, and the user profile is continuously updated.

[0394] For example, if a user is particularly interested in sports, they could be provided with videos that compile only the highlights and decisive moments from weekly matches. This user can enjoy the important scenes in a short amount of time without having to watch the entire long match, resulting in a highly efficient viewing experience.

[0395] The following describes the processing flow.

[0396] Step 1:

[0397] Users access their account settings screen and enter their interests, viewing preferences, and genre preferences. This data is sent to the server via their device.

[0398] Step 2:

[0399] The server analyzes the received user preference data and viewing history, and uses machine learning algorithms to create a user profile. This profile indicates the types of content the user is predicted to be interested in.

[0400] Step 3:

[0401] When a user selects a video they want to watch, the server begins processing that video for analysis. The server uses speech recognition technology to convert the video's audio data into text and detects action and scene changes from the video data.

[0402] Step 4:

[0403] The server uses the analyzed data to score the importance of each scene, associating it with the user profile. Higher scores are assigned to scenes that are more likely to interest the user.

[0404] Step 5:

[0405] Once high-priority scenes are identified, the server groups them as scenes to be viewed and generates a list of timestamps indicating the time ranges that should be skipped.

[0406] Step 6:

[0407] The device receives a list of timestamps sent from the server and uses this list when the user plays a video to automatically skip unnecessary parts and play only the important scenes consecutively.

[0408] Step 7:

[0409] Users can efficiently watch only the parts that interest them in a short amount of time. This viewing data is then sent back to the server and used to update the user profile.

[0410] (Example 1)

[0411] 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."

[0412] In today's world, a vast amount of video content is available, and users are expected to select and watch content that matches their interests and preferences. However, there is a lack of efficient means to view the necessary information and interesting scenes, and users often get overwhelmed by a large amount of irrelevant information. This problem should be solved by developing a system that supports effective video selection and viewing based on user interests.

[0413] 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.

[0414] In this invention, the server includes means for collecting attribute data based on user preferences, means for generating user information that determines display priority based on the attribute data, and a processing device for analyzing the importance of each scene from the acquired video footage. This enables users to efficiently view content that matches their interests in a short amount of time.

[0415] "User preference-based attribute data" refers to information obtained from users' interests, preferences, past viewing history, etc., and is used to characterize the characteristics of individual users.

[0416] "User information that determines display priority" is information generated based on user attribute data, and it is an indicator that shows which content should be prioritized for viewing by the user.

[0417] A "processing device for analyzing the importance of each scene from video footage" is a hardware or software device used to divide video content into individual scenes, evaluate them, and determine their importance.

[0418] "Speech recognition technology" is a technology that analyzes audio signals as digital data and converts them into text information, and is used to understand audio within videos.

[0419] "Visual information analysis technology" is a technology used to analyze image data and understand its content, and is used to detect motion and scene changes within a video.

[0420] "Evaluation technology" refers to techniques that use transcribed audio and visual information to measure the value of each scene, and is a method used in scoring and other applications.

[0421] The system of this invention is designed to optimize the user's video viewing experience. Specifically, the server collects attribute data based on the user's preferences from the user's terminal and generates user information that determines the display priority based on this data. This process utilizes machine learning models (e.g., TensorFlow or PyTorch).

[0422] The server then analyzes the video the user wishes to watch. This analysis uses speech recognition technology (e.g., a common speech recognition API) to convert the audio in the video into text. This text data is then combined with visual information analysis technology (e.g., OpenCV) to extract changes in actions and scenes, and the analysis is performed accordingly.

[0423] To assess the importance of each scene, the server performs a comprehensive evaluation. This assigns an importance score to each scene in the video, determining which scenes are most important. The evaluated information is compiled into a skip list generated by the server and sent to the terminal.

[0424] On the device, only important scenes aligned with the user's interests are played consecutively based on the received skip list. This allows users to efficiently view content of interest in a short amount of time. Additionally, data obtained during viewing is returned to the server, updating the user profile.

[0425] For example, if a user enters the prompt "I want to see highlights from a new movie," the server can process this information and extract and provide action scenes or climactic moments from the relevant movie. This allows the user to quickly experience the overall atmosphere of the film.

[0426] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0427] Step 1:

[0428] The server collects attribute data based on user preferences from the user's device. This data includes the user's past viewing history, preferred genres, and themes. The server uses this information to build a data structure that provides a detailed understanding of the user's interests. Specifically, it receives data from the device using a data acquisition API and stores it in a database.

[0429] Step 2:

[0430] The server generates user information to determine display priority based on the collected attribute data, using a generative AI model. The input here is the user data collected in step 1, which is processed to generate a user profile, and the prioritized information is output as an analysis result. Specifically, the operation involves updating the profile based on user preferences using a machine learning algorithm.

[0431] Step 3:

[0432] The server analyzes the importance of each scene in a video that the user wishes to watch. It takes user-selected video data as input, converts the audio to text using speech recognition technology, and detects scene changes using visual information analysis technology. The output is an importance score assigned to each scene. Specifically, it uses a speech recognition API to convert the audio to text and video processing technology to analyze the scenes.

[0433] Step 4:

[0434] The server generates a skip list based on the analysis results. The input is the importance score for each scene provided in step 3. Using this, the server selects the scenes with high importance and outputs a list of scenes that the user should watch. Specifically, the scene selection algorithm generates the list based on the scoring results.

[0435] Step 5:

[0436] The device plays the video based on the skip list sent from the server. In this step, it receives input regarding the user's viewing preferences and outputs only the selected scenes sequentially. Specifically, this involves implementing a video playback function using a skip list.

[0437] Step 6:

[0438] The server receives viewing data from the terminal and updates the user profile. The input includes new data about the user's viewing behavior, which is used to update the user profile and supply the improved output with enhanced analytical accuracy to the next process. Specifically, the operation involves analyzing viewing history data and dynamically updating the profile.

[0439] (Application Example 1)

[0440] 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."

[0441] Modern content streaming services offer a vast amount of content, but users often spend a lot of time finding the important scenes that interest them. Therefore, there is a need for a system that efficiently selects the most important parts of a video according to the user's preferences, allowing for quick viewing. In particular, in their busy daily lives, users need a way to quickly consume content directly related to their interests.

[0442] 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.

[0443] In this invention, the server includes means for collecting preference information based on the user's interests, means for generating individual information to determine viewing priorities based on the preference information, means for analyzing the importance of each scene from the input video, means for providing application functions that operate on an electronic device to play back only the important scenes based on the analysis results, means for predicting new interests based on viewing history using a generation artificial intelligence model, and means for generating prompt sentences to interact with the user. As a result, the user can not only efficiently watch parts of interest in a short amount of time, but also constantly discover new interests.

[0444] "User-based preference information" refers to data that reflects a user's viewing history and preferences.

[0445] "Generating individual information to determine viewing priorities" refers to the process of determining the priority of scenes that should be viewed based on the user's preference information and generating that information.

[0446] "Analysis methods for analyzing the importance of each scene from input video" refers to methods and techniques for evaluating and analyzing the importance of each scene based on video data.

[0447] "Providing an application function that operates on an electronic device to play back only important scenes based on the analysis results" means realizing a function that uses the results of video analysis to play back selected important scenes on a specific electronic device.

[0448] "Predicting new interests based on viewing history using generative artificial intelligence models" refers to the process of using machine learning models to infer a user's potential interests from their past viewing history.

[0449] "Generating prompts to interact with the user" refers to creating interactive inquiries and instructions for the user, and using this as a means of communication.

[0450] The embodiments for carrying out this invention are shown below.

[0451] The server collects preference information and viewing history data based on user interests transmitted from the user's terminal. It then analyzes this data using a generative artificial intelligence model to generate a user profile. This profile includes individual information for determining viewing priorities. The analysis also includes a process of predicting new interests based on viewing history data. Furthermore, the server analyzes video data, utilizes speech recognition technology to convert audio data into text data to evaluate the importance of each scene, and integrates this with the visual data. This results in higher scores being assigned to scenes deemed important.

[0452] Next, the server uses the analysis results to select important scenes and creates a skip list for playback. This list is sent to the user's electronic device, and actual playback takes place on that device. As a result, the user can efficiently watch only the important scenes that are relevant to their interests.

[0453] For example, when a user who enjoys traveling watches a travel documentary, the generative AI model analyzes the user's past viewing patterns and determines that scenes related to specific regions or cultures are important. Based on this analysis, the user can automatically enjoy scenes that match their interests.

[0454] Examples of prompts for a generative AI model:

[0455] "Based on data from travel documentaries the user has previously watched, predict potential new regions they might be interested in and identify relevant scenes."

[0456] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0457] Step 1:

[0458] The server receives preference information and viewing history data transmitted from the user's terminal. This data indicates the user's interests and is the input data necessary for the server to generate the next profile. The preference information and viewing history are integrated and stored in a database.

[0459] Step 2:

[0460] The server uses a generative artificial intelligence model to analyze received preference information and viewing history data. In this process, machine learning algorithms are used to learn the user's interest patterns, and a profile is generated based on the results. The output is a user profile including viewing priorities. This profile is used for future video selection.

[0461] Step 3:

[0462] The server utilizes viewing priority information obtained from pre-configured profiles to analyze video content. It receives video data as input, converts the audio data into text data using speech recognition technology, and analyzes the emotional or visual content of each scene. This analysis calculates an importance score for each scene.

[0463] Step 4:

[0464] The server generates a skip list based on the analysis results. It creates a skip list that includes only high-priority scenes and sends this list to the device. This skip list serves as a guide to optimize the user's viewing experience.

[0465] Step 5:

[0466] The device uses a skip list received from the server to play only the scenes deemed important. Users can streamline their viewing experience by continuously playing pre-selected, interesting scenes via the device. The user's viewing results are then fed back to the server as new preference information.

[0467] 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.

[0468] This invention provides a video playback system that further personalizes the viewing experience by combining it with an emotion engine that recognizes user emotions. This system comprehensively utilizes user preference data, viewing history, and real-time emotion data to select and play the most optimal viewing scenes.

[0469] When a user watches a video, the device's emotion engine analyzes the user's facial expressions and voice tone through the camera and microphone to recognize their emotions in real time. The device then sends data about the user's current emotional state to a server. The server uses this emotion data to further refine the user profile and adjust viewing priorities.

[0470] The server analyzes the user's desired video content based on their profile and emotional data, and evaluates the importance of each scene. Importance is scored based on the characteristics of scenes the user has previously enjoyed watching and their real-time emotional state. As a result, scenes with high importance are selected for viewing.

[0471] The device smoothly plays the scenes provided by the server, efficiently delivering scenes that the user is likely to find interesting. This allows the user to enjoy an emotionally enriching video experience. In particular, if the user is clearly in a positive emotional state, the server will take full advantage of that state and prioritize selecting content that the user will enjoy more. On the other hand, if the user is in a negative emotional state, it will present content that promotes relaxation or mood improvement.

[0472] For example, if a user watching a movie displays a sad expression, the emotion engine can immediately detect this, and the server can adjust the next scene to be more positive and encouraging, thereby continuously personalizing the viewing experience.

[0473] The following describes the processing flow.

[0474] Step 1:

[0475] The user launches a video viewing application and selects the content they want to watch. At this time, the device notifies the user that it will use the camera and microphone and obtains permission for emotion recognition.

[0476] Step 2:

[0477] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time to determine their emotional state. This analysis detects emotional states such as positive, negative, and neutral.

[0478] Step 3:

[0479] The device sends recognized emotion data to the server. This data includes the type and intensity of the emotion, which the server can use to adjust the user's viewing experience.

[0480] Step 4:

[0481] The server combines emotional data and profiles received from the user to perform video analysis. It scores the importance of each scene and reprioritizes content according to the user's emotional state.

[0482] Step 5:

[0483] The server generates a skip list that reflects emotional data and selects scenes to watch. If positive emotions are detected, adjustments are made, such as selecting scenes that maintain the user's mood.

[0484] Step 6:

[0485] The device receives a skip list sent from the server and begins playback only of the specified scenes. This allows the user to have a video experience that matches their real-time emotions.

[0486] Step 7:

[0487] While the video is playing, the device continues to monitor the user's emotions and automatically provides feedback to the server as new emotion data becomes available. Based on this feedback, the server continuously updates the skip list as needed.

[0488] (Example 2)

[0489] 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."

[0490] Traditional video playback systems have limitations in personalizing content based on users' fixed preferences and viewing history, making it difficult to provide flexible video content that responds to users' changing emotions in real time. As a result, they fail to provide a viewing experience optimized for users' interests and emotions, leading to decreased viewer satisfaction.

[0491] 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.

[0492] In this invention, the server includes means for recognizing the user's emotional state, means for updating the user profile, and means for adjusting viewing priorities. This makes it possible to provide video scenes that respond to the user's changing emotions in real time.

[0493] "User emotional state" refers to information that identifies the user's emotions, acquired in real time through input devices such as cameras and microphones.

[0494] A "user profile" is a collection of personalized information that is continuously updated based on the user's preferences, viewing history, and sentiment data.

[0495] "Viewing priority" refers to the criteria used to determine the order and priority of video scenes presented to a user, based on user profiles and real-time sentiment data.

[0496] An "analysis tool" is a system component that analyzes the characteristics of each scene in the input video and calculates its importance.

[0497] "Importance" is an indicator that is evaluated by analytical methods and shows how valuable each video scene is to the user.

[0498] A "selected scene" is a specific portion of a video that has been deemed highly important through analysis and chosen for viewing.

[0499] This invention utilizes sentiment data and user profiles between the terminal and the server to personalize the user's viewing experience. Specifically, it consists of the following elements:

[0500] The device uses its camera and microphone to capture facial expressions and voice in real time while the user is watching video content. The collected data is analyzed by an emotion engine to calculate the user's emotional state. This emotional data is securely transmitted to a server.

[0501] The server integrates sentiment data submitted by the user with existing user profiles and updates the profile accordingly. Machine learning algorithms are used to update the user profile, allowing for highly accurate predictions of user preferences and emotional tendencies. Based on this profile, the server analyzes the importance of the video scenes being watched and generates viewing priorities based on real-time emotions.

[0502] The device selects and plays streaming viewing scenes based on instructions sent from the server. This allows users to enjoy content that best suits their mood at the time. In particular, if a positive emotional state is detected, content that further enhances the user's mood can be prioritized.

[0503] For example, if a user smiles slightly while watching a movie, the device detects this emotion and sends the data to the server. The server then selects a brighter scene to watch next and changes the viewing scene to provide the user with a richer viewing experience.

[0504] Appropriate prompts might include: "Please describe the design of a system that uses real-time user sentiment data to customize the video viewing experience. Please explain in detail the process for selecting viewing scenes based on the user's emotional state."

[0505] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0506] Step 1:

[0507] The device uses its camera and microphone to acquire facial expression and voice data while the user is watching a video. This is the input, from which the emotion engine collects the data necessary for processing. Specifically, the camera analyzes facial feature points, and the microphone records the pitch and tone of the voice. This data is sent to the emotion engine, which then provides an output that identifies the user's emotional state.

[0508] Step 2:

[0509] The device sends real-time sentiment data analyzed by the sentiment engine to the server. This transmission process uses a secure network protocol. The input is sentiment data output by the sentiment engine, and data consistency and privacy are maintained when it is sent to the server. The server receives this data and uses it for further profile updates.

[0510] Step 3:

[0511] The server updates the user profile based on the received sentiment data. Specifically, it integrates existing profile information, viewing history, and preference data, and generates a new profile using a machine learning algorithm. The input is new and old user data, and this data is integrated and analyzed to obtain the output of a personalized profile.

[0512] Step 4:

[0513] The server uses updated user profiles and real-time sentiment data to analyze the importance of desired viewing scenes in each video. The analysis evaluates the characteristics of each scene and assigns an importance score. The input is data about each scene in the video, and based on this, it generates output that selects the scenes with the highest importance.

[0514] Step 5:

[0515] The device receives an optimized viewing scene provided by the server and plays it back to the user without interruption. Buffering technology is used to ensure smooth playback. The final input is scene data from the server, which is then presented to the user as media output. This process provides a personalized experience tailored to the user.

[0516] (Application Example 2)

[0517] 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."

[0518] When users watch video content, there is a challenge in providing a viewing experience that is tailored to their individual tastes and emotional state. Conventional systems have been unable to appropriately adjust the content they watch based on their interests and emotions, resulting in a limited user experience.

[0519] 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.

[0520] In this invention, the server includes means for generating information to determine viewing priorities based on user preference information, means for recognizing the user's emotions in real time, and means for dynamically adjusting viewing content based on the user's emotions and preferences. This makes it possible to personalize viewing content according to the user's emotional state.

[0521] A "user" is an individual who is watching video content.

[0522] "Preference information" refers to data collected based on a user's viewing history and interests.

[0523] "Viewing priority" is an indicator that determines the order in which videos are played based on the user's preferences.

[0524] "Information" refers to the components of a user's viewing profile generated on the server.

[0525] A "scene" refers to an individual scene or segment within video content.

[0526] "Importance" is an indicator that evaluates the value each scene holds for the user's viewing experience.

[0527] "Analysis means" refers to technologies and devices for analyzing audio and visual information within video content.

[0528] "Emotional state" refers to the real-time psychological condition perceived from the user's facial expressions and tone of voice.

[0529] "Real-time recognition methods" refer to technologies that instantly detect emotions by analyzing the user's facial expressions and voice.

[0530] "A means of dynamically adjusting" refers to a function that changes the content played according to the user's emotions and viewing history.

[0531] "Personalization" means optimizing content to suit the individual user's characteristics and preferences.

[0532] To implement this invention, a system is constructed in which the user uses a smartphone or smart glasses. This system consists of an emotion engine for recognizing emotions in real time, a database for storing user preference information, and a server for analyzing and playing videos.

[0533] The system uses the smartphone's camera and microphone to collect the user's facial expressions and voice tone. This data is analyzed by an emotion engine (e.g., using image and audio analysis libraries such as OpenCV or TensorFlow) to evaluate the user's emotional state in real time. This emotional state data is then sent to a server.

[0534] The server generates a profile based on the user's preferences and viewing history. This profile is built upon an analysis of the user's past viewing history and emotional data, and this information is used to determine viewing priorities. Each scene in the content is analyzed by converting audio and visual information into text, and its importance is scored. Based on this scoring data, personalized videos are provided to the user.

[0535] For example, when a user smiles while watching a comedy film, the system prioritizes playing highly entertaining scenes. Conversely, if the user appears sad, it presents relaxing scenes to adjust the viewing experience.

[0536] An example of a prompt to a generative AI model is, "To determine the user's smile and maximize the humor level of the scene, what next scene would you recommend?" This makes it possible to automatically select the optimal content structure for the viewer.

[0537] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0538] Step 1:

[0539] The device uses its camera and microphone to acquire real-time video and audio data of the user. The input consists of video and audio data, and the output is the transfer of this data to an analysis tool. Specifically, the device's internal sensors are activated to collect samples of the user's face and voice.

[0540] Step 2:

[0541] The device transmits the acquired video and audio data to an emotion engine for analysis of the emotional state. The input data includes the user's facial expressions and voice tone, and the output generates an emotional state (e.g., happiness, sadness). Specifically, a facial recognition algorithm (e.g., OpenCV) classifies the user's facial expressions, and a voice analysis engine (e.g., TensorFlow) evaluates the voice tone.

[0542] Step 3:

[0543] The terminal sends the analyzed emotional state data to the server. The input is the output data from the emotion engine, which is then transmitted to the server via the communication network. Specifically, the terminal's network interface is activated, and the data is securely sent to the server.

[0544] Step 4:

[0545] The server updates the profile using the user's emotional state data and preference information. The input is emotional data and the existing user profile, and the output is the updated profile. Specifically, the database management system updates the user information using the new data.

[0546] Step 5:

[0547] The server uses the updated profile to recalculate viewing priorities and scores the importance of each scene in the video. Inputs include the profile and viewing history, and output is an importance score for each scene. Specifically, a machine learning algorithm evaluates each scene and assigns a score.

[0548] Step 6:

[0549] The server selects the most suitable scenes for the user based on the scene importance score of the video and sends that information to the terminal. The input data is the score for each scene, and the output is a list of selected scenes. Specifically, the server's scheduling system works to create and send the scene list.

[0550] Step 7:

[0551] The terminal plays a video based on a scene list received from the server. The input is a scene list, and the output is continuous playback of the video for the user. Specifically, the video player selectively plays the instructed scenes, delivering the video and audio to the user.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] [Fourth Embodiment]

[0556] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0557] 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.

[0558] 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).

[0559] 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.

[0560] 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.

[0561] 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).

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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.

[0567] 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.

[0568] 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".

[0569] This invention is designed to streamline the user's video viewing experience. The system includes a program that creates a profile reflecting the user's preferences and interests, and automatically selects and plays important portions of video content.

[0570] The server receives preference data and viewing history from the user's device and uses machine learning algorithms to build a user profile based on this information. The profile includes information about specific genres, themes, and preferences. Based on this profile, the server analyzes videos that the user wishes to watch and evaluates the importance of each scene.

[0571] In video analysis, speech recognition technology is used to convert audio into text, and the analysis is performed by detecting actions and scene changes within the video. Based on this, the server assigns an importance score to each scene. The parts deemed important based on the scoring results are aggregated and designated as the scenes to be viewed.

[0572] On the device, content is provided that plays only the scenes the user is interested in, using a skip list sent from the server. This allows the user to efficiently watch only the parts that interest them in a short amount of time. In addition, new data obtained through this viewing experience is also sent to the server, and the user profile is continuously updated.

[0573] For example, if a user is particularly interested in sports, they could be provided with videos that compile only the highlights and decisive moments from weekly matches. This user can enjoy the important scenes in a short amount of time without having to watch the entire long match, resulting in a highly efficient viewing experience.

[0574] The following describes the processing flow.

[0575] Step 1:

[0576] Users access their account settings screen and enter their interests, viewing preferences, and genre preferences. This data is sent to the server via their device.

[0577] Step 2:

[0578] The server analyzes the received user preference data and viewing history, and uses machine learning algorithms to create a user profile. This profile indicates the types of content the user is predicted to be interested in.

[0579] Step 3:

[0580] When a user selects a video they want to watch, the server begins processing that video for analysis. The server uses speech recognition technology to convert the video's audio data into text and detects action and scene changes from the video data.

[0581] Step 4:

[0582] The server uses the analyzed data to score the importance of each scene, associating it with the user profile. Higher scores are assigned to scenes that are more likely to interest the user.

[0583] Step 5:

[0584] Once high-priority scenes are identified, the server groups them as scenes to be viewed and generates a list of timestamps indicating the time ranges that should be skipped.

[0585] Step 6:

[0586] The device receives a list of timestamps sent from the server and uses this list when the user plays a video to automatically skip unnecessary parts and play only the important scenes consecutively.

[0587] Step 7:

[0588] Users can efficiently watch only the parts that interest them in a short amount of time. This viewing data is then sent back to the server and used to update the user profile.

[0589] (Example 1)

[0590] 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".

[0591] In today's world, a vast amount of video content is available, and users are expected to select and watch content that matches their interests and preferences. However, there is a lack of efficient means to view the necessary information and interesting scenes, and users often get overwhelmed by a large amount of irrelevant information. This problem should be solved by developing a system that supports effective video selection and viewing based on user interests.

[0592] 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.

[0593] In this invention, the server includes means for collecting attribute data based on user preferences, means for generating user information that determines display priority based on the attribute data, and a processing device for analyzing the importance of each scene from the acquired video footage. This enables users to efficiently view content that matches their interests in a short amount of time.

[0594] "User preference-based attribute data" refers to information obtained from users' interests, preferences, past viewing history, etc., and is used to characterize the characteristics of individual users.

[0595] "User information that determines display priority" is information generated based on user attribute data, and it is an indicator that shows which content should be prioritized for viewing by the user.

[0596] A "processing device for analyzing the importance of each scene from video footage" is a hardware or software device used to divide video content into individual scenes, evaluate them, and determine their importance.

[0597] "Speech recognition technology" is a technology that analyzes audio signals as digital data and converts them into text information, and is used to understand audio within videos.

[0598] "Visual information analysis technology" is a technology used to analyze image data and understand its content, and is used to detect motion and scene changes within a video.

[0599] "Evaluation technology" refers to techniques that use transcribed audio and visual information to measure the value of each scene, and is a method used in scoring and other applications.

[0600] The system of this invention is designed to optimize the user's video viewing experience. Specifically, the server collects attribute data based on the user's preferences from the user's terminal and generates user information that determines the display priority based on this data. This process utilizes machine learning models (e.g., TensorFlow or PyTorch).

[0601] The server then analyzes the video the user wishes to watch. This analysis uses speech recognition technology (e.g., a common speech recognition API) to convert the audio in the video into text. This text data is then combined with visual information analysis technology (e.g., OpenCV) to extract changes in actions and scenes, and the analysis is performed accordingly.

[0602] To assess the importance of each scene, the server performs a comprehensive evaluation. This assigns an importance score to each scene in the video, determining which scenes are most important. The evaluated information is compiled into a skip list generated by the server and sent to the terminal.

[0603] On the device, only important scenes aligned with the user's interests are played consecutively based on the received skip list. This allows users to efficiently view content of interest in a short amount of time. Additionally, data obtained during viewing is returned to the server, updating the user profile.

[0604] For example, if a user enters the prompt "I want to see highlights from a new movie," the server can process this information and extract and provide action scenes or climactic moments from the relevant movie. This allows the user to quickly experience the overall atmosphere of the film.

[0605] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0606] Step 1:

[0607] The server collects attribute data based on user preferences from the user's device. This data includes the user's past viewing history, preferred genres, and themes. The server uses this information to build a data structure that provides a detailed understanding of the user's interests. Specifically, it receives data from the device using a data acquisition API and stores it in a database.

[0608] Step 2:

[0609] The server generates user information to determine display priority based on the collected attribute data, using a generative AI model. The input here is the user data collected in step 1, which is processed to generate a user profile, and the prioritized information is output as an analysis result. Specifically, the operation involves updating the profile based on user preferences using a machine learning algorithm.

[0610] Step 3:

[0611] The server analyzes the importance of each scene in a video that the user wishes to watch. It takes user-selected video data as input, converts the audio to text using speech recognition technology, and detects scene changes using visual information analysis technology. The output is an importance score assigned to each scene. Specifically, it uses a speech recognition API to convert the audio to text and video processing technology to analyze the scenes.

[0612] Step 4:

[0613] The server generates a skip list based on the analysis results. The input is the importance score for each scene provided in step 3. Using this, the server selects the scenes with high importance and outputs a list of scenes that the user should watch. Specifically, the scene selection algorithm generates the list based on the scoring results.

[0614] Step 5:

[0615] The device plays the video based on the skip list sent from the server. In this step, it receives input regarding the user's viewing preferences and outputs only the selected scenes sequentially. Specifically, this involves implementing a video playback function using a skip list.

[0616] Step 6:

[0617] The server receives viewing data from the terminal and updates the user profile. The input includes new data about the user's viewing behavior, which is used to update the user profile and supply the improved output with enhanced analytical accuracy to the next process. Specifically, the operation involves analyzing viewing history data and dynamically updating the profile.

[0618] (Application Example 1)

[0619] 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".

[0620] Modern content streaming services offer a vast amount of content, but users often spend a lot of time finding the important scenes that interest them. Therefore, there is a need for a system that efficiently selects the most important parts of a video according to the user's preferences, allowing for quick viewing. In particular, in their busy daily lives, users need a way to quickly consume content directly related to their interests.

[0621] 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.

[0622] In this invention, the server includes means for collecting preference information based on the user's interests, means for generating individual information to determine viewing priorities based on the preference information, means for analyzing the importance of each scene from the input video, means for providing application functions that operate on an electronic device to play back only the important scenes based on the analysis results, means for predicting new interests based on viewing history using a generation artificial intelligence model, and means for generating prompt sentences to interact with the user. As a result, the user can not only efficiently watch parts of interest in a short amount of time, but also constantly discover new interests.

[0623] "User-based preference information" refers to data that reflects a user's viewing history and preferences.

[0624] "Generating individual information to determine viewing priorities" refers to the process of determining the priority of scenes that should be viewed based on the user's preference information and generating that information.

[0625] "Analysis methods for analyzing the importance of each scene from input video" refers to methods and techniques for evaluating and analyzing the importance of each scene based on video data.

[0626] "Providing an application function that operates on an electronic device to play back only important scenes based on the analysis results" means realizing a function that uses the results of video analysis to play back selected important scenes on a specific electronic device.

[0627] "Predicting new interests based on viewing history using generative artificial intelligence models" refers to the process of using machine learning models to infer a user's potential interests from their past viewing history.

[0628] "Generating prompts to interact with the user" refers to creating interactive inquiries and instructions for the user, and using this as a means of communication.

[0629] The embodiments for carrying out this invention are shown below.

[0630] The server collects preference information and viewing history data based on user interests transmitted from the user's terminal. It then analyzes this data using a generative artificial intelligence model to generate a user profile. This profile includes individual information for determining viewing priorities. The analysis also includes a process of predicting new interests based on viewing history data. Furthermore, the server analyzes video data, utilizes speech recognition technology to convert audio data into text data to evaluate the importance of each scene, and integrates this with the visual data. This results in higher scores being assigned to scenes deemed important.

[0631] Next, the server uses the analysis results to select important scenes and creates a skip list for playback. This list is sent to the user's electronic device, and actual playback takes place on that device. As a result, the user can efficiently watch only the important scenes that are relevant to their interests.

[0632] For example, when a user who enjoys traveling watches a travel documentary, the generative AI model analyzes the user's past viewing patterns and determines that scenes related to specific regions or cultures are important. Based on this analysis, the user can automatically enjoy scenes that match their interests.

[0633] Examples of prompts for a generative AI model:

[0634] "Based on data from travel documentaries the user has previously watched, predict potential new regions they might be interested in and identify relevant scenes."

[0635] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0636] Step 1:

[0637] The server receives preference information and viewing history data transmitted from the user's terminal. This data indicates the user's interests and is the input data necessary for the server to generate the next profile. The preference information and viewing history are integrated and stored in a database.

[0638] Step 2:

[0639] The server uses a generative artificial intelligence model to analyze received preference information and viewing history data. In this process, machine learning algorithms are used to learn the user's interest patterns, and a profile is generated based on the results. The output is a user profile including viewing priorities. This profile is used for future video selection.

[0640] Step 3:

[0641] The server utilizes viewing priority information obtained from pre-configured profiles to analyze video content. It receives video data as input, converts the audio data into text data using speech recognition technology, and analyzes the emotional or visual content of each scene. This analysis calculates an importance score for each scene.

[0642] Step 4:

[0643] The server generates a skip list based on the analysis results. It creates a skip list that includes only high-priority scenes and sends this list to the device. This skip list serves as a guide to optimize the user's viewing experience.

[0644] Step 5:

[0645] The device uses a skip list received from the server to play only the scenes deemed important. Users can streamline their viewing experience by continuously playing pre-selected, interesting scenes via the device. The user's viewing results are then fed back to the server as new preference information.

[0646] 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.

[0647] This invention provides a video playback system that further personalizes the viewing experience by combining it with an emotion engine that recognizes user emotions. This system comprehensively utilizes user preference data, viewing history, and real-time emotion data to select and play the most optimal viewing scenes.

[0648] When a user watches a video, the device's emotion engine analyzes the user's facial expressions and voice tone through the camera and microphone to recognize their emotions in real time. The device then sends data about the user's current emotional state to a server. The server uses this emotion data to further refine the user profile and adjust viewing priorities.

[0649] The server analyzes the user's desired video content based on their profile and emotional data, and evaluates the importance of each scene. Importance is scored based on the characteristics of scenes the user has previously enjoyed watching and their real-time emotional state. As a result, scenes with high importance are selected for viewing.

[0650] The device smoothly plays the scenes provided by the server, efficiently delivering scenes that the user is likely to find interesting. This allows the user to enjoy an emotionally enriching video experience. In particular, if the user is clearly in a positive emotional state, the server will take full advantage of that state and prioritize selecting content that the user will enjoy more. On the other hand, if the user is in a negative emotional state, it will present content that promotes relaxation or mood improvement.

[0651] For example, if a user watching a movie displays a sad expression, the emotion engine can immediately detect this, and the server can adjust the next scene to be more positive and encouraging, thereby continuously personalizing the viewing experience.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] The user launches a video viewing application and selects the content they want to watch. At this time, the device notifies the user that it will use the camera and microphone and obtains permission for emotion recognition.

[0655] Step 2:

[0656] The emotion engine built into the device analyzes the user's facial expressions and voice tone in real time to determine their emotional state. This analysis detects emotional states such as positive, negative, and neutral.

[0657] Step 3:

[0658] The device sends recognized emotion data to the server. This data includes the type and intensity of the emotion, which the server can use to adjust the user's viewing experience.

[0659] Step 4:

[0660] The server combines emotional data and profiles received from the user to perform video analysis. It scores the importance of each scene and reprioritizes content according to the user's emotional state.

[0661] Step 5:

[0662] The server generates a skip list that reflects emotional data and selects scenes to watch. If positive emotions are detected, adjustments are made, such as selecting scenes that maintain the user's mood.

[0663] Step 6:

[0664] The device receives a skip list sent from the server and begins playback only of the specified scenes. This allows the user to have a video experience that matches their real-time emotions.

[0665] Step 7:

[0666] While the video is playing, the device continues to monitor the user's emotions and automatically provides feedback to the server as new emotion data becomes available. Based on this feedback, the server continuously updates the skip list as needed.

[0667] (Example 2)

[0668] 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".

[0669] Traditional video playback systems have limitations in personalizing content based on users' fixed preferences and viewing history, making it difficult to provide flexible video content that responds to users' changing emotions in real time. As a result, they fail to provide a viewing experience optimized for users' interests and emotions, leading to decreased viewer satisfaction.

[0670] 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.

[0671] In this invention, the server includes means for recognizing the user's emotional state, means for updating the user profile, and means for adjusting viewing priorities. This makes it possible to provide video scenes that respond to the user's changing emotions in real time.

[0672] "User emotional state" refers to information that identifies the user's emotions, acquired in real time through input devices such as cameras and microphones.

[0673] A "user profile" is a collection of personalized information that is continuously updated based on the user's preferences, viewing history, and sentiment data.

[0674] "Viewing priority" refers to the criteria used to determine the order and priority of video scenes presented to a user, based on user profiles and real-time sentiment data.

[0675] An "analysis tool" is a system component that analyzes the characteristics of each scene in the input video and calculates its importance.

[0676] "Importance" is an indicator that is evaluated by analytical methods and shows how valuable each video scene is to the user.

[0677] A "selected scene" is a specific portion of a video that has been deemed highly important through analysis and chosen for viewing.

[0678] This invention utilizes sentiment data and user profiles between the terminal and the server to personalize the user's viewing experience. Specifically, it consists of the following elements:

[0679] The device uses its camera and microphone to capture facial expressions and voice in real time while the user is watching video content. The collected data is analyzed by an emotion engine to calculate the user's emotional state. This emotional data is securely transmitted to a server.

[0680] The server integrates sentiment data submitted by the user with existing user profiles and updates the profile accordingly. Machine learning algorithms are used to update the user profile, allowing for highly accurate predictions of user preferences and emotional tendencies. Based on this profile, the server analyzes the importance of the video scenes being watched and generates viewing priorities based on real-time emotions.

[0681] The device selects and plays streaming viewing scenes based on instructions sent from the server. This allows users to enjoy content that best suits their mood at the time. In particular, if a positive emotional state is detected, content that further enhances the user's mood can be prioritized.

[0682] For example, if a user smiles slightly while watching a movie, the device detects this emotion and sends the data to the server. The server then selects a brighter scene to watch next and changes the viewing scene to provide the user with a richer viewing experience.

[0683] Appropriate prompts might include: "Please describe the design of a system that uses real-time user sentiment data to customize the video viewing experience. Please explain in detail the process for selecting viewing scenes based on the user's emotional state."

[0684] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0685] Step 1:

[0686] The device uses its camera and microphone to acquire facial expression and voice data while the user is watching a video. This is the input, from which the emotion engine collects the data necessary for processing. Specifically, the camera analyzes facial feature points, and the microphone records the pitch and tone of the voice. This data is sent to the emotion engine, which then provides an output that identifies the user's emotional state.

[0687] Step 2:

[0688] The device sends real-time sentiment data analyzed by the sentiment engine to the server. This transmission process uses a secure network protocol. The input is sentiment data output by the sentiment engine, and data consistency and privacy are maintained when it is sent to the server. The server receives this data and uses it for further profile updates.

[0689] Step 3:

[0690] The server updates the user profile based on the received sentiment data. Specifically, it integrates existing profile information, viewing history, and preference data, and generates a new profile using a machine learning algorithm. The input is new and old user data, and this data is integrated and analyzed to obtain the output of a personalized profile.

[0691] Step 4:

[0692] The server uses updated user profiles and real-time sentiment data to analyze the importance of desired viewing scenes in each video. The analysis evaluates the characteristics of each scene and assigns an importance score. The input is data about each scene in the video, and based on this, it generates output that selects the scenes with the highest importance.

[0693] Step 5:

[0694] The device receives an optimized viewing scene provided by the server and plays it back to the user without interruption. Buffering technology is used to ensure smooth playback. The final input is scene data from the server, which is then presented to the user as media output. This process provides a personalized experience tailored to the user.

[0695] (Application Example 2)

[0696] 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".

[0697] When users watch video content, there is a challenge in providing a viewing experience that is tailored to their individual tastes and emotional state. Conventional systems have been unable to appropriately adjust the content they watch based on their interests and emotions, resulting in a limited user experience.

[0698] 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.

[0699] In this invention, the server includes means for generating information to determine viewing priorities based on user preference information, means for recognizing the user's emotions in real time, and means for dynamically adjusting viewing content based on the user's emotions and preferences. This makes it possible to personalize viewing content according to the user's emotional state.

[0700] A "user" is an individual who is watching video content.

[0701] "Preference information" refers to data collected based on a user's viewing history and interests.

[0702] "Viewing priority" is an indicator that determines the order in which videos are played based on the user's preferences.

[0703] "Information" refers to the components of a user's viewing profile generated on the server.

[0704] A "scene" refers to an individual scene or segment within video content.

[0705] "Importance" is an indicator that evaluates the value each scene holds for the user's viewing experience.

[0706] "Analysis means" refers to technologies and devices for analyzing audio and visual information within video content.

[0707] "Emotional state" refers to the real-time psychological condition perceived from the user's facial expressions and tone of voice.

[0708] "Real-time recognition methods" refer to technologies that instantly detect emotions by analyzing the user's facial expressions and voice.

[0709] "A means of dynamically adjusting" refers to a function that changes the content played according to the user's emotions and viewing history.

[0710] "Personalization" means optimizing content to suit the individual user's characteristics and preferences.

[0711] To implement this invention, a system is constructed in which the user uses a smartphone or smart glasses. This system consists of an emotion engine for recognizing emotions in real time, a database for storing user preference information, and a server for analyzing and playing videos.

[0712] The system uses the smartphone's camera and microphone to collect the user's facial expressions and voice tone. This data is analyzed by an emotion engine (e.g., using image and audio analysis libraries such as OpenCV or TensorFlow) to evaluate the user's emotional state in real time. This emotional state data is then sent to a server.

[0713] The server generates a profile based on the user's preferences and viewing history. This profile is built upon an analysis of the user's past viewing history and emotional data, and this information is used to determine viewing priorities. Each scene in the content is analyzed by converting audio and visual information into text, and its importance is scored. Based on this scoring data, personalized videos are provided to the user.

[0714] For example, when a user smiles while watching a comedy film, the system prioritizes playing highly entertaining scenes. Conversely, if the user appears sad, it presents relaxing scenes to adjust the viewing experience.

[0715] An example of a prompt to a generative AI model is, "To determine the user's smile and maximize the humor level of the scene, what next scene would you recommend?" This makes it possible to automatically select the optimal content structure for the viewer.

[0716] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0717] Step 1:

[0718] The device uses its camera and microphone to acquire real-time video and audio data of the user. The input consists of video and audio data, and the output is the transfer of this data to an analysis tool. Specifically, the device's internal sensors are activated to collect samples of the user's face and voice.

[0719] Step 2:

[0720] The device transmits the acquired video and audio data to an emotion engine for analysis of the emotional state. The input data includes the user's facial expressions and voice tone, and the output generates an emotional state (e.g., happiness, sadness). Specifically, a facial recognition algorithm (e.g., OpenCV) classifies the user's facial expressions, and a voice analysis engine (e.g., TensorFlow) evaluates the voice tone.

[0721] Step 3:

[0722] The terminal sends the analyzed emotional state data to the server. The input is the output data from the emotion engine, which is then transmitted to the server via the communication network. Specifically, the terminal's network interface is activated, and the data is securely sent to the server.

[0723] Step 4:

[0724] The server updates the profile using the user's emotional state data and preference information. The input is emotional data and the existing user profile, and the output is the updated profile. Specifically, the database management system updates the user information using the new data.

[0725] Step 5:

[0726] The server uses the updated profile to recalculate viewing priorities and scores the importance of each scene in the video. Inputs include the profile and viewing history, and output is an importance score for each scene. Specifically, a machine learning algorithm evaluates each scene and assigns a score.

[0727] Step 6:

[0728] The server selects the most suitable scenes for the user based on the scene importance score of the video and sends that information to the terminal. The input data is the score for each scene, and the output is a list of selected scenes. Specifically, the server's scheduling system works to create and send the scene list.

[0729] Step 7:

[0730] The terminal plays a video based on a scene list received from the server. The input is a scene list, and the output is continuous playback of the video for the user. Specifically, the video player selectively plays the instructed scenes, delivering the video and audio to the user.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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."

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] The following is further disclosed regarding the embodiments described above.

[0753] (Claim 1)

[0754] A means of collecting preference data based on user interests,

[0755] A means for generating a profile that determines viewing priority based on the aforementioned preference data,

[0756] An analytical method for analyzing the importance of each scene from the input video,

[0757] A system that includes means for selecting scenes to be viewed based on their importance and for continuously playing only the selected scenes.

[0758] (Claim 2)

[0759] The system according to claim 1, comprising means for automatically updating the scenes to be prioritized for playback using the user's viewing history according to their preferences.

[0760] (Claim 3)

[0761] The system according to claim 1, comprising a means for importance analysis that converts audio in a video into text, analyzes it, and integrates it with visual data to perform scoring.

[0762] "Example 1"

[0763] (Claim 1)

[0764] A means of collecting attribute data based on user preferences,

[0765] A means for generating user information that determines the display priority based on the attribute data,

[0766] A processing unit for analyzing the importance of each scene from acquired video footage,

[0767] A means for selecting scenes to be viewed based on their importance and continuously displaying only the selected scenes,

[0768] This technology uses speech recognition to convert speech into text information and detects motion and scene changes within the video.

[0769] A system that includes a technology for integrating and evaluating the aforementioned textual and visual information.

[0770] (Claim 2)

[0771] The system according to claim 1, comprising means for automatically updating scenes to be displayed preferentially based on the user's viewing history according to their preferences.

[0772] (Claim 3)

[0773] The system according to claim 1, comprising means for assigning an evaluation score based on information generated using speech recognition technology and visual information analysis technology.

[0774] "Application Example 1"

[0775] (Claim 1)

[0776] A means of collecting preference information based on user interests,

[0777] means for generating individual information to determine viewing priority based on the aforementioned preference information,

[0778] An analytical means for analyzing the importance of each scene from the input video,

[0779] A means for selecting scenes to be viewed based on their importance and for continuously playing only the selected scenes,

[0780] A means to provide an application function that operates on an electronic device for replaying only important scenes based on the analysis results,

[0781] A method for predicting new interests based on viewing history using a generative artificial intelligence model,

[0782] A means of generating prompt messages and interacting with the user.

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, comprising means for automatically updating the scenes to be prioritized for playback using the user's viewing history according to their interests.

[0786] (Claim 3)

[0787] The system according to claim 1, comprising a means for importance analysis that converts auditory information in a video into textual information, analyzes it, and integrates it with visual information to perform an evaluation.

[0788] "Example 2 of combining an emotion engine"

[0789] (Claim 1)

[0790] A means of recognizing the user's emotional state,

[0791] Means for updating the user profile based on the aforementioned emotional state,

[0792] A means for adjusting viewing priority using the user profile and sentiment data acquired in real time,

[0793] An analytical method for analyzing the importance of each scene from the input video,

[0794] A system that includes means for selecting scenes to be viewed based on their importance and for continuously playing only the selected scenes.

[0795] (Claim 2)

[0796] The system according to claim 1, comprising means for automatically updating viewing priorities using the user's past viewing history and sentiment data.

[0797] (Claim 3)

[0798] The system according to claim 1, wherein the importance analysis means is equipped with means for integrating emotional data together with visual data to perform scoring.

[0799] "Application example 2 when combining with an emotional engine"

[0800] (Claim 1)

[0801] A means of collecting preference information based on user interests,

[0802] A means for generating information to determine viewing priority based on the aforementioned preference information,

[0803] An analytical means for analyzing the importance of each scene from the input video,

[0804] A means for selecting scenes to be viewed based on their importance and for continuously playing only the selected scenes,

[0805] A means of recognizing user emotions in real time,

[0806] A means of evaluating emotional states using facial expressions and voice, and transmitting the data,

[0807] A system that includes means for dynamically adjusting viewing content based on the user's emotions and preferences.

[0808] (Claim 2)

[0809] The system according to claim 1, comprising means for automatically updating scenes to be prioritized for playback using the user's viewing history according to their preferences, and optimizing the update according to the user's real-time emotions.

[0810] (Claim 3)

[0811] The system according to claim 1, further comprising a means for importance analysis that converts audio in a video into text for analysis, integrates it with visual information for scoring, and dynamically adjusts the content to be played back using emotion recognition data. [Explanation of symbols]

[0812] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting preference data based on user interests, A means for generating a profile that determines viewing priority based on the aforementioned preference data, An analytical method for analyzing the importance of each scene from the input video, A system that includes means for selecting scenes to be viewed based on their importance and for continuously playing only the selected scenes.

2. The system according to claim 1, comprising means for automatically updating the scenes to be prioritized for playback using the user's viewing history according to their preferences.

3. The system according to claim 1, comprising a means for importance analysis that converts audio in a video into text, analyzes it, and integrates it with visual data to perform scoring.

Images