Video template infringement detection method, system, device and medium

Abstract

The invention discloses a video template infringement detection method and apparatus, a device and a storage medium. The method comprises the steps of obtaining a to-be-detected target video template and a benchmarking video template; performing anti-interference graph synthesis analysis processing on the target video template and the benchmarking video template under various strategies to obtain a first video template and a second video template corresponding to each strategy; extracting a first material track of the first video template, and extracting a second material track of the second video template; determining correlation data of the first video template and the second video template under a corresponding strategy according to the first material track and the second material track; and determining an infringement coefficient of the target video template relative to the benchmarking video template according to the correlation data of the first video template and the second video template under all strategies. According to the method, automatic video template infringement detection can be realized, and the detection efficiency and accuracy are better. The method can be widely applied to the technical field of videos.

Description

Technical Field

[0001] The present application relates to the field of video technology, and in particular to a method, device, equipment and storage medium for detecting infringement of a video template. Background Art

[0002] At present, with the development of information technology, more and more enterprise system applications are being developed to provide services for users. For example, with the rapid development of multimedia technology, the creation and application of video templates are becoming more and more extensive. Users can create, share and use relevant video templates, thereby improving the efficiency and quality of video generation.

[0003] In actual applications, it is found that many applications have plagiarized video templates. In order to protect the rights of original authors, it is necessary to detect the infringement of video templates. At present, the video template infringement detection method mainly relies on manual comparison and recognition, which is not only inefficient, but also easily affected by subjective factors, resulting in inaccurate detection results. In addition, with the continuous increase in the number of video templates, manual detection methods can no longer meet actual needs.

[0004] In summary, the problems existing in related technologies need to be solved urgently. Summary of the invention

[0005] The purpose of this application is to solve one of the technical problems existing in the related art to at least a certain extent.

[0006] To this end, an object of an embodiment of the present application is to provide a video template infringement detection method, device, equipment and storage medium.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present application include:

[0008] On the one hand, an embodiment of the present application provides a method for detecting infringement of a video template, the method comprising:

[0009] Acquire a target video template to be detected and a reference video template for comparison with the target video template;

[0010] Performing anti-interference graph synthesis analysis processing under multiple strategies on the target video template and the benchmark video template to obtain a first video template and a second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing;

[0011] Extracting a first material track of the first video template, and extracting a second material track of the second video template;

[0012] Determining correlation data between the first video template and the second video template under a corresponding strategy according to the first material track and the second material track;

[0013] According to the correlation data between the first video template and the second video template under all strategies, an infringement coefficient of the target video template relative to the benchmark video template is determined.

[0014] In addition, the video template infringement detection method according to the above embodiment of the present application may also have the following additional technical features:

[0015] Further, in one embodiment of the present application, the strategy types of the anti-interference graph synthesis analysis processing include fully transparent synthesis analysis processing, fully unsaturated synthesis analysis processing, fully saturated synthesis analysis processing and random synthesis analysis processing.

[0016] Further, in one embodiment of the present application, the target video template and the reference video template are subjected to anti-interference graph synthesis analysis processing under multiple strategies to obtain the first video template and the second video template corresponding to each strategy, including:

[0017] The target video template is used as the first video template corresponding to the target video template under the strategy of fully transparent synthesis analysis and processing, and the benchmark video template is used as the second video template corresponding to the benchmark video template under the strategy of fully transparent synthesis analysis and processing;

[0018] Inputting the same black background image into the target video template and the reference video template, obtaining a first video template corresponding to the target video template under the strategy of completely unsaturated synthesis analysis and processing, and a second video template corresponding to the reference video template under the strategy of completely unsaturated synthesis analysis and processing;

[0019] Inputting the same white background image into the target video template and the reference video template, obtaining a first video template corresponding to the target video template under the strategy of full saturation synthesis analysis processing, and a second video template corresponding to the reference video template under the strategy of full saturation synthesis analysis processing;

[0020] The same random color picture is input into the target video template and the reference video template to obtain a first video template corresponding to the target video template under the strategy of random synthesis analysis and processing, and a second video template corresponding to the reference video template under the strategy of random synthesis analysis and processing.

[0021] Further, in one embodiment of the present application, extracting the first material track of the first video template includes:

[0022] Extracting key frames from the first video template to obtain a key frame sequence corresponding to the first video template;

[0023] Inputting the key frame sequence into a pre-trained material trajectory model to extract a first material trajectory of the first video template;

[0024] The first material track includes several key frames in the first video template.

[0025] Further, in an embodiment of the present application, determining the correlation data of the first video template and the second video template under the corresponding strategy according to the first material track and the second material track includes:

[0026] Extracting a first track feature of the first material track, and extracting a second track feature of the second material track; wherein the first track feature includes a plurality of first key frame features, and the second track feature includes the same number of second key frame features as the first key frame features;

[0027] Calculating the Euclidean distance between each group of the first key frame features and the second key frame features;

[0028] Determine, according to the Euclidean distance, the similarity between each group of the first key frame features and the second key frame features;

[0029] Calculate the difference between 1 and the similarity to determine the dissimilarity between each group of the first key frame features and the second key frame features;

[0030] Calculating the product of the dissimilarity corresponding to each group of the first key frame feature and the second key frame feature to obtain a first value;

[0031] According to the difference between 1 and the first value, correlation data between the first video template and the second video template is determined.

[0032] Further, in one embodiment of the present application, determining the infringement coefficient of the target video template relative to the benchmark video template according to the correlation data of the first video template and the second video template under all strategies includes:

[0033] Detecting a first ratio of the number of key frames in the first material trajectory to the total number of key frames in the first video template;

[0034] Detecting a second ratio of the number of key frames in the second material track to the total number of key frames in the second video template;

[0035] Determining a correlation impact value between the first video template and the second video template according to the first ratio and the second ratio;

[0036] The average of the corresponding correlation impact values ​​under all strategies is calculated to obtain the infringement coefficient of the target video template relative to the benchmark video template.

[0037] Further, in an embodiment of the present application, determining the correlation impact value of the first video template and the second video template according to the first ratio and the second ratio includes:

[0038] The correlation impact value of the first video template and the second video template is calculated by the following formula:

[0039] R=(1-(1-R1)(1-R2))C

[0040] In the formula, R represents the correlation influence value between the first video template and the second video template, R1 represents the first ratio, R2 represents the second ratio, and C represents the correlation data between the first video template and the second video template.

[0041] On the other hand, an embodiment of the present application provides a video template infringement detection device, the device comprising:

[0042] An acquisition unit, used to acquire a target video template to be detected and a reference video template for comparison with the target video template;

[0043] A processing unit is used to perform anti-interference graph synthesis analysis processing on the target video template and the benchmark video template under multiple strategies to obtain a first video template and a second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing;

[0044] an extraction unit, configured to extract a first material track of the first video template, and extract a second material track of the second video template;

[0045] a calculation unit, configured to determine correlation data between the first video template and the second video template under a corresponding strategy according to the first material track and the second material track;

[0046] A statistical unit is used to determine the infringement coefficient of the target video template relative to the benchmark video template according to the correlation data of the first video template and the second video template under all strategies.

[0047] On the other hand, an embodiment of the present application provides an electronic device, including:

[0048] at least one processor;

[0049] at least one memory for storing at least one program;

[0050] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned video template infringement detection method.

[0051] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned video template infringement detection method.

[0052] The advantages and benefits of the present application will be partially given in the following description, and partially become apparent from the following description, or be understood through the practice of the present application:

[0053] The video template infringement detection method, device, equipment and storage medium disclosed in the embodiment of the present application obtain a target video template to be detected and a benchmark video template for comparison with the target video template; perform anti-interference graph synthesis analysis processing under multiple strategies on the target video template and the benchmark video template to obtain the first video template and the second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing; extract the first material track of the first video template, and extract the second material track of the second video template; according to the first material track and the second material track, determine the correlation data of the first video template and the second video template under the corresponding strategy; according to the correlation data of the first video template and the second video template under all strategies, determine the infringement coefficient of the target video template relative to the benchmark video template. This method can realize automated video template infringement detection, and the detection efficiency and accuracy are better, which is conducive to reducing labor costs and improving the effectiveness of copyright protection of video templates. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present application. For technical personnel in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A schematic diagram of an implementation environment of a video template infringement detection method provided in an embodiment of the present application;

[0056] Figure 2 A schematic diagram of a flow chart of a video template infringement detection method provided in an embodiment of the present application;

[0057] Figure 3 A schematic diagram of a strategy type for anti-interference graph synthesis analysis processing provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of a random color picture provided in an embodiment of the present application;

[0059] Figure 5 A schematic diagram of the structure of a video template infringement detection device provided in an embodiment of the present application;

[0060] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0062] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0064] 1) Video template: A pre-designed video element and effect that allows users to modify and edit it according to personal needs to produce various types of videos.

[0065] 2) Material: some dynamic or static design element.

[0066] 3) Trajectory: The material moves or changes along a specific path.

[0067] At present, with the development of information technology, more and more enterprise system applications are being developed to provide services for users. For example, with the rapid development of multimedia technology, the creation and application of video templates are becoming more and more extensive. Users can create, share and use relevant video templates, thereby improving the efficiency and quality of video generation.

[0068] In actual applications, it is found that many applications have plagiarized video templates. In order to protect the rights of original authors, it is necessary to detect the infringement of video templates. At present, the video template infringement detection method mainly relies on manual comparison and recognition, which is not only inefficient, but also easily affected by subjective factors, resulting in inaccurate detection results. In addition, with the continuous increase in the number of video templates, manual detection methods can no longer meet actual needs.

[0069] In view of this, a video template infringement detection method is provided in an embodiment of the present application, which obtains a target video template to be detected and a benchmark video template for comparison with the target video template; performs anti-interference graph synthesis analysis processing under multiple strategies on the target video template and the benchmark video template to obtain the first video template and the second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing; extracts the first material track of the first video template, and extracts the second material track of the second video template; according to the first material track and the second material track, determines the correlation data of the first video template and the second video template under the corresponding strategy; according to the correlation data of the first video template and the second video template under all strategies, determines the infringement coefficient of the target video template relative to the benchmark video template. This method can realize automated video template infringement detection, and the detection efficiency and accuracy are better, which is conducive to reducing labor costs and improving the effectiveness of copyright protection of video templates.

[0070] Please refer to Figure 1 , Figure 1 The schematic diagram of the implementation environment of a video template infringement detection method provided in the embodiment of the present application is shown. In the implementation environment, the main hardware and software entities involved include a terminal device 110 and a backend server 120. The terminal device 110 and the backend server 120 are connected in communication.

[0071] Specifically, the video template infringement detection method provided in the embodiments of the present application can be executed alone on the terminal device 110 side, or can be executed alone on the background server 120 side, or can be executed based on data interaction between the terminal device 110 and the background server 120.

[0072] The terminal device 110 of the above embodiment may include a mobile phone, a computer, a smart wearable device, a PDA device, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc., but is not limited thereto. The backend server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0073] The terminal device 110 and the backend server 120 may establish a communication connection via a wireless network or a wired network. The wireless network or wired network uses standard communication technology and / or protocols, and the network may be set to the Internet or any other network, such as but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network.

[0074] Of course, it is understandable that Figure 1 The implementation environment in the example is only some optional application scenarios of the video template infringement detection method provided in the embodiment of the present application, and the actual application is not fixed. Figure 1 The hardware and software environment shown.

[0075] Below, in combination with the introduction of the aforementioned implementation environment, a video template infringement detection method provided in an embodiment of the present application is introduced and explained.

[0076] Please refer to Figure 2 , Figure 2 : is a schematic diagram of a video template infringement detection method provided in an embodiment of the present application, and the video template infringement detection method includes but is not limited to:

[0077] Step 210: obtaining a target video template to be detected and a reference video template for comparison with the target video template;

[0078] Step 220: Perform anti-interference graph synthesis analysis processing under multiple strategies on the target video template and the benchmark video template to obtain a first video template and a second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing;

[0079] Step 230: extracting a first material track of the first video template, and extracting a second material track of the second video template;

[0080] Step 240: Determine correlation data between the first video template and the second video template under a corresponding strategy according to the first material track and the second material track;

[0081] Step 250: Determine the infringement coefficient of the target video template relative to the benchmark video template based on the correlation data between the first video template and the second video template under all strategies.

[0082] In an embodiment of the present application, a video template infringement detection method is provided, which can effectively improve two major technical problems in the field of video template copyright protection: first, traditional infringement detection methods are inefficient and difficult to meet the needs of rapid detection of large-scale video content; second, the detection accuracy is low, which is prone to misjudgment or omission, affecting the effectiveness of copyright protection.

[0083] Specifically, in the embodiment of the present application, when performing infringement detection on a video template, a basic resource database can be established, in which various video templates can be stored. When a new video template appears, the existing video templates in the resource database can be used to detect infringement of the new video template to determine whether the new video template may have infringement behavior. In the embodiment of the present application, the video template that needs to be detected for infringement can be recorded as the target video template, and the video template to be compared with the target video template can be recorded as the benchmark video template.

[0084] It is easy to understand that when performing infringement detection on the target video template, multiple benchmark video templates can be used to determine whether the target video template has any infringement behavior. In the embodiment of the present application, the process of comparing the target video template and a benchmark video template is introduced, which can be reused on multiple other benchmark video templates to determine the infringement coefficients of the target video template and each benchmark video template. The present application does not limit the number of benchmark video templates involved in the comparison.

[0085] In an embodiment of the present application, when detecting a target video template, it and a benchmark video template for comparison can be obtained. Both the target video template and the benchmark video template can be a video clip, which includes a number of image frames. Then, the target video template and the benchmark video template can be subjected to anti-interference graph synthesis analysis processing under multiple strategies. Under each strategy, the result after the target video template is processed can be obtained, which is recorded as the first video template, and the result after the benchmark video template is processed can be recorded as the second video template.

[0086] In an embodiment of the present application, the anti-interference graph synthesis analysis processing can eliminate the interference of multiple layers superimposed on each other in the video template. Generally speaking, layer mixing modes include normal, dissolve, darken, brighten, saturation, difference, color and other main modes and their extended modes. According to the principle of the mixing algorithm, the normal and dissolve modes are affected by the transparency of the layer, and the other modes are affected by the layer color (bgr). When stealing video templates to generate other video templates, their layers are often simply processed to avoid possible infringement detection. Therefore, in an embodiment of the present application, the target video template and the benchmark video template are subjected to anti-interference graph synthesis analysis processing to reduce the impact of multi-layer mixing on detection.

[0087] For example, referring to Figure 3 , Figure 3 A schematic diagram of a strategy type for anti-interference graph synthesis analysis processing provided in an embodiment of the present application is shown. The strategy types for anti-interference graph synthesis analysis processing in an embodiment of the present application may include fully transparent synthesis analysis processing, fully unsaturated synthesis analysis processing, fully saturated synthesis analysis processing, and random synthesis analysis processing. These strategies are introduced and explained below.

[0088] Under the strategy of fully transparent synthesis analysis and processing, the target video template itself can be used as the first video template, and the benchmark video template itself can be used as the second video template.

[0089] Under the strategy of fully unsaturated synthesis analysis and processing, the user layer can be used to input the same black background (b:0, g:0, r:0, a:255) image to each video template to remove the color information in the image, so that the detection focuses more on the brightness and contrast of the image, and improves the recognition of special effect elements composed of brightness changes rather than color changes, thereby reducing the interference of color mixing on the analysis. In other words, the same black background image can be input to the target video template and the benchmark video template to obtain the first video template and the second video template.

[0090] Under the strategy of fully saturated synthesis analysis and processing, the color saturation of the image can be emphasized or changed by using the user layer to input a white background (b:255, g:255, r:255, a:255) image into the video template. By enhancing the color saturation, the special effects are more prominent, which simplifies the special effects analysis process to a certain extent. In other words, the same white background image can be input into the target video template and the benchmark video template to obtain the first video template and the second video template.

[0091] Under the strategy of random synthesis analysis and processing, the same random color (the color random range of each pixel in the picture: b: 0→255, g: 0→255, r: 0→255, a: 0→255) picture is input to the video template. Figure 4 , Figure 4 A schematic diagram of a random color picture provided in an embodiment of the present application is shown. A random color picture is a random pixel color picture, which can be used as a "noise" source to effectively disperse and weaken interference factors in other layers. When this picture is mixed with a target image, its irregular color distribution will break the original interference pattern, making the special effects analysis more accurate and reliable. At this time, the same random color picture is input into the target video template and the benchmark video template to obtain a first video template and a second video template.

[0092] After obtaining the first video template and the second video template corresponding to each strategy, the material track of the first video template can be extracted, and the material track of the second video template can be extracted, and the material track of the first video template is recorded as the first material track, and the material track of the second video template is recorded as the second material track.

[0093] Exemplarily, taking the extraction process of the first material track as an example, it may include:

[0094] Extracting key frames from the first video template to obtain a key frame sequence corresponding to the first video template;

[0095] Inputting the key frame sequence into a pre-trained material trajectory model to extract a first material trajectory of the first video template;

[0096] The first material track includes several key frames in the first video template.

[0097] In an embodiment of the present application, for the first video template and the second video template, key frames can be extracted from them respectively to obtain corresponding key frame sequences. Then, a pre-trained material trajectory model can be used to extract the key frame sequence to obtain a first material trajectory of the first video template and a second material trajectory of the second video template. Here, the material trajectory can be a new sequence consisting of key frames of specific materials in the original key frame sequence. The present application does not limit the specific parameters and structure of the material trajectory model. For example, in some embodiments, the material trajectory model can be a sequence-to-sequence model, with the input being a key frame sequence and the output being a material trajectory.

[0098] In the embodiment of the present application, after obtaining the first material track and the second material track, the correlation data between the first video template and the second video template under the corresponding strategy can be determined. Here, the correlation data can be used to characterize the similarity between the first video template and the second video template.

[0099] Specifically, in some embodiments, determining the correlation data of the first video template and the second video template under the corresponding strategy according to the first material track and the second material track includes:

[0100] Extracting a first track feature of the first material track, and extracting a second track feature of the second material track; wherein the first track feature includes a plurality of first key frame features, and the second track feature includes a plurality of second key frame features, which are the same in number as the first key frame features;

[0101] Calculating the Euclidean distance between each group of the first key frame features and the second key frame features;

[0102] Determine, according to the Euclidean distance, the similarity between each group of the first key frame features and the second key frame features;

[0103] Calculate the difference between 1 and the similarity to determine the dissimilarity between each group of the first key frame features and the second key frame features;

[0104] Calculating the product of the dissimilarity corresponding to each group of the first key frame feature and the second key frame feature to obtain a first value;

[0105] According to the difference between 1 and the first value, correlation data between the first video template and the second video template is determined.

[0106] In an embodiment of the present application, when determining the correlation data of the first video template and the second video template, for the first material track and the second material track, feature extraction can be performed on them. For example, the image features of each key frame of the material track can be extracted by using the convolution layer and the pooling layer, and the extracted from the first material track is recorded as the first key frame feature, and the extracted from the second material track is recorded as the second key frame feature. The number of the two can be the same, and two are grouped together. Then, for each group of first key frame features and second key frame features, their Euclidean distance can be calculated, for example, it can be a standardized Euclidean distance, which is not limited by the present application. In an embodiment of the present application, according to the Euclidean distance, the similarity between each group of first key frame features and second key frame features can be determined, because the smaller the Euclidean distance, the greater the similarity, so a feasible formula for calculating similarity can be expressed as: w = 1 / (1+d), where w represents similarity and d represents Euclidean distance.

[0107] Then, the difference between 1 and the similarity is calculated to determine the dissimilarity between each group of first key frame features and second key frame features, and the dissimilarity can be expressed as 1-w. Next, in the embodiment of the present application, the product of the dissimilarity corresponding to each group of first key frame features and second key frame features can be calculated to obtain a first value L, and the difference between 1 and the first value can be calculated to determine the correlation data between the first material track and the second material track, thereby further determining the correlation data between the first video template and the second video template.

[0108] It should be noted that in the embodiment of the present application, the number of material tracks in the video template may be multiple. When there are multiple material tracks, the correlation data corresponding to each group of material tracks can be summed to obtain the correlation data of the first video template and the second video template.

[0109] In the embodiment of the present application, according to the correlation data between the first video template and the second video template under all strategies, the infringement coefficient of the target video template relative to the benchmark video template can be determined. Specifically, the process may include:

[0110] Detecting a first ratio of the number of key frames in the first material trajectory to the total number of key frames in the first video template;

[0111] Detecting a second ratio of the number of key frames in the second material track to the total number of key frames in the second video template;

[0112] Determining a correlation impact value between the first video template and the second video template according to the first ratio and the second ratio;

[0113] The average of the corresponding correlation impact values ​​under all strategies is calculated to obtain the infringement coefficient of the target video template relative to the benchmark video template.

[0114] In the embodiment of the present application, when calculating the infringement coefficient, a first ratio of the number of key frames in the first material track to the total number of key frames in the first video template can be detected, denoted as R1, and a second ratio of the number of key frames in the second material track to the total number of key frames in the second video template can be detected, denoted as R2. Based on the first ratio and the second ratio, the correlation data of this group of tracks can be determined to determine the overall correlation impact value. For example, it can be calculated using the following formula:

[0115] R=(1-(1-R1)(1-R2))C

[0116] In the formula, R represents the correlation influence value between the first video template and the second video template, R1 represents the first ratio, R2 represents the second ratio, and C represents the correlation data between the first video template and the second video template.

[0117] Through the above process, the correlation impact values ​​corresponding to the video templates under different strategies can be determined, and the infringement coefficient of the target video template relative to the benchmark video template can be obtained by taking the average value.

[0118] In the embodiment of the present application, the higher the infringement coefficient, the more likely the target video template is to be consistent with the benchmark video template, and the higher the probability of infringement. Specifically, a threshold can be set for comparison. If the infringement coefficient of the target video template relative to the benchmark video template exceeds the threshold, it means that the target video template is infringing, and the infringed object is the current benchmark video template.

[0119] The technical solution in this application has at least the following technical effects:

[0120] 1) Significantly improve detection efficiency: The deep learning model can automatically extract high-level feature representations from video templates, avoiding the tedious process of manual feature design, while supporting parallel processing of large amounts of video content, thereby greatly improving the efficiency of infringement detection.

[0121] 2) Improve detection accuracy: By leveraging the powerful learning capabilities of deep learning models, this application can capture subtle differences and unique features in video templates. Through sophisticated feature comparison and similarity calculation, it can accurately identify infringement behaviors and reduce the probability of misjudgment and missed judgments.

[0122] 3) Enhanced copyright protection capabilities: By building and maintaining a video template feature database, this application provides copyright holders with an efficient and reliable infringement detection tool, which helps to promptly discover and stop infringements, safeguard the legitimate rights and interests of video template creators, and promote the healthy and orderly development of video content.

[0123] 4) Strong adaptability: The system and method of the present application are not only applicable to existing video template infringement detection, but can also adapt to future developments and changes in video content formats and technologies by continuously optimizing deep learning models and feature databases, thereby maintaining their long-term effectiveness and competitiveness.

[0124] In summary, this application effectively solves the efficiency and accuracy problems in video template infringement detection by introducing deep learning technology, provides strong technical support for copyright protection of video templates, and has significant technical effects and broad application prospects.

[0125] Reference Figure 5 In an embodiment of the present application, a video template infringement detection device is also provided, comprising:

[0126] An acquisition unit 510 is used to acquire a target video template to be detected and a reference video template for comparison with the target video template;

[0127] The processing unit 520 is used to perform anti-interference graph synthesis analysis processing under multiple strategies on the target video template and the benchmark video template to obtain a first video template and a second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing;

[0128] An extraction unit 530, configured to extract a first material track of the first video template, and extract a second material track of the second video template;

[0129] A calculation unit 540, configured to determine correlation data between the first video template and the second video template under a corresponding strategy according to the first material track and the second material track;

[0130] The statistical unit 550 is used to determine the infringement coefficient of the target video template relative to the benchmark video template according to the correlation data between the first video template and the second video template under all strategies.

[0131] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0132] Reference Figure 6 , an embodiment of the present application provides an electronic device, including:

[0133] at least one processor 610;

[0134] At least one memory 620, used to store at least one program;

[0135] When the at least one program is executed by the at least one processor 610, the at least one processor 610 implements the above-mentioned video template infringement detection method.

[0136] Similarly, the contents of the above method embodiments are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0137] The embodiment of the present application further provides a computer-readable storage medium, in which a program executable by the processor 610 is stored. When the program executable by the processor 610 is executed by the processor 610, it is used to execute the above-mentioned video template infringement detection method.

[0138] Similarly, the contents of the above method embodiments are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0139] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0140] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional techniques of the engineer. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0141] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0142] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0143] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0144] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0145] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0146] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0147] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Technical personnel familiar with the field can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A video template infringement detection method, characterized in that: The method comprises: Acquire a target video template to be detected and a reference video template for comparison with the target video template; Performing anti-interference graph synthesis analysis processing under multiple strategies on the target video template and the benchmark video template to obtain a first video template and a second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing; Extracting a first material track of the first video template, and extracting a second material track of the second video template; Determining correlation data between the first video template and the second video template under a corresponding strategy according to the first material track and the second material track; According to the correlation data between the first video template and the second video template under all strategies, an infringement coefficient of the target video template relative to the benchmark video template is determined.

2. A video template infringement detection method according to claim 1, characterized in that: The strategy types of the anti-interference graph synthesis analysis processing include fully transparent synthesis analysis processing, fully unsaturated synthesis analysis processing, fully saturated synthesis analysis processing and random synthesis analysis processing.

3. A video template infringement detection method according to claim 2, characterized in that: The anti-interference graph synthesis analysis processing is performed on the target video template and the benchmark video template under multiple strategies to obtain the first video template and the second video template corresponding to each strategy, including: The target video template is used as the first video template corresponding to the target video template under the strategy of fully transparent synthesis analysis and processing, and the benchmark video template is used as the second video template corresponding to the benchmark video template under the strategy of fully transparent synthesis analysis and processing; Inputting the same black background image into the target video template and the reference video template, obtaining a first video template corresponding to the target video template under the strategy of completely unsaturated synthesis analysis and processing, and a second video template corresponding to the reference video template under the strategy of completely unsaturated synthesis analysis and processing; Inputting the same white background image into the target video template and the reference video template, obtaining a first video template corresponding to the target video template under the strategy of full saturation synthesis analysis processing, and a second video template corresponding to the reference video template under the strategy of full saturation synthesis analysis processing; The same random color picture is input into the target video template and the reference video template to obtain a first video template corresponding to the target video template under the strategy of random synthesis analysis and processing, and a second video template corresponding to the reference video template under the strategy of random synthesis analysis and processing.

4. A video template infringement detection method according to claim 1, characterized in that: The extracting the first material track of the first video template includes: Extracting key frames from the first video template to obtain a key frame sequence corresponding to the first video template; Inputting the key frame sequence into a pre-trained material trajectory model to extract a first material trajectory of the first video template; The first material track includes several key frames in the first video template.

5. A video template infringement detection method according to claim 1, characterized in that: The determining, according to the first material track and the second material track, correlation data of the first video template and the second video template under the corresponding strategy includes: Extracting a first track feature of the first material track, and extracting a second track feature of the second material track; wherein the first track feature includes a plurality of first key frame features, and the second track feature includes the same number of second key frame features as the first key frame features; Calculating the Euclidean distance between each group of the first key frame features and the second key frame features; Determine, according to the Euclidean distance, the similarity between each group of the first key frame features and the second key frame features; Calculate the difference between 1 and the similarity to determine the dissimilarity between each group of the first key frame features and the second key frame features; Calculating the product of the dissimilarity corresponding to each group of the first key frame feature and the second key frame feature to obtain a first value; According to the difference between 1 and the first value, correlation data between the first video template and the second video template is determined.

6. A video template infringement detection method according to claim 1, characterized in that: The determining, according to the correlation data between the first video template and the second video template under all strategies, the infringement coefficient of the target video template relative to the benchmark video template includes: Detecting a first ratio of the number of key frames in the first material trajectory to the total number of key frames in the first video template; Detecting a second ratio of the number of key frames in the second material track to the total number of key frames in the second video template; Determining a correlation impact value between the first video template and the second video template according to the first ratio and the second ratio; The average of the corresponding correlation impact values ​​under all strategies is calculated to obtain the infringement coefficient of the target video template relative to the benchmark video template.

7. A video template infringement detection method according to claim 6, characterized in that: The determining, according to the first ratio and the second ratio, a correlation impact value between the first video template and the second video template includes: The correlation impact value of the first video template and the second video template is calculated by the following formula: R=(1-(1-R1)(1-R2))C In the formula, R represents the correlation influence value between the first video template and the second video template, R1 represents the first ratio, R2 represents the second ratio, and C represents the correlation data between the first video template and the second video template.

8. A video template infringement detection device, characterized in that: The device comprises: An acquisition unit, used to acquire a target video template to be detected and a reference video template for comparison with the target video template; A processing unit is used to perform anti-interference graph synthesis analysis processing on the target video template and the benchmark video template under multiple strategies to obtain a first video template and a second video template corresponding to each strategy; wherein the first video template is the target video template obtained after the anti-interference graph synthesis analysis processing, and the second video template is the benchmark video template obtained after the anti-interference graph synthesis analysis processing; an extraction unit, configured to extract a first material track of the first video template, and extract a second material track of the second video template; a calculation unit, configured to determine correlation data between the first video template and the second video template under a corresponding strategy according to the first material track and the second material track; A statistical unit is used to determine the infringement coefficient of the target video template relative to the benchmark video template according to the correlation data of the first video template and the second video template under all strategies.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a video template infringement detection method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement a video template infringement detection method as described in any one of claims 1-7 when executed by the processor.

Images