Video content adjustment method and adjustment system, storage medium and electronic equipment

Abstract

The invention discloses a video content adjusting method and system, a storage medium and electronic equipment, and the method comprises the steps: reading a content tag of a video, and obtaining the biological feature data and dominant behavior data of a user; analyzing according to the biological characteristic data and the dominant behavior data, matching with the content label, and determining the content of the video; the biological characteristic data and the dominant behavior data are updated, the change trend of the data is determined, and the corresponding content label and the content of the video are updated; according to the method, analysis is performed according to the biological characteristic data and the dominant behavior data, the corresponding video content is determined, and the video content can be adjusted according to the biological characteristic data and the dominant behavior data fed back by the user in real time, so that the adjustment of the video content better meets the requirements of the user.

Description

Technical Field

[0001] This invention relates to the field of video content recommendation and adjustment, and more particularly to a method, system, storage medium, and electronic device for adjusting video content. Background Technology

[0002] With the rapid development of digital media and entertainment technologies, viewers' demand for personalized and immersive experiences is constantly increasing. Currently, short video platforms typically use recommendation algorithms to improve the user's viewing experience. These algorithms mainly rely on explicit user behavioral data, such as viewing time, likes, favorites, comments, and tipping, to infer users' interests and preferences.

[0003] While these explicit behavior-based recommendation algorithms have improved content relevance and user engagement to some extent, they still have significant limitations. First, these algorithms rely primarily on users' explicit behaviors, neglecting their immediate emotional feedback and physiological state while viewing content. This may result in recommended content failing to accurately reflect users' true interests and immediate needs in certain situations.

[0004] Users' explicit behaviors are often influenced by a variety of factors, such as social pressure, time constraints, and platform guidance, and may not fully represent their true preferences. Therefore, there is an urgent need for a new system and method that can combine users' proactive behavioral feedback and real-time changes in biometrics to achieve dynamic adjustments to video content. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a method, system, storage medium, and electronic device for adjusting video content.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for adjusting video content, comprising:

[0007] S1: Read the video's content tags and obtain the user's biometric data and explicit behavioral data;

[0008] S2: Analyze the biometric data and the overt behavioral data, match them with the content tags, and determine the content of the video;

[0009] S3: Update the biometric data and the overt behavior data, determine the trend of data change, and update the corresponding content tags and video content.

[0010] As a further description of the above technical solution: Step S1 includes:

[0011] S11: Perform feature labeling based on at least one or more video intervals to generate corresponding content tags;

[0012] S12: Obtain explicit behavioral data of users based on historical video recordings, and obtain biometric data of users based on wearable devices and cameras.

[0013] As a further description of the above technical solution: Step S2 includes:

[0014] S21: Based on the biometric data and the overt behavioral data, perform neural network training through a learning model to obtain video preference data;

[0015] S22: Based on the video preference data, identify the content tags of the matching video and determine the video content to be played.

[0016] As a further description of the above technical solution: Step S3 includes:

[0017] S31: During video playback, update the biometric data and the overt behavior data to determine the data change trend; based on the data change trend, determine the video adjustment strategy;

[0018] S32: Based on the adjustment strategy, determine the matching tags and adjust the played video and video content.

[0019] As a further description of the above technical solution: the biometric data includes changes in heart rate, blood pressure, and facial expression; the explicit behavioral data includes data on viewing time, likes, favorites, comments, and rewards.

[0020] As a further description of the above technical solution: the video preference data includes the user's emotional trends, viewing habits and content preferences, and generates a user profile, updates the video preference data, updates the user profile, and generates a content recommendation list and an emotional heatmap.

[0021] As a further description of the above technical solution: the adjustment strategy includes adjusting the video's visuals, sound effects, and playback time based on the video preference data and user profile.

[0022] It also includes a video content adjustment system, said adjustment system being applicable to any of the adjustment methods described in the above technical solutions, comprising:

[0023] The user feedback collection module acquires explicit behavioral data from users.

[0024] The biometric monitoring module acquires the user's biometric data;

[0025] The data processing module receives the overt behavioral data and the biometric data, analyzes them, and determines the trend of data change.

[0026] The content tagging module performs feature marking on video content and generates corresponding tags for at least one or more video content ranges;

[0027] The content adjustment module matches the corresponding content tags based on the changing trends of the data and adjusts the video content accordingly.

[0028] It also includes a computer-readable storage medium storing a computer program for running the adjustment method, wherein the computer program causes a computer to perform the adjustment method as described in any of the above technical solutions.

[0029] It also includes an electronic device, comprising:

[0030] One or more processors; memory; and

[0031] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including an adjustment method as described in any of the above technical solutions.

[0032] The above technical solution has the following advantages or beneficial effects:

[0033] By analyzing biometric data and overt behavioral data, corresponding video content is determined. The video content can be adjusted based on real-time feedback from users' biometric data and overt behavioral data, making the video content more in line with user needs and significantly improving user engagement and satisfaction. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 The process of the adjustment method proposed in this invention Figure 1 ;

[0036] Figure 2 The process of the adjustment method proposed in this invention Figure 2 ;

[0037] Figure 3 The process of the adjustment method proposed in this invention Figure 3 ;

[0038] Figure 4 The process of the adjustment method proposed in this invention Figure 4 ;

[0039] Figure 5 This is a schematic diagram of the adjustment system proposed in this invention.

[0040] Legend:

[0041] 1. User feedback collection module; 2. Biometric monitoring module; 3. Data processing module; 4. Content tagging module; 5. Content adjustment module. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Reference Figure 1 One embodiment of the present invention provides a method for adjusting video content, comprising:

[0044] S1: Read the video's content tags and obtain the user's biometric data and explicit behavioral data;

[0045] S2: Analyze biometric data and overt behavioral data, match them with content tags, and determine the content of the video;

[0046] S3: Update biometric data and overt behavioral data, determine data trends, and update corresponding content tags and video content.

[0047] The system identifies completed videos and obtains content tags. After video content production, it tags the content, marking features such as plot type, emotional tone, and visual style for subsequent analysis and adjustment. It also acquires explicit user behavior data, including viewing time, likes, favorites, comments, and donations. Furthermore, it uses wearable devices and cameras to obtain real-time biometric data and facial expression changes to comprehensively reflect the user's emotional state.

[0048] The system analyzes the collected explicit behavioral data and biometric data to identify users' real-time emotional states and changes in interests. It then uses machine learning models to generate video preference data and user profiles to determine the matching video content.

[0049] Update biometric and overt behavioral data, and dynamically adjust video content—including plot development, pacing, and visual effects—based on data analysis results and video content tags to match users' emotional states and enhance the viewing experience. In multi-person viewing scenarios, identify and coordinate the group's emotional states, adjusting content to achieve group emotional synchronization and enhance the immersive experience of collective viewing.

[0050] New explicit behavioral data and biometric data generated by users during viewing will be continuously collected. The system will continuously update user profiles and content tags, and optimize video content adjustment strategies to adapt to users' ever-changing needs.

[0051] Reference Figure 2 Step S1 includes:

[0052] S11: Perform feature labeling based on at least one or more video intervals to generate corresponding content tags;

[0053] S12: Obtain explicit behavioral data of users based on historical video recordings, and obtain biometric data of users based on wearable devices and cameras.

[0054] In this embodiment, different video segments contain different themes, plots, or visual elements. By analyzing these segments separately, various features of the video can be captured in greater detail. Feature labeling is performed based on the video content, including visual feature labeling, audio feature labeling, and action and behavior feature labeling. Visual feature labeling involves various visual elements in the video frame, such as colors, shapes, objects, and scenes. These visual features are automatically identified and labeled using image recognition technology and pre-trained models (such as object detection models based on convolutional neural networks). Audio feature labeling includes the type of background music (whether it is upbeat pop or soothing classical music) and speech content (such as dialogue topics, keywords, etc.). For audio features, audio recognition technology is used to extract keywords after speech-to-text conversion, or the type of background music is identified using an audio classification model. Action and behavior feature labeling is performed using pose estimation technology. The feature labeling of the video segments described above generates corresponding content tags that reflect the intuitive content of the video and provide valuable information for subsequent video retrieval, recommendation, and other applications.

[0055] Biometric data includes changes in heart rate, blood pressure, and facial expressions; overt behavioral data includes viewing time, likes, favorites, comments, and tipping. Video platforms record users' overt behaviors, and this information can be obtained through data mining of historical video records associated with user accounts. By querying and analyzing these database records, users' overt behavioral data can be extracted.

[0056] Biometric data reflects a user's physiological and subconscious reactions while watching videos, revealing deeper insights into their true feelings about the content. Wearable devices (such as smart bracelets and smartwatches) can acquire biometric data such as heart rate and skin conductance, reflecting emotional states like excitement and tension. Camera-captured facial expressions and eye gaze data reveal a user's level of concentration and emotional changes. Wearable devices collect biometric data through built-in sensors, including smart bracelets, heart rate monitors, blood pressure monitors, smart glasses, and facial expression recognition devices. These devices transmit the collected data to the user's mobile device or cloud server via Bluetooth or other wireless communication methods. For camera-captured biometric data, computer vision technologies, such as facial recognition algorithms, are used to analyze facial expressions, and eye-tracking algorithms determine the gaze point.

[0057] Reference Figure 3 In step S2, the following is included:

[0058] S21: Based on biometric data and overt behavioral data, a neural network is trained using a learning model to obtain video preference data;

[0059] S22: Based on video preference data, identify the content tags that match the video and determine the video content to be played.

[0060] In this embodiment, biometric data and overt behavioral data need to be integrated and preprocessed before being fed into the learning model. First, the data needs to be normalized to unify data of different magnitudes to the same scale. The learning model includes recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or multilayer perceptrons (MLPs) from deep learning. The preprocessed data is divided into training, validation, and test sets. The training set is used to train the neural network, allowing the model to learn patterns and rules in the data. During training, the training data is input into the neural network, and the prediction results are calculated through forward propagation. The validation set is used to monitor the model's performance and prevent overfitting. When the model's performance on the validation set no longer improves, training stops. The test set is used to evaluate the generalization ability of the trained model, ensuring that the model can accurately predict video preferences for new, unseen data, thus obtaining the final video preference data.

[0061] Video preference data includes user sentiment trends, viewing habits, and content preferences. This data is used to generate a user profile, update the video preference data and user profile, and create a content recommendation list and sentiment heatmap. Based on the video preference data, it is matched with content tags. A similarity threshold is set; only when the similarity of video content exceeds this threshold is it considered a match with the content tag and can be used as a subsequent video for playback, allowing for adjustments and switching of video content.

[0062] Reference Figure 4 In step S3, the following is included:

[0063] S31: During video playback, update biometric data and overt behavioral data to determine the trend of data change; based on the trend of data change, determine the video adjustment strategy;

[0064] S32: Based on the adjustment strategy, determine the matching tags and adjust the played video and video content.

[0065] In this embodiment, during video playback, biometric data and overt behavioral data are updated in real time. The updated biometric data is analyzed to identify trends. For example, by analyzing the heart rate data curve, if a sustained increase in heart rate over a certain period is observed, it indicates that the user is excited or nervous about the currently playing video content; while a facial expression gradually changing from a smile to a frown indicates that the user's interest in the video content is decreasing or dissatisfaction has arisen. Through continuous monitoring and analysis of this data, the dynamic changes in user emotions as the video content develops can be captured, allowing for the determination of video adjustment strategies.

[0066] The adjustment strategy includes adjusting the video's visuals, sound effects, and playback time based on video preference data and user profiles, including adjusting sound effects, screen brightness, and color saturation.

[0067] Based on the determined adjustment strategy, identify the video content tags that match the strategy, select matching videos from the video library for playback, and adjust the video content according to the adjustment strategy.

[0068] Example 1

[0069] Emotionally driven content adjustment is crucial because viewers' emotional fluctuations directly impact their viewing experience. By monitoring users' emotional states in real time, content can be dynamically adjusted to maintain user interest and engagement.

[0070] Implementation steps:

[0071] 1. Users wear heart rate monitoring devices and cameras to access the video viewing interface.

[0072] 2. The system collects users' heart rate and facial expression data in real time.

[0073] 3. Record users' explicit behavioral data, including viewing time, likes, favorites, comments, and tips.

[0074] 4. The data processing module receives and analyzes the user's biometric data and explicit behavioral data, identifies the user's emotional state and level of engagement, and executes step 5 or step 6 based on the results.

[0075] 5. When users exhibit positive emotions (expressions of joy or tension, reduced blinking) or engage in positive overt behaviors (liking or saving videos, giving positive comments, or tipping), the system will maintain the existing content or play similar content.

[0076] 6. If a user shows indifference or disinterest (with a blank expression or staring at an area outside the screen), or if the user's explicit behavior indicates a decrease in engagement (shortening the viewing time, canceling likes or favorites, giving negative comments), the system will switch to a different scenario to re-attract the user's attention.

[0077] 7. Return to step 1 until the user finishes watching.

[0078] By adjusting video content in real time based on users' emotional states and explicit behaviors, it's possible to significantly enhance user emotional engagement and viewing experience, encouraging them to continue watching and interact more with the content. This approach ensures more precise and personalized content adjustments, thereby increasing user satisfaction and viewing stickiness.

[0079] Example 2

[0080] Visual effects optimization is crucial for enhancing user immersion and viewing experience when watching videos. By monitoring users' emotional state and overt behaviors in real time, the system can dynamically adjust visual effects to improve viewing comfort and engagement.

[0081] Implementation steps:

[0082] 1. Users wear heart rate monitoring devices and cameras to access the video viewing interface.

[0083] 2. The system collects users' heart rate and facial expression data in real time.

[0084] 3. Record users' explicit behavioral data, including viewing time, likes, favorites, comments, and tips.

[0085] 4. The data processing module receives and analyzes the user's biometric data and explicit behavioral data. It identifies the user's emotional state (such as focus, fatigue) and engagement level, and executes step 5 or step 6 based on the results.

[0086] 5. When users show focus and pleasure (such as staring at the screen for a long time and having a relaxed expression) or engage in positive overt behaviors (such as watching for a long time, liking, or collecting), the content adjustment module increases the brightness and color saturation of the screen to enhance visual stimulation and immersion.

[0087] 6. If the user shows signs of fatigue or discomfort (such as frequent blinking or shifting their gaze), or if their overt behavior indicates a decrease in user engagement (such as choosing playback speed, not liking or saving), the system will reduce the screen brightness and color saturation to alleviate the user's visual burden.

[0088] 7. Return to step 1 and continue to monitor and adjust the visual effects until the user finishes watching.

[0089] By dynamically optimizing visual effects by combining users' emotional state and explicit behaviors, the system can significantly improve users' viewing comfort and immersive experience, and prevent users from becoming fatigued or bored too quickly.

[0090] Example 3

[0091] Sound effects adjustment is crucial for creating atmosphere and conveying emotions when watching videos. By monitoring users' emotional state and overt behaviors in real time, the system can dynamically adjust sound effects to enhance the user's emotional experience and engagement.

[0092] Implementation steps:

[0093] 1. Users wear heart rate monitoring devices and cameras to access the video viewing interface.

[0094] 2. The system collects users' heart rate and facial expression data in real time.

[0095] 3. Record users' explicit behavioral data, including viewing time, likes, favorites, comments, and tips.

[0096] 4. The data processing module receives and analyzes the user's biometric data and overt behavioral data.

[0097] Identify the user's emotional state (such as excitement, stress) and level of engagement, and proceed to step 5 or step 6 based on the results.

[0098] 5. When users show excitement and pleasure (such as increased heart rate and focused expression) or engage in positive overt behaviors (such as liking or tipping), the content adjustment module maintains the intensity of sound effects and background music to preserve the emotional expression and atmosphere.

[0099] 6. If a user exhibits stress or anxiety (such as abnormal heart rate or facial tension), or if overt behaviors indicate reduced user engagement (such as reduced viewing time or negative comments), the content adjustment module will lower the volume and play soothing background music to alleviate the user's anxiety.

[0100] 7. Return to step 1 and continue monitoring and adjusting the sound effects until the user finishes watching.

[0101] By dynamically adjusting sound effects based on the user's emotional state and overt behavior, the system can significantly enhance the user's emotional experience and viewing satisfaction. This method ensures that the sound effects are in harmony with the user's psychological and emotional state.

[0102] Example 4

[0103] User profile updates and real-time content recommendations are crucial because users' interests and emotional states can change at any time during video viewing. By collecting and analyzing users' behavioral and biometric data in real time, the system can dynamically update user profiles and provide personalized content recommendations based on the latest information to better meet users' immediate needs.

[0104] Implementation steps:

[0105] 1. Users wear heart rate monitoring devices and cameras to access the video viewing interface.

[0106] 2. The system collects users' heart rate, facial expression data, and explicit behavioral data (such as viewing time, likes, favorites, comments, and tips) in real time.

[0107] 3. The data processing module receives and comprehensively analyzes the user's biometric data and explicit behavioral data. It identifies the user's current emotional state and interests.

[0108] 4. Based on the analysis results, the system updates user profiles in real time, recording changes in user emotional trends, viewing habits, and content preferences. The updated user profiles reflect users' immediate reactions and engagement with different types of storylines.

[0109] 5. Using the updated user profiles, the system generates personalized content recommendation lists.

[0110] 6. Recommend and play video content that matches the user's current emotional state and interests.

[0111] 7. Returning to step 1, the system continues to monitor the user's emotional state and explicit behavioral feedback, further updating the user profile and adjusting strategies until the user finishes watching.

[0112] By adjusting content in real time and updating user profiles, the system can respond promptly to changes in user interests and emotions, providing viewing options that better meet user needs. This approach ensures accurate and personalized content recommendations, improving user satisfaction and engagement.

[0113] Example 5

[0114] Multi-user emotional synchronization enhances the viewing experience in a social video-watching environment. By analyzing the emotional states of multiple users in real time, the system can create a shared viewing experience, making interactions between users more vivid and engaging.

[0115] Implementation steps:

[0116] 1. Multiple users access the same video viewing interface through their respective devices (such as smartphones, tablets, or smart TVs) and wear heart rate monitoring devices and cameras.

[0117] 2. The system collects real-time biometric data (such as heart rate and facial expression) and explicit behavioral data (such as viewing time and interaction frequency) from each user.

[0118] 3. The data processing module simultaneously analyzes the biometric and behavioral data of all users to identify each user's current emotional state and interests.

[0119] 4. The system aggregates users' emotional states to generate an "emotional heatmap," displaying the emotional trends of all users during the viewing process. This heatmap uses color intensity and different shades to represent these emotional trends. For example, the X-axis represents viewing time, the Y-axis represents different emotional states (such as happiness, sadness, excitement, etc.), and the color intensity represents the strength of the emotion.

[0120] 5. Based on the emotional heatmap, the system adjusts the playback rhythm and content of the video in real time. For example, if most users show strong excitement or emotion during a certain scene, the system can extend the playback time of that scene or add interactive elements to enhance the collective experience.

[0121] 6. During the viewing process, the system will recommend interactive content that matches the user's current emotional state based on the user's emotional synchronization, such as voting, bullet screen discussions, or character interactions, to encourage communication and interaction among users.

[0122] 7. Return to step 1 and continue monitoring. When the user's emotional state changes, the system will update the emotional heatmap in real time and adjust the playback strategy according to the new emotional trend to ensure the continuity and interactivity of the viewing experience.

[0123] By synchronizing emotions among multiple users, the system not only enhances the social interactivity of video viewing but also strengthens user immersion and engagement. This approach makes the viewing experience more personalized and engaging, promoting emotional connection and sharing among users. The application of emotion heatmaps provides users with intuitive feedback on their emotional state, enhancing interaction and participation during the viewing process.

[0124] Reference Figure 5It also includes an embodiment of a video content adjustment system, which is applicable to any of the adjustment methods described above, including:

[0125] User feedback collection module 1 acquires explicit behavioral data of users;

[0126] Biometric monitoring module 2 acquires the user's biometric data;

[0127] Data processing module 3 receives and analyzes overt behavioral data and biometric data to determine the trend of data changes.

[0128] Content tagging module 4 performs feature tagging on video content and generates corresponding tags for at least one or more video content ranges.

[0129] Content adjustment module 5 adjusts the video content based on the data's changing trends and matching the corresponding content tags.

[0130] In this embodiment, the user feedback collection module 1 records explicit user behavior data, including viewing time, likes, favorites, comments, and donations. This data is used to infer user interests and preferences and capture user interaction behavior, helping the system understand the needs of the audience.

[0131] The biometric monitoring module 2 acquires real-time changes in the user's biometric data through wearable devices (such as smart bracelets and heart rate monitors) and cameras. The biometrics monitored by this module include heart rate, blood pressure, and facial expressions, used to assess the user's emotional state while watching short videos.

[0132] Data processing module 3 utilizes artificial intelligence algorithms to comprehensively analyze the collected explicit behavioral data and biometric data. Through machine learning models, it identifies users' real-time emotional states and changes in interests, thereby generating personalized content adjustment suggestions.

[0133] The content tagging module 4 tags the content during the video production stage, marking it according to features such as plot type, emotional tone, and visual style, and generating corresponding tag information to improve the matching degree between content and user profile, and ensure the relevance of recommended content.

[0134] Based on the analysis results and content tags from the data processing module 3, the content adjustment module 5 dynamically adjusts the video content, including plot development, pacing changes, and visual effects. In this way, the system can respond to users' emotional changes in real time, improving user immersion and satisfaction.

[0135] It also includes a computer-readable storage medium storing a computer program for running the adjustment method, wherein the computer program causes the computer to perform the following steps:

[0136] S1: Read the video's content tags and obtain the user's biometric data and explicit behavioral data;

[0137] S2: Analyze biometric data and overt behavioral data, match them with content tags, and determine the content of the video;

[0138] S3: Update biometric data and overt behavioral data, determine data trends, and update corresponding content tags and video content.

[0139] The computer-readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of a computer program from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a computer-readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be a component of the processor. The processor and the computer-readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the ASIC can reside in a user equipment. Of course, the processor and the computer-readable storage medium can also exist as discrete components in a communication device.

[0140] Specifically, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0141] It also includes an electronic device, comprising:

[0142] One or more processors; memory; and

[0143] One or more programs, wherein the programs are stored in memory and configured to be executed by one or more processors, the programs comprising the steps of performing the following:

[0144] S1: Read the video's content tags and obtain the user's biometric data and explicit behavioral data;

[0145] S2: Analyze biometric data and overt behavioral data, match them with content tags, and determine the content of the video;

[0146] S3: Update biometric data and overt behavioral data, determine data trends, and update corresponding content tags and video content.

[0147] A memory is used to store computer programs. This memory may include high-speed random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0148] A processor is used to execute computer programs stored in memory. The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0149] Alternatively, the memory can be either standalone or integrated with the processor.

[0150] When memory is a device independent of the processor, electronic devices may also include a bus. This bus is used to connect the memory and the processor. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc.

[0151] It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the prior art, can be embodied in the form of software products. These computer software products can be stored in computer-readable storage media, such as ROM / RAM, magnetic disks, optical disks, etc., and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or certain portions of the embodiments. In this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In the absence of further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0152] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for adjusting video content, characterized in that, include: S1: Read the video's content tags and obtain the user's biometric data and explicit behavioral data; S2: Analyze the biometric data and the overt behavioral data, match them with the content tags, and determine the content of the video; S3: Update the biometric data and the overt behavior data, determine the trend of data change, and update the corresponding content tags and video content.

2. The adjustment method according to claim 1, characterized in that: Step S1 includes: S11: Perform feature labeling based on at least one or more video intervals to generate corresponding content tags; S12: Obtain explicit behavioral data of users based on historical video recordings, and obtain biometric data of users based on wearable devices and cameras.

3. The adjustment method according to claim 1, characterized in that: Step S2 includes: S21: Based on the biometric data and the overt behavioral data, perform neural network training through a learning model to obtain video preference data; S22: Based on the video preference data, identify the content tags of the matching video and determine the video content to be played.

4. The adjustment method according to claim 1, characterized in that: Step S3 includes: S31: During video playback, update the biometric data and the overt behavior data to determine the data change trend; based on the data change trend, determine the video adjustment strategy; S32: Based on the adjustment strategy, determine the matching tags and adjust the played video and video content.

5. The adjustment method according to claim 1, characterized in that: The biometric data includes data on changes in heart rate, blood pressure, and facial expressions; the explicit behavioral data includes data on viewing time, likes, favorites, comments, and donations.

6. The adjustment method according to claim 3, characterized in that: The video preference data includes users' emotional trends, viewing habits, and content preferences, and generates a user profile. The video preference data is then updated, the user profile is updated, and a content recommendation list and an emotional heatmap are generated.

7. The adjustment method according to claim 4, characterized in that: The adjustment strategy includes adjusting the video's visuals, sound effects, and playback time based on the video preference data and user profiles.

8. A video content adjustment system, characterized in that, The adjustment system is applicable to the adjustment method described in any one of claims 1-7, comprising: The user feedback collection module acquires explicit behavioral data from users. The biometric monitoring module acquires the user's biometric data; The data processing module receives the overt behavioral data and the biometric data, analyzes them, and determines the trend of data change. The content tagging module performs feature marking on video content and generates corresponding tags for at least one or more video content ranges; The content adjustment module matches the corresponding content tags based on the changing trends of the data and adjusts the video content accordingly.

9. A computer-readable storage medium, characterized in that, It stores a computer program for running the adjustment method, wherein the computer program causes the computer to perform the adjustment method as described in any one of claims 1-7.

10. An electronic device, characterized in that, include: One or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including methods for performing the adjustment method as described in any one of claims 1-7.

Images