User creation content management method

Abstract

The invention discloses a user creation content management method, which comprises the following steps: obtaining first creation content of a user based on resource creation on a creation platform, the first creation content comprising a resource category and a resource combination rule; the resource category comprises a first category and a second category, and the combination rule is a resource placement sequence and a resource placement position in the creation content editor; obtaining a rendered image based on the first creation content of the user; determining a first approximation degree of the first authoring content and other authoring content in a content database based on the rendered image and the authoring content; storing the first creation content of the user to the resource database of the first category or the resource database of the second category based on the first approximation degree; the first category corresponds to a preset resource or a resource whose similarity to the preset resource is lower than a first threshold value, and is open to a user of the creation platform, and the second category is visible to a creator of the resource. According to the technical scheme, the management efficiency and the copyright protection capability of the content created by the user are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of content management, and in particular to a method for managing user-generated content. Background Art

[0002] With the rapid development of user-generated content (UGC) platforms, the types of content created by users are becoming more and more diverse, covering a variety of resource types such as pictures, audio, and video. In the prior art, the classification and storage of created content mostly rely on users to manually add tags or classify them into preset categories. This traditional method has the problems of low classification accuracy and insufficient efficiency, especially when faced with a large amount of complex content, which can easily lead to classification errors. In addition, manual operations also increase the burden on users and make it difficult to ensure efficient management of large-scale content platforms. At the same time, users often reuse the same or similar resources when creating content, and the platform is filled with a large amount of duplicate or similar content, resulting in a waste of storage resources and a decrease in retrieval efficiency. The existing duplicate content management mechanism is relatively weak and cannot effectively deduplicate and optimize storage.

[0003] Another prominent issue is the inadequate copyright and authorization management. Existing platforms lack a strict review mechanism for the resource licensing status of user-generated content, especially for the management of open and private resources. Unauthorized resources are easily disclosed, increasing the risk of copyright disputes. Existing technologies are unable to automatically detect the authorization type of resources before storing content, resulting in imperfect resource management. In addition, existing content retrieval mostly relies on keywords and tags, and cannot accurately match based on the feature vectors of the content. Users often find it difficult to obtain satisfactory results when searching for similar content. With the rapid increase in the amount of content on the platform, intelligent content classification, management, and retrieval methods have become an urgent technical need. Summary of the invention

[0004] At least one aspect or advantage of the invention will be set forth in part in the following description, or may be obvious from the description, or may be learned by practice of the disclosed subject matter.

[0005] According to a first aspect of the present invention, a method for managing user-generated content includes:

[0006] Acquire a first creative content created by a user on a creative platform based on resources, wherein the first creative content includes a resource category and a resource combination rule; the resource category includes a first category and a second category, and the combination rule is a resource placement order and a resource placement position in a creative content editor;

[0007] Acquire a rendered image based on the first creative content of the user;

[0008] determining a first similarity between the first creative content and other creative content in the content database based on the rendered image and the creative content;

[0009] Saving the user's first creative content to a resource database of a first category or a resource database of a second category based on the first similarity;

[0010] The first category corresponds to a preset resource or a resource whose similarity to the preset resource is lower than a first threshold and is open to users of the creation platform, and the second category is visible to the creator of the resource;

[0011] The resource is a plane resource or a spatial model of an image.

[0012] According to one embodiment of the present invention, the first approximation includes a second approximation and a third approximation;

[0013] The second similarity is obtained based on the cosine similarity between the resource feature vector of the first creative content and the resource feature vectors of other creative contents in the content database, and the resource feature vector is obtained based on resource categories and weights of each resource category;

[0014] The third approximation is obtained based on the cosine approximation of the image feature vector of the first creative content and the image feature vectors of other creative contents in the content database, and the image feature vector is obtained based on the vectorized rendered image.

[0015] According to one embodiment of the present invention, the process of acquiring the image feature vector includes:

[0016] Vectorize the rendered image to obtain a vectorized graphic;

[0017] Draw the vectorized graphics into the canvas;

[0018] Determining a first direction and a second direction based on pixel values ​​within the canvas;

[0019] Performing a mirror operation on pixels in the canvas based on a first direction and a second direction;

[0020] The image in the canvas is convolved with a convolution kernel to obtain the image feature vector.

[0021] According to one embodiment of the present invention, the vectorized graphics are drawn into the canvas with a preset line width and line color.

[0022] According to an embodiment of the present invention, when the similarity is lower than a first threshold, the first creative content is marked as a first category and saved in a resource database;

[0023] When the similarity is not lower than the first threshold, the first creative content is marked as a second category and saved in the resource database.

[0024] According to one embodiment of the present invention, before the first creative content is saved, the resource category included in the first creative content is checked;

[0025] When the first creative content contains resource information of the first category and the license type of the corresponding resource information is a prohibited type, or the license type of the user-created content is a prohibited type, or it contains resources of the second category and the license type contains a prohibited type, the type of the first creative content is set to the second category.

[0026] According to one embodiment of the present invention, before the first creative content is saved, the resource category included in the creative content of the user is checked;

[0027] Acquire the first creative content including the authorized resource information of the first category, and construct the second creative content based on the authorized resource information of the first category and the resource information of the second category;

[0028] The type of the second creative content is set to the second category and saved in the resource database.

[0029] According to a second aspect of the present invention, a management system for user-generated content includes:

[0030] A creative content acquisition unit is used to acquire a first creative content created by a user on a creative platform based on resources, wherein the first creative content includes a resource category and a resource combination rule; the resource category includes a first category and a second category, and the combination rule is a resource placement order and a resource placement position in a creative content editor;

[0031] A rendering image acquisition unit, which acquires a rendering image based on the first creative content of the user;

[0032] A first similarity acquisition unit, which determines a first similarity between the first creative content and other creative content in the content database based on the rendered image and the creative content;

[0033] A resource storage unit, which saves the first creation content of the user to a resource database of the first category or a resource database of the second category based on the first similarity;

[0034] The first category corresponds to a preset resource or a resource whose similarity to the preset resource is lower than a first threshold and is open to users of the creation platform, and the second category is visible to the creator of the resource;

[0035] The resource is a plane resource or a spatial model of an image.

[0036] According to a third aspect of the present invention, an electronic device includes a processor and a memory; the memory is used to store programs; the processor executes the program to implement a method for managing user-generated content.

[0037] According to a fourth aspect of the present invention, a computer-readable storage medium stores a program, and the program is executed by a processor to implement a method for managing user-generated content.

[0038] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0039] By analyzing the similarity of user-generated content, the content is automatically allocated to the appropriate resource library, effectively managing content resources and simplifying the user's management burden.

[0040] When checking the resource category and license type of the content, it is able to prevent unauthorized resources from entering the public category and protect the rights of content creators.

[0041] Through vectorization and approximation calculation of rendered images, the accuracy of resource matching can be improved and the storage and classification of user-generated content can be optimized.

[0042] The hierarchical storage method based on similarity can make resource storage and retrieval more efficient, reduce the occurrence of duplicate content, and improve resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart of a method for managing user-generated content provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The present disclosure will now be discussed with reference to several exemplary embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thus implement the present disclosure, rather than implying any limitation on the scope of the present disclosure.

[0045] As used herein, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "based at least in part on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment". The term "another embodiment" is to be interpreted as "at least one other embodiment". The orientation or position relationship indicated by the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "vertical", "horizontal", "lateral", "longitudinal" and the like is based on the orientation or position relationship shown in the accompanying drawings. These terms are mainly for better describing the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation. In addition, in addition to being used to indicate an orientation or position relationship, some of the above terms may also be used to indicate other meanings, such as the term "upper" may also be used to indicate a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to the specific circumstances. In addition, the terms "install", "set", "provided with", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be an internal connection between two devices, elements or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances. In addition, the terms "first", "second", etc. are mainly used to distinguish different devices, elements or components (the specific types and structures may be the same or different), and are not used to indicate or imply the relative importance and quantity of the indicated devices, elements or components. Unless otherwise specified, "plurality" means two or more.

[0046] With the development of user-generated content (UGC) platforms, the types and quantity of content created by users continue to increase, including multiple resources such as pictures, audio, and video. Existing platforms usually rely on users to manually classify and store content, but this method is inefficient and prone to inaccurate classification. At the same time, users often reuse similar resources when creating, resulting in a large amount of duplicate content on the platform, wasting storage space and affecting retrieval efficiency. In addition, existing technologies have loopholes in copyright and authorization management, and lack automatic detection of resource authorization status, which may lead to the disclosure of unauthorized resources and increase the risk of copyright disputes. Therefore, the platform urgently needs an intelligent content classification and management method that can improve resource management efficiency and improve copyright management.

[0047] According to one embodiment of the present invention, referring to Figure 1As shown, a method for managing user-generated content is provided, comprising:

[0048] The first creative content created by the user based on resources on the creative platform is obtained, wherein the first creative content includes resource categories and resource combination rules; the resource categories include a first category and a second category, and the combination rules are a resource placement order and a resource placement position in the creative content editor.

[0049] Specifically, in the creation platform, the user creates the first creative content through the editor, and the content includes the resource category selected by the user and the resource combination rules. Resource categories include two categories: the first category, such as the platform's built-in resources, such as preset pictures, icons, etc.; and the second category, resources uploaded by the user or imported externally. The resource combination rules are determined based on the order and position in which the user places the resources in the editor. By allowing users to freely select resource categories and combine resources, the platform provides a high degree of creative flexibility. At the same time, by recording the order and position of resource placement, it can provide structured reference information for subsequent content management, such as similarity analysis, to help the system better understand the user's creative intent and content structure.

[0050] A rendered image is obtained based on the first creative content of the user.

[0051] Specifically, the system generates a rendered image based on the user's creative content. The rendered image can be the final image that presents the combined resources according to the user's editing, or a preview image of the intermediate version. The rendered image can intuitively reflect the user's final creative results. By comparing the rendered image with other creative content, the system can perform similarity calculations more efficiently. This solution is designed to simplify the resource analysis process, enable the platform to quickly detect similar content, and improve the accuracy of subsequent classification and storage.

[0052] A first similarity between the first creative content and other creative content in the content database is determined based on the rendered image and the creative content.

[0053] Specifically, the system determines the first similarity by analyzing the image features of the rendered image and other creative content in the content database. The similarity is calculated by comparing the feature vector of the resource and the image feature vector. The resource feature vector is calculated based on the resource category and its weight, and the image feature vector is calculated based on the cosine similarity of the vectorized result of the rendered image. The present invention uses dual similarity calculations of resource features and image features to improve the accuracy of similarity analysis. The resource feature vector can reflect the characteristics of the resource itself through category and weight calculation; and the image feature vector can capture the overall form of the image through vectorization processing. By combining features of two different dimensions, the platform can more accurately judge the similarity of content and avoid misjudgment caused by relying solely on a single feature.

[0054] The first creative content of the user is saved to a resource database of a first category or a resource database of a second category based on the first similarity.

[0055] The first category corresponds to preset resources or resources whose similarity to the preset resources is lower than a first threshold and is open to users of the creation platform, and the second category is visible to creators of the resources.

[0056] The resource is a plane resource or a spatial model of an image.

[0057] Specifically, based on the calculated similarity results, the system determines whether the user's creative content is similar to the preset resources. If the similarity is lower than the first threshold, the content is classified into the first category and saved to the open resource database for other users to use; if the similarity is higher than the first threshold, it is classified into the second category and is only available to the creator himself. This similarity-based classification method improves resource management efficiency. When the content is similar to existing resources on the platform, it is avoided from being repeatedly displayed to other users, the storage and use of redundant content is reduced, and the utilization efficiency of platform resources is improved; for content with strong originality, it is saved in the second category and is only available to creators to view, protecting users' creative achievements and creativity from being disclosed prematurely, and preventing resource abuse or theft.

[0058] The present invention is applicable to a variety of resource types, including planar resources of images, such as photos, drawings, etc.; or spatial models, such as 3D models. The platform processes different types of resources separately to ensure that all resource categories can participate in the rendering and similarity calculation of the creative content. By supporting a variety of resource types, the present invention can provide users with a wider range of creative possibilities and meet the needs of users with different creative needs. Whether it is a two-dimensional image or a three-dimensional model, the platform can effectively manage and store it, ensuring resource diversity and enhancing the user's creative experience.

[0059] According to one embodiment of the present invention, the first approximation includes a second approximation and a third approximation;

[0060] The system calculates the first proximity based on the second proximity and the third proximity, which is used to ultimately evaluate the overall similarity between the first creative content and other content. By combining the similarities of the two dimensions of resource feature vectors and image feature vectors, the platform can comprehensively measure the similarity of creative content. By combining the similarity calculations in two different dimensions, the platform can more accurately judge the similarity of creative content. The resource feature vector focuses on the resource combination of the creative content, while the image feature vector focuses on the visual expression of the content. The mutual complementation of the two dimensions can avoid the limitations of single-dimensional judgment. Therefore, the first proximity can more comprehensively reflect the similarity of the creative content and effectively improve the accuracy and precision of the platform's content management.

[0061] The second similarity is obtained based on the cosine similarity between the resource feature vector of the first creative content and the resource feature vectors of other creative contents in the content database, and the resource feature vector is obtained based on resource categories and weights of each resource category;

[0062] Specifically, the platform first extracts a resource feature vector from the first creative content. The generation of the resource feature vector is based on the resource category used by the user and the weight of each resource category. For example, the weight of image resources may be higher than that of text resources, or certain types of resources (such as platform preset resources) have specific weight values. After that, the system will calculate the cosine similarity between the resource feature vector and the resource feature vectors of other creative content in the content database to obtain the second similarity. By using resource categories and weights to generate resource feature vectors, the platform can accurately reflect the relative importance and combination of each resource in the creative content. Cosine similarity is a commonly used similarity measurement method, which can express their similarity by calculating the angle between two vectors. Therefore, this method can effectively judge the similarity of two creative contents at the resource level, especially when users use a large number of identical or similar resources, and can accurately identify them.

[0063] The third approximation is obtained based on the cosine approximation of the image feature vector of the first creative content and the image feature vectors of other creative contents in the content database, and the image feature vector is obtained based on the vectorized rendered image.

[0064] Specifically, after the system generates a rendered image, it vectorizes it and obtains an image feature vector. The specific steps include: converting the rendered image into a geometric form through an image vectorization tool to obtain a vectorized graphic; then generating a specific image feature vector based on the graphic. Subsequently, the system calculates the cosine similarity between the image feature vector and the image feature vectors of other creative contents in the content database to obtain a third approximation. The vectorized rendered image used in the present invention can convert complex images into mathematical expressions, which is convenient for calculation and comparison. The cosine approximation of the image feature vector can accurately measure the similarity of images, especially when it comes to the visual elements of the creative content. This method can effectively capture the differences in shape, color, layout, etc. between images. Therefore, the system can identify the visual similarity of content through image features, supplementing the similarity judgment at the resource feature level.

[0065] According to one embodiment of the present invention, the process of acquiring the image feature vector includes:

[0066] Vectorize the rendered image to obtain a vectorized graphic;

[0067] Specifically, the system first vectorizes the rendered image created by the user. Vectorization is the conversion of an image from a pixel-based format to a geometric representation, such as points, lines, and surfaces. Through vectorization, the geometric features of the image can be captured instead of simply relying on the color values ​​of the pixels. The advantage of this design is that vectorized images can greatly simplify the processing complexity of the image and have the advantage of being resolution-independent, which facilitates subsequent feature extraction. Compared with bitmaps, vector graphics can more clearly represent structural features such as shapes and contours, thereby providing a more accurate basis for feature extraction. Through vectorization operations, images are converted into more geometrically meaningful expressions, which facilitates subsequent convolution processing and the generation of feature vectors.

[0068] Draw the vectorized graphics into the canvas;

[0069] Specifically, the system draws the vectorized graphics into a virtual canvas to ensure that the graphics are processed in a standardized space. This step is intended to provide a unified reference framework for subsequent feature extraction. The advantage of this design is that drawing into the canvas can standardize all images to the same scale and framework, avoiding errors caused by different image sizes or proportions. This step can effectively reduce inconsistencies in the processing process. Unified drawing of graphics provides a standardized processing environment, ensuring that all images are processed under the same conditions, improving the consistency of image processing.

[0070] Determining a first direction and a second direction based on pixel values ​​within the canvas;

[0071] Specifically, the system determines the two main directions of the graphic based on the pixel values ​​in the canvas, called the first direction and the second direction. The first direction may be the main axis direction of the graphic, and the second direction is perpendicular to it. By analyzing the distribution of pixel values, the system can identify the main structure or main outline of the graphic. This design is because, by determining the main direction of the graphic, the system can summarize and extract the main features of the graphic, which is particularly critical for subsequent mirroring operations and convolution processing. Identifying the main direction of the graphic helps to capture key geometric features in the image more effectively. This step helps the system identify the geometric structure of the image, improves the accuracy of the feature vector, and enables the system to better capture the core features of the image.

[0072] Performing a mirror operation on pixels in the canvas based on a first direction and a second direction;

[0073] Specifically, after determining the main direction, the system performs a mirror operation on the pixels in the canvas, that is, performs a symmetry transformation on the graphic along the first direction and the second direction. The mirror operation can amplify the symmetry features of the graphic and enhance the expressiveness of the image in the feature space. The advantage of this design is that the mirror operation is intended to enhance the symmetry features in the image. Many natural and artificial images have certain symmetries, and these symmetry features can be better captured through mirror transformation, thereby improving the effect of subsequent convolution processing. The mirror operation can enhance the symmetry information of the image and help the system better extract features related to symmetry, thereby improving the accuracy of similarity analysis.

[0074] The image in the canvas is convolved with a convolution kernel to obtain the image feature vector.

[0075] Specifically, the system applies a convolution kernel to the graphics in the canvas for convolution operations. The convolution kernel is used to extract local features (such as edges, textures, etc.) in the graphics. Through multiple convolution operations, the system can generate a high-dimensional feature vector that represents the overall features of the image. This design is because the convolution operation is a key step in deep learning and image processing, and can effectively extract local features of the image, such as edges, corners and other information. This processing method can retain the detailed features of the image and convert it into a vector representation that can be used for similarity calculation. After the convolution process, the system generates a high-dimensional image feature vector. This feature vector can fully express the structural features and details of the image, providing a sufficient basis for subsequent similarity calculations.

[0076] According to one embodiment of the present invention, the vectorized graphics are drawn into the canvas with a preset line width and line color.

[0077] Specifically, the system defines standard line width and line color for vector graphics, and these parameters remain consistent when drawing graphics. The line width can be a fixed value (such as 1 pixel or 3 pixels), while the line color can be set to a standardized color (such as black or gray) to unify the display and processing of all graphics. By setting a unified line width and color, the platform can eliminate the differences caused by user personalized adjustments, making subsequent graphics processing and feature extraction more consistent and standardized. This design avoids feature extraction errors caused by differences in line width or color, while simplifying the complexity of graphics. By presetting line width and color, the platform can maintain consistency when processing various graphics, ensuring that all vectorized graphics are feature extracted under the same conditions, thereby improving the accuracy of image analysis.

[0078] After determining the line width and color, the system draws the vectorized graphics into a virtual canvas according to these preset standards. The size and proportion of the canvas are kept uniform, ensuring that all graphics are drawn in a standardized coordinate system. The drawn graphics can be a simplified version with monochrome and fixed lines for easy subsequent processing. Drawing into a standard canvas not only ensures the standardization of all graphics, but also simplifies complex graphic details through a unified graphic representation, which facilitates the system's feature analysis. This unified canvas drawing method ensures consistency in image processing, especially when the images are from different sources or styles. By standardizing the drawing of all vectorized graphics into a unified canvas, the system can more easily process images from different sources and ensure the stability and consistency of the feature extraction process.

[0079] Once a graphic is drawn with a preset line width and color, the system performs standardized subsequent processing on the graphic (such as convolution, similarity calculation, etc.). Since all graphics have consistent line width and color, the system can perform processing more efficiently without adjusting parameters for each graphic individually. Standardized line width and color allow graphics to be unaffected by style and design when extracting features, and the system can focus more on the structure and shape characteristics of the graphics without considering subtle differences in color and lines. In addition, fixed line width ensures that details are not lost. Through a unified graphic representation, the system can more accurately capture the geometric features of the graphics and improve the accuracy of subsequent feature extraction and similarity analysis. The efficiency of feature extraction is also improved because it is no longer necessary to customize the processing flow for each graphic.

[0080] According to an embodiment of the present invention, when the similarity is lower than a first threshold, the first creative content is marked as a first category and saved in a resource database;

[0081] When the similarity is not lower than the first threshold, the first creative content is marked as a second category and saved in the resource database.

[0082] Specifically, the system first calculates the similarity between the user's first creative content and other creative content in the database through the aforementioned steps. The calculation of the similarity may be based on the cosine similarity of the resource feature vector and the image feature vector, combining the multi-dimensional similarity analysis of resource combination and image features. Through multi-dimensional similarity calculation, the system can more accurately judge the degree of similarity between the creative content and other content, avoiding misjudgment due to relying on a single factor. This design ensures the accuracy of classification while avoiding the accumulation of duplicate content. Through accurate similarity calculation, the system can comprehensively evaluate the similarity of the creative content, laying the foundation for subsequent classification and storage.

[0083] After the calculation is completed, the system will compare the similarity with the preset first threshold. If the similarity is lower than the threshold, it means that the first creation has a low similarity with the existing content and is relatively unique. By setting the threshold, the system can distinguish between similar content and unique content. Content below the threshold usually represents highly original content and is worth storing and managing separately. Doing so can protect the user's creative work while preventing content from being unnecessarily marked as duplicates. Setting a threshold enables the system to automatically filter out relatively unique content, improve content management efficiency, and ensure that users' original content is properly protected and classified.

[0084] If the similarity is lower than the first threshold, the system will mark the first creation as the first category. Content in the first category indicates that the similarity with the preset resources or existing content is low and it is highly original. This type of content will be saved to the resource database for use or display by platform users. By classifying unique content as the first category and saving it to the resource library, the platform can effectively manage and display highly original content and avoid resource duplication. At the same time, the content in the open repository can be used by more users, improving the circulation and value of the content.

[0085] If the similarity is not lower than the first threshold, the system will mark the first creative content as the second category. Content in the second category indicates that it has a high degree of similarity to existing content and may be a modification or secondary creation based on existing content. This type of content is usually not open to all users and is only saved to the resource library for creators to view and manage. The setting of the second category protects the originality of the content and the interests of the creators. Content with a high degree of similarity is not suitable for public display to prevent the platform from being flooded with a large number of duplicate or similar resources, affecting the user experience. Limiting these contents to be visible only to the creator can effectively reduce resource redundancy while protecting the creator's modifications or changes to the content. By marking it as the second category, the system can optimize the content quality in the resource library, avoid the accumulation of a large amount of similar content, and enhance the uniqueness and richness of the platform's resources.

[0086] According to one embodiment of the present invention, before the first creative content is saved, the resource category included in the first creative content is checked;

[0087] When the first creative content contains resource information of the first category and the license type of the corresponding resource information is a prohibited type, or the license type of the user-created content is a prohibited type, or it contains resources of the second category and the license type contains a prohibited type, the type of the first creative content is set to the second category.

[0088] Specifically, the system first analyzes the first creative content and checks the resource categories it contains. Resource categories may include first-category resources (such as platform built-in resources or preset resources) and second-category resources (such as user-uploaded or externally imported resources). By checking the resource categories, the system can identify in advance which resources are preset public resources and which resources are private resources uploaded externally. This ensures that the legality of the content is initially judged before it is saved to prevent the spread of illegal content. This inspection process lays the foundation for subsequent license type verification, which helps the system distinguish the source of content and ensure the standardization of content management.

[0089] If the first creative content contains first-category resources, the system will further check the license type of these resources. If the license type of a resource is "prohibited type", the system will prohibit the content from entering the first-category resource library, that is, the resource will not be allowed to be used publicly. This design ensures that the platform follows the resource usage license when using built-in resources, avoiding unauthorized resources from being used or disseminated publicly. Through the automated inspection mechanism, the possibility of illegal use of resources can be reduced to ensure compliance with resource management within the platform. By checking the license type, the system can automatically identify and prevent resources that do not meet the license requirements from entering the public category, ensuring the legality and copyright compliance of the content.

[0090] The system also checks the overall license type of the first creative content created by the user. If the license type of the creative content is "prohibited type", that is, the user does not allow their content to be used publicly, the system will also mark the content as the second category, which is limited to the user's own viewing and management. This checking step ensures that the user's content copyright and usage rights can be effectively protected. When uploading content, users may specify that their content is private or for personal use only. By automatically detecting the license type, the system can respect the user's copyright requirements and prevent unauthorized content from being disclosed. Through this check, the system can accurately distinguish the user's copyright requirements, avoid copyright disputes, and safeguard the user's creative rights.

[0091] If the first creation contains second-category resources (such as resources uploaded by users), the system will also check their license type. If the resource's license type contains "prohibited type", the system will mark the first creation as the second category, restricting it to be viewed only by the resource creator and not open to other users. This design ensures that external resources uploaded by users are also protected by licenses. The platform automatically identifies the license type of resources to prevent unauthorized external resources from being mistakenly displayed publicly, thereby reducing legal and copyright risks. This mechanism effectively protects the use rights of external resources and prevents infringements, while ensuring that the platform's content management system complies with copyright regulations.

[0092] If the system finds that the license type contains "prohibited type" in any of the above checks, the system will mark the first creative content as the second category, whether at the resource level or the user creation level. Content in the second category will not be displayed publicly, and only the content creator himself can view and manage it. By limiting creative content containing prohibited type resources to the second category, the platform can effectively control the public and private use of resources, ensure the compliance of the content, and respect the use licenses of resource providers and creators. This design ensures that content containing restrictive resources will not be displayed publicly, effectively avoiding the risk of infringement, and safeguarding the rights and interests of resources and creators.

[0093] According to one embodiment of the present invention, before the first creative content is saved, the resource category included in the creative content of the user is checked;

[0094] Acquire the first creative content including the authorized resource information of the first category, and construct the second creative content based on the authorized resource information of the first category and the resource information of the second category;

[0095] The type of the second creative content is set to the second category and saved in the resource database.

[0096] Specifically, the system first analyzes the user's first creative content and checks the resource categories contained therein. Resource categories usually include first-category resources built into the platform (such as authorized images, icons, or materials) and second-category resources uploaded by users themselves (such as externally imported pictures or models). By pre-checking the resource categories, the system can identify different types of resources and ensure that resource management in subsequent processing is clearer and more standardized. This design can prevent unauthorized resources from being misused within the platform. This step helps the system perform resource compliance management before content is saved, ensures the legality of the content, and lays the foundation for subsequent resource processing.

[0097] The system further analyzes the resources in the first creative content and extracts the resource information that belongs to the first category and has been authorized. These resources may include images, materials or other authorized resources built into the platform. This step ensures that the system extracts the first category resource information only when the resources have been authorized. The purpose of this design is to avoid improper use of unauthorized content and ensure that the resources within the platform comply with copyright licensing requirements. Through this check, the system can ensure that only authorized resource information is processed and used, reducing legal and copyright risks in the process of resource use.

[0098] The system constructs the second creative content based on the authorized first-category resource information and the second-category resource information provided by the user. The second creative content may be new content generated by recombining or processing resources based on the first creative content. This design allows the system to merge the user's creative content with the authorized resources to ensure that the generated creative content complies with copyright regulations and is more compliant. At the same time, secondary construction based on different categories of resources can provide creators with more creative freedom. Through the second creative content constructed based on multiple categories of resources, the system can generate content that meets copyright requirements, while providing users with new ways of creation and ways to combine materials, enriching the user's creative experience.

[0099] After completing the construction of the second creative content, the system will set the type of the content to the second category. The second category of content is usually user-uploaded or secondary processed content, which will not be directly disclosed and can only be viewed or managed by the creator himself. Marking the newly generated creative content as the second category ensures that unauthorized resources will not be disclosed, while allowing creators to modify and further optimize them. This design protects the creative rights of creators and prevents the abuse of resources or unauthorized disclosure. By setting the content to the second category, the system can effectively control the scope of resource use, protect the privacy and copyright compliance of the content, and prevent unauthorized resources from entering the public domain.

[0100] Finally, the system saves the generated second category creative content to the resource database. This content will not be open to other users, but only for the creator to view and manage until the resource's permissions or licensing status changes. The design of saving to the resource database ensures the secure storage and management of content, while respecting the resource's usage license and the user's creative rights. Creators can continue to optimize their creations in their own content libraries without worrying about the public use rights of the content. Through this step, the system can ensure that the content in the resource database meets compliance requirements, effectively protect users' creative content, and improve the platform's content security and management efficiency.

[0101] According to one embodiment of the present invention, a management system for user-generated content includes:

[0102] A creative content acquisition unit is used to acquire a first creative content created by a user on a creative platform based on resources, wherein the first creative content includes a resource category and a resource combination rule; the resource category includes a first category and a second category, and the combination rule is a resource placement order and a resource placement position in a creative content editor;

[0103] A rendering image acquisition unit, which acquires a rendering image based on the first creative content of the user;

[0104] A first similarity acquisition unit, which determines a first similarity between the first creative content and other creative content in the content database based on the rendered image and the creative content;

[0105] A resource storage unit, which saves the first creation content of the user to a resource database of the first category or a resource database of the second category based on the first similarity;

[0106] The first category corresponds to a preset resource or a resource whose similarity to the preset resource is lower than a first threshold and is open to users of the creation platform, and the second category is visible to the creator of the resource;

[0107] The resource is a plane resource or a spatial model of an image.

[0108] According to one embodiment of the present invention, an electronic device includes a processor and a memory; the memory is used to store programs; the processor executes the program to implement a method for managing user-generated content.

[0109] According to an embodiment of the present invention, a computer-readable storage medium stores a program, and the program is executed by a processor to implement a method for managing user-generated content.

[0110] The beneficial effects of the present invention are:

[0111] By automatically identifying resource categories and performing similarity analysis, the system can quickly and accurately classify and store creative content, reducing content redundancy.

[0112] The system checks resource permissions to prevent unauthorized disclosure of content, ensure content compliance and protect the rights of creators.

[0113] Combining resource features and image features, dual similarity calculation improves classification accuracy.

[0114] The system supports two-dimensional and three-dimensional resources, providing a wider range of creative possibilities to meet the needs of different users.

[0115] By processing images with uniform line width and color, the accuracy of feature extraction and similarity calculation is improved.

[0116] Unauthorized content is restricted to be visible only to the creator, ensuring content privacy and flexible management.

[0117] Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0118] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0119] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0120] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0121] In addition, each functional module in the embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0122] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the energy-saving signal sending / receiving method of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0123] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0124] It should be understood that the size of the sequence number of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. For the purpose of example and description, the foregoing description of the implementation of the present disclosure has been given. The foregoing description is not exhaustive and is not intended to limit the present disclosure to the exact form disclosed. Various deformations and modifications may exist according to the above teachings, or various deformations and modifications may be obtained from the practice of the present disclosure. These embodiments are selected and described to illustrate the principles of the present disclosure and its practical application, so that those skilled in the art can use the present disclosure in various embodiments and various modifications suitable for the specific purpose conceived.

Claims

1. A method for managing user-generated content, characterized in that: include: Acquire a first creative content created by a user on a creative platform based on resources, wherein the first creative content includes a resource category and a resource combination rule; the resource category includes a first category and a second category, and the combination rule is a resource placement order and a resource placement position in a creative content editor; Acquire a rendered image based on the first creative content of the user; determining a first similarity between the first creative content and other creative content in the content database based on the rendered image and the creative content; Saving the user's first creative content to a resource database of a first category or a resource database of a second category based on the first similarity; The first category corresponds to a preset resource or a resource whose similarity to the preset resource is lower than a first threshold and is open to users of the creation platform, and the second category is visible to the creator of the resource; The resource is a plane resource or a spatial model of an image.

2. The method for managing user-generated content according to claim 1, wherein: The first approximation includes a second approximation and a third approximation; The second similarity is obtained based on the cosine similarity between the resource feature vector of the first creative content and the resource feature vectors of other creative contents in the content database, and the resource feature vector is obtained based on resource categories and weights of each resource category; The third approximation is obtained based on the cosine approximation of the image feature vector of the first creative content and the image feature vectors of other creative contents in the content database, and the image feature vector is obtained based on the vectorized rendered image.

3. The method for managing user-generated content according to claim 2, wherein: The process of obtaining the image feature vector includes: Vectorize the rendered image to obtain a vectorized graphic; Draw the vectorized graphics into the canvas; Determining a first direction and a second direction based on pixel values ​​within the canvas; Performing a mirror operation on pixels in the canvas based on a first direction and a second direction; The image in the canvas is convolved with a convolution kernel to obtain the image feature vector.

4. The method for managing user-generated content according to claim 3, wherein: Vectorized graphics are drawn into the canvas with a preset line width and line color.

5. The method for managing user-generated content according to claim 1, wherein: When the similarity is lower than a first threshold, marking the first creative content as a first category and saving it in a resource database; When the similarity is not lower than the first threshold, the first creative content is marked as a second category and saved in the resource database.

6. The method for managing user-generated content according to claim 5, wherein: Before the first creative content is saved, checking the resource category included in the first creative content; When the first creative content contains resource information of the first category and the license type of the corresponding resource information is a prohibited type, or the license type of the user-created content is a prohibited type, or it contains resources of the second category and the license type contains a prohibited type, the type of the first creative content is set to the second category.

7. The method for managing user-generated content according to claim 5, characterized in that: Before the first creative content is saved, checking the resource category included in the creative content of the user; Acquire the first creative content including the authorized resource information of the first category, and construct the second creative content based on the authorized resource information of the first category and the resource information of the second category; The type of the second creative content is set to the second category and saved in the resource database.

8. A management system for user-generated content, characterized in that: include: A creative content acquisition unit is used to acquire a first creative content created by a user on a creative platform based on resources, wherein the first creative content includes a resource category and a resource combination rule; the resource category includes a first category and a second category, and the combination rule is a resource placement order and a resource placement position in a creative content editor; A rendering image acquisition unit, which acquires a rendering image based on the first creative content of the user; A first similarity acquisition unit, which determines a first similarity between the first creative content and other creative content in the content database based on the rendered image and the creative content; A resource storage unit, which saves the first creation content of the user to a resource database of the first category or a resource database of the second category based on the first similarity; The first category corresponds to a preset resource or a resource whose similarity to the preset resource is lower than a first threshold and is open to users of the creation platform, and the second category is visible to the creator of the resource; The resource is a plane resource or a spatial model of an image.

9. An electronic device, characterized in that: It comprises a processor and a memory; the memory is used to store a program; the processor executes the program to implement the method for managing user-generated content as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method for managing user-generated content as described in any one of claims 1 to 7.

Images