Object attribute dynamic configuration method for digital media multiple platforms

Abstract

The invention relates to the technical field of digital media processing, in particular to an object attribute dynamic configuration method for digital media multiple platforms. According to the scheme, aiming at the configuration problem caused by the difference of technical specifications when digital media are displayed on different platforms, platform feature vectors containing composite features are generated by collecting and analyzing the technical specifications of the platforms in real time; establishing a nonlinear conversion model from the basic attributes of the object to the specific attributes of the platform by using a multi-layer perceptron; a subscription-publishing architecture containing a subscription management module, a message publishing module and a message distribution module is constructed, so that a digital media object can subscribe to a platform strategy change notification; and when the notification is received, triggering configuration re-calculation, applying the new attribute to the object and updating the configuration information. The method can dynamically adapt to the standard change of the platform, improves the management efficiency and display effect of the digital media content, has the advantages of high universality, high configuration accuracy and the like, and effectively meets the multi-platform digital media transmission requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of digital media processing, and in particular to a method for dynamically configuring object attributes for digital media multi-platforms. Background Art

[0002] With the rapid development of digital media technology, digital media content needs to be displayed and disseminated on many different platforms, such as televisions, computers, mobile phones, tablets, etc. However, different platforms have significant technical specifications in terms of color space, file format, compression format, file size, encryption method, frame rate, and resolution.

[0003] Traditional methods for configuring digital media object properties are often static, requiring a one-time configuration based on the requirements of a specific platform after content production is complete. This approach requires re-production and re-configuration of digital media content whenever the platform's technical specifications change. This not only consumes significant time and resources, but also results in inconsistent display effects across different platforms, failing to meet user demands for a high-quality digital media experience. Summary of the Invention

[0004] The present invention provides a method for dynamically configuring object attributes for digital media multi-platforms. The method generates platform feature vectors by real-time parsing the technical specifications of each platform, establishes a nonlinear conversion model from basic object attributes to platform-specific attributes using a multi-layer perceptron, and adopts a subscription-publish model to receive platform policy change notifications to trigger configuration recalculation, thereby realizing dynamic configuration of digital media object attributes and improving the display effect and management efficiency of digital media content on different platforms.

[0005] A method for dynamically configuring object attributes for digital media multi-platforms, comprising:

[0006] S1. Technical specification collection and feature vector generation: Through web crawlers, API calls, or access to official platform documents, collect the technical specifications of each platform in terms of color space, file format, compression format, file size, encryption method, frame rate, and resolution in real time, parse this information, and generate platform feature vectors.

[0007] Preferably, for color space, collect detailed parameters such as its standard name, color gamut range, white point coordinates, gamma correction curve, etc.; for file format, collect file encoding method, extension, supported metadata, etc.; for compression format, understand the compression algorithm used (such as JPEG, PNG compression algorithm) and compression ratio range; for file size, obtain the maximum and minimum allowed values ​​for a single file; for encryption method, clarify the encryption algorithm used (such as AES, RSA) and encryption key management method; for frame rate, determine the number of frames per second of video playback; for resolution, obtain the number of horizontal and vertical pixels of the image or video.

[0008] Optimally, the collected raw information is collated and standardized, converting data in different formats into a unified mathematical model or quantitative indicator. A platform feature vector is then constructed based on the parsed data, with each dimension of the vector corresponding to a key technical characteristic parameter.

[0009] Preferably, the process of generating the feature vector includes combining the collected features to construct new features, specifically including:

[0010] Based on feature calculation, comprehensive features of frame rate and resolution and comprehensive features of file size and compression ratio are constructed;

[0011] The frame rate and resolution comprehensive feature measures the information density of the video content per unit time through the combined features of frame rate and resolution; the file size and compression ratio comprehensive feature reflects the compressed file status on different platforms through the combined features of file size and compression ratio.

[0012] Based on feature cross-construction, color space, encryption method and file format cross-features as well as frame rate, resolution and compression format cross-features are constructed;

[0013] Among them, the color space, encryption method and file format cross-features comprehensively consider the three aspects of color space, encryption method and file format, and construct cross-features to reflect the commonly used file formats under specific color space and encryption method; the frame rate, resolution and compression format cross-features combine frame rate, resolution and compression format to reflect the characteristics of commonly used compression formats under different frame rates and resolutions.

[0014] Preferably, the specific method for constructing the frame rate and resolution comprehensive feature based on feature calculation is to calculate the product of frame rate and resolution, and then perform normalization processing. The result is the frame rate and resolution comprehensive feature, which is defined as the information density of the video content per unit time. The specific calculation formula is:

[0015]

[0016] Where FR is the frame rate, H is the number of horizontal pixels, V is the number of vertical pixels, and Hmax 、V max and FR max are the maximum values ​​of vertical pixel count, horizontal pixel count, and frame rate of the resolution in the considered platform, respectively.

[0017] Preferably, the specific method for constructing the comprehensive feature of file size and compression ratio based on feature calculation is to calculate the product of file size and compression ratio, and then perform normalization processing. The result is the comprehensive feature of file size and compression ratio, which is used to reflect the situation after file compression on different platforms. The specific calculation formula is:

[0018]

[0019] In the formula, S is the file size, CR is the file compression ratio, S max The maximum file size allowed on the platform, CR max It is the maximum compression ratio in the platform.

[0020] Preferably, the specific method of constructing the color space, encryption method and file format cross-features based on feature intersection is:

[0021] Assume that the color space gamut range is represented by C, the encryption method is represented by E after label encoding, and the file format is represented by F=[f1,f2,…,f n ], then the combined color space, encryption method and file format cross feature vector is:

[0022]

[0023] Preferably, the specific method of constructing the frame rate, resolution and compression format cross-features based on feature cross-features is:

[0024] Assume that the frame rate is FR, the resolution is represented by the number of horizontal pixels H and the number of vertical pixels V, and the compression format is represented by Z after label encoding. Then the combined cross feature vector of frame rate, resolution and compression format is

[0025] S2. Establishment of nonlinear conversion model: Based on the generated platform feature vector, a multi-layer perceptron model architecture is selected to establish a nonlinear conversion model from the basic attributes of the object to the platform-specific attributes.

[0026] Preferably, the multi-layer perceptron model architecture consists of an input layer, a hidden layer and an output layer. The input layer receives the basic attributes and platform feature vectors of the digital media object. The hidden layer contains multiple neurons and performs nonlinear transformation on the input information through an activation function. The output layer outputs the predicted platform-specific attributes. A large amount of sample data is used during training, and the error gradient is calculated through the back propagation algorithm, and the weights and biases of the network are updated to make the model prediction results close to the actual platform-specific attributes.

[0027] S3. Implementation of the subscription-publish model: Adopt the subscription-publish model to allow digital media objects to subscribe to policy change notifications of various platforms.

[0028] Preferably, the subscription-publishing model is implemented based on the digital media object management system. When the platform technical specifications change, a notification containing the changed technical specification type and the specific parameter values ​​before and after the change will be sent to the system's message publishing module. The system pushes the notification to the corresponding object through the message distribution module based on the subscription information of the digital media object.

[0029] S4. Configuration recalculation trigger: After receiving the platform policy change notification, the digital media object parses the change information in the notification and generates a new platform feature vector.

[0030] Preferably, after the recalculation of the object attributes is completed, the newly calculated specific attributes are applied to the digital media object, and the configuration information of the object stored in the digital media object management system database on the platform is updated, including the new specific attributes, the platform to which it belongs, and the update time, etc., to ensure that the display and distribution of the object on the platform complies with the latest technical specifications.

[0031] Compared with the prior art, the advantages of the present invention are:

[0032] Strong dynamic adaptability: The present invention can respond to changes in the technical specifications of various platforms in real time. Through a subscription-publishing model, it promptly obtains change information and triggers the recalculation of object attribute configurations. This allows the attributes of digital media objects to dynamically adapt to the requirements of different platforms, ensuring consistency and optimal display effects of content across different platforms.

[0033] Improved efficiency: This approach avoids the tedious process of reproducing and reconfiguring content when platform technical specifications change, saving significant time and resources. It also improves the management efficiency of digital media content through automated configuration recalculation.

[0034] High accuracy: The nonlinear conversion model built using a multi-layer perceptron can learn the complex nonlinear mapping relationship between basic object attributes and platform-specific attributes, thereby more accurately converting basic object attributes into specific attributes suitable for different platforms, improving configuration accuracy;

[0035] Good versatility: The present invention is applicable to various types of digital media objects and multiple different platforms, and has strong versatility. By extracting the key features of the platform and establishing a universal conversion model, it can handle the differences between different platforms in color space, file format, etc. DETAILED DESCRIPTION

[0036] In one embodiment, a method for dynamically configuring object attributes for a digital media multi-platform is provided, specifically comprising:

[0037] Platform technical specification collection and feature vector generation:

[0038] Collect technical specifications for each platform:

[0039] Platform A: The color space is sRGB, the relative value of the color gamut is 0.9, and the supported file formats are MP4 and JPEG. The commonly used compression format is H.264 encoding (compression ratio range is 0.3-0.5). The maximum allowed file size is 10MB, and the encryption method uses the AES algorithm. The video frame rate is commonly 30fps, and the resolution is mainly 1920×1080.

[0040] Platform B: The color space is AdobeRGB, the relative value of the color gamut is 0.95, and the supported file formats are AVI and PNG. The commonly used compression format is VP9 encoding (compression ratio range is 0.4-0.6). The maximum allowed file size is 8MB, and the encryption method uses the RSA algorithm. The video frame rate is commonly 60fps, and the resolution is mainly 3840×2160.

[0041] Platform C: The color space is P3, the relative value of the color gamut range is 0.85, and the supported file formats are MOV and TIFF. The commonly used compression format is HEVC encoding (compression ratio range is 0.2-0.4), the maximum allowed file size is 12MB, the encryption method uses the SM2 algorithm, the video frame rate is commonly 24fps, and the resolution is mainly 1280×720.

[0042] Data preprocessing and feature extraction:

[0043] Normalizing the color gamut of the color space can be done by dividing the color gamut value of each platform by the maximum color gamut value (assuming that the maximum color gamut relative value of all possible platforms is 1).

[0044] Perform one-hot encoding on the file formats. For example, the MP4 of platform A is encoded as [1,0] (assuming there are only two formats to compare), the AVI of platform B is encoded as [1,0], and the MOV of platform C is encoded as [1,0] (similarly, encode the two formats supported by each platform).

[0045] Also perform appropriate encoding conversion on compression format, encryption method, etc.;

[0046] Extract numerical features such as file size, frame rate, and resolution, and perform standardization.

[0047] Construct composite features and platform feature vectors:

[0048] Frame rate and resolution comprehensive characteristics (information density): Calculate the information density of each platform according to the formula. Take platform A as an example, its frame rate FR = 30, resolution H = 1920, V = 1080, assuming the maximum frame rate FR among all platforms max =60, maximum horizontal pixel number H max =3840, maximum vertical pixel number V max =2160, then the information density Similarly, calculate the information density values ​​of platform B and platform C and use them as part of the composite feature;

[0049] Comprehensive characteristics of file size and compression ratio (actual size expected after compression): Taking platform A as an example, assuming file size S = 5MB, compression ratio CR = 0.4, and maximum file size S max =10MB (the maximum file size allowed by platform A), maximum compression ratio CR max =0.5 (the maximum value of the compression ratio range of platform A), then the actual size expected value after compression Similarly, calculate the corresponding values ​​of platform B and platform C and add them to the composite feature;

[0050] Color space, encryption method and file format cross-features: Taking platform A as an example, the color space gamut range is standardized to 0.9, the encryption method AES encoding is 0, and the file format MP4 one-hot encoding is [1,0]. The cross-feature vector is: According to this method, the corresponding cross-feature vectors of platform B and platform C are constructed;

[0051] Frame rate, resolution and compression format cross-features: Taking platform A as an example, the frame rate is 30fps, the resolution is 1920×1080, and the compression format H.264 is encoded as 0. The cross-feature vector is constructed as follows: According to this method, the corresponding cross-feature vectors of platform B and platform C are constructed;

[0052] Finally, the above basic features and composite features are combined in a predetermined order to generate a complete platform feature vector for each platform.

[0053] Nonlinear transformation model establishment:

[0054] Model architecture determination: A multi-layer perceptron is used to establish a nonlinear conversion model. The number of neurons in the input layer is determined according to the dimension of the platform feature vector (including basic features and composite features) and the dimension of the basic attributes of the digital media object. Assuming that the dimension of the platform feature vector after integration is 20, and the dimension of the basic attributes of the object such as general color values ​​and basic sizes is 5, the number of neurons in the input layer is 25. Set up two hidden layers, the number of neurons in the first hidden layer is set to 50, and the activation function uses the ReLU function; the number of neurons in the second hidden layer is set to 30, and the ReLU function is also used. The number of neurons in the output layer is determined according to the dimension of the platform-specific attributes. Assuming that the platform-specific attribute dimension is 10, the output layer has 10 neurons, and the activation function selects the appropriate output format according to the specific output attribute characteristics;

[0055] Model training: Collect a large amount of sample data corresponding to different digital media objects on different platforms. This data covers the feature vectors, basic object properties, and corresponding platform-specific properties of different platforms. Use mean squared error as the loss function and the Adam optimization algorithm for model training. Set an appropriate learning rate (e.g., 0.001) and a training round number of 1000. During training, continuously adjust the model weight parameters to gradually reduce the loss function value and converge to a convergence.

[0056] Implementation of the publish-subscribe model:

[0057] Build a subscription-publishing architecture in the digital media object management system. The digital media object sends a subscription request to the system's subscription management module, indicating that it wants to subscribe to policy change notifications from platforms A, B, and C.

[0058] When Platform A updates its technical specifications, for example, by increasing the maximum supported file size to 15MB or changing the encryption method to a new self-developed encryption algorithm (and performing corresponding code updates), Platform A encapsulates these changes into standard messages through the message publishing module and sends them to the message middleware of the digital media object management system.

[0059] The message distribution module accurately pushes the change notification of platform A to each digital media object that has subscribed to the platform based on the previous subscription record of the digital media object.

[0060] Configure recalculation trigger and application:

[0061] After receiving the policy change notification from platform A, the digital media object parses the change information in the notification and regenerates a new platform feature vector according to the above method;

[0062] The trained multi-layer perceptron model is called, taking the basic attributes of the digital media object and the new platform feature vector as input. The model calculates and outputs the specific attributes of the object under the new technical specifications of Platform A. For example, for a video object, the model might recalculate video encoding parameters and frame rate adjustments that are suitable for the new file size limit, encryption method, and other specifications.

[0063] In another embodiment, the process includes a continuous monitoring and feedback optimization step, specifically implemented as follows:

[0064] After the digital media object is displayed and disseminated on the platform according to the new configuration, a continuous monitoring mechanism is activated to continuously evaluate the configuration effect of the digital media object by collecting feedback information from the user end (such as user evaluation, playback time, number of playback interruptions, etc.) and performance data from the system end (such as network transmission rate, server load, etc.);

[0065] Based on the analysis of the collected data, if it is found that there are widespread problems such as poor image quality, playback lag, or certain configuration attributes have caused system performance bottlenecks during actual operation, the relevant information will be fed back to the nonlinear conversion model training link. Using these actual feedback data as supplementary samples, the model will be further optimized and trained, and the parameters and structure of the model will be adjusted to enable it to more accurately generate platform-specific attributes that are in line with actual usage scenarios and have better effects, thereby continuously improving the display quality and overall performance of digital media objects on various platforms.

[0066] Apply these new specific attributes to the digital media object, such as re-encoding video files according to the new encoding parameters, adjusting image files according to the new color space and size requirements, etc. At the same time, update the configuration information of the digital media object stored in the management system database on Platform A, recording the new specific attributes, the platform to which it belongs, and the update time, etc., to ensure that the subsequent display and distribution of the object on Platform A complies with the latest technical specifications.

[0067] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0068] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for dynamically configuring object attributes for digital media multi-platforms, characterized in that: include: S1. Technical Specification Collection and Feature Vector Generation: Through web crawlers, API calls, or access to official platform documentation, we collect the technical specifications of each platform in terms of color space, file format, compression format, file size, encryption method, frame rate, and resolution in real time, and parse this information to generate platform feature vectors. S2. Nonlinear conversion model establishment: Based on the generated platform feature vector, a multi-layer perceptron model architecture is selected to establish a nonlinear conversion model from basic object attributes to platform-specific attributes; S3. Subscribe-Publish Model Implementation: Adopt the subscribe-publish model to allow digital media objects to subscribe to policy change notifications of various platforms; S4. Configuration recalculation trigger: After receiving the platform policy change notification, the digital media object parses the change information in the notification and generates a new platform feature vector.

2. The method for dynamic configuration of object attributes for digital media multi-platform according to claim 1, characterized in that: The process of generating the feature vector includes combining the collected features to construct new features, specifically including: Based on feature calculation, comprehensive features of frame rate and resolution and comprehensive features of file size and compression ratio are constructed; The frame rate and resolution comprehensive feature measures the information density of the video content per unit time through the combined features of frame rate and resolution; the file size and compression ratio comprehensive feature reflects the compressed file status on different platforms through the combined features of file size and compression ratio. Based on feature cross-construction, color space, encryption method and file format cross-features as well as frame rate, resolution and compression format cross-features are constructed; Among them, the color space, encryption method and file format cross-features comprehensively consider the three aspects of color space, encryption method and file format, and construct cross-features to reflect the commonly used file formats under specific color space and encryption method; the frame rate, resolution and compression format cross-features combine frame rate, resolution and compression format to reflect the characteristics of commonly used compression formats under different frame rates and resolutions.

3. The method for dynamic configuration of object attributes for digital media multi-platform according to claim 2, characterized in that: The specific method for constructing the frame rate and resolution comprehensive feature based on feature calculation is to calculate the product of frame rate and resolution, and then perform normalization processing. The result is the frame rate and resolution comprehensive feature, which is defined as the information density of the video content per unit time. The specific calculation formula is: Where FR is the frame rate, H is the number of horizontal pixels, V is the number of vertical pixels, and H max 、V max and FR max are the maximum values ​​of vertical pixel count, horizontal pixel count, and frame rate of the resolution in the considered platform, respectively.

4. The method for dynamic configuration of object attributes for digital media multi-platform according to claim 2, characterized in that: The specific method for constructing the comprehensive feature of file size and compression ratio based on feature calculation is to calculate the product of file size and compression ratio, and then perform normalization processing. The result is the comprehensive feature of file size and compression ratio, which is used to reflect the situation after file compression on different platforms. The specific calculation formula is: In the formula, S is the file size, CR is the file compression ratio, S max The maximum file size allowed on the platform, CR max It is the maximum compression ratio in the platform.

5. The method for dynamic configuration of object attributes for digital media multi-platform according to claim 2, characterized in that: The specific method of constructing color space, encryption method and file format cross features based on feature cross is: Assume that the color space gamut range is represented by C, the encryption method is represented by E after label encoding, and the file format is represented by F=[f1,f2,…,f n ], then the combined color space, encryption method and file format cross feature vector is:

6. The method for dynamically configuring object attributes for digital media multi-platforms according to claim 2, characterized in that: The specific method of constructing the frame rate, resolution and compression format cross-features based on feature cross-construction is: Assume that the frame rate is FR, the resolution is represented by the number of horizontal pixels H and the number of vertical pixels V, and the compression format is represented by Z after label encoding. Then the combined cross feature vector of frame rate, resolution and compression format is 7. The method for dynamic configuration of object attributes for digital media multi-platform according to claim 1, characterized in that: The multi-layer perceptron model architecture consists of an input layer, a hidden layer, and an output layer. The input layer receives the basic attributes of digital media objects and platform feature vectors. The hidden layer contains multiple neurons and performs nonlinear transformation on the input information through activation functions. The output layer outputs predicted platform-specific attributes. A large amount of sample data is used during training, and the error gradient is calculated through the backpropagation algorithm. The network weights and biases are updated to make the model prediction results close to the actual platform-specific attributes.

8. The method for dynamic configuration of object attributes for digital media multi-platforms according to claim 1, characterized in that: After the object attributes are recalculated, the newly calculated specific attributes are applied to the digital media object, and the configuration information of the object stored in the digital media object management system database on the platform is updated, including the new specific attributes, the platform to which it belongs, and the update time, etc., to ensure that the display and distribution of the object on the platform complies with the latest technical specifications.

Images