Video operation behavior data updating method, device, equipment and storage medium

Abstract

The present invention discloses a method, device, equipment and storage medium for updating video operation behavior data, the method comprising: determining the associated video associated with the current video; when detecting the user operation behavior corresponding to the current video, determining the correlation between the current video and the associated video; obtaining the operation behavior data corresponding to the user operation behavior, and determining the correction value of the operation behavior data statistics of the associated video according to the correlation and the operation behavior data; updating the operation behavior data statistics based on the correction value. The present invention not only realizes the fair distribution of video traffic, but also can prevent others from stealing original videos to obtain benefits, thereby causing the original video creator to suffer losses in video revenue.

Description

Technical Field

[0001] The present invention relates to the field of video processing technology, and in particular to a method, device, equipment and storage medium for updating video operation behavior data. Background Art

[0002] At present, the original videos of the original video creators on the Internet are used by others after being quoted, stolen, adapted, etc., to generate new videos. When the new video is released online and viewed by users, the number of views of the new video will increase, but the number of views of the original video will not increase due to the update of the number of views of the new video, resulting in inaccurate statistics on the number of views of the original video, which seriously affects the creative income of the original video creator. Summary of the invention

[0003] The embodiments of the present invention provide a method, device, equipment and storage medium for updating video operation behavior data, aiming to solve the technical problem that after the original video of the original video creator is used by others to generate a new video, the views of the original video will not increase due to the update of the views of the new video, resulting in inaccurate views statistics of the original video.

[0004] An embodiment of the present invention provides a method for updating video operation behavior data, the method comprising:

[0005] Determine the associated videos associated with the current video;

[0006] When detecting that the current video corresponds to a user operation behavior, determining a correlation degree between the current video and the associated video;

[0007] Acquire operation behavior data corresponding to the user operation behavior, and determine a correction value of a statistical value of the operation behavior data of the associated video according to the correlation degree and the operation behavior data;

[0008] The operation behavior data statistics are updated based on the correction value.

[0009] Optionally, the step of determining an associated video associated with the current video includes:

[0010] Determine the video similarity and / or picture matching ratio between the current video and a preset video in a preset video resource library;

[0011] According to the video similarity and / or the picture matching ratio, an associated video associated with the current video is determined from the video resource library.

[0012] Optionally, the step of determining, from the video resource library, an associated video associated with the current video according to the video similarity and / or the picture matching ratio includes:

[0013] Selecting a preset video corresponding to the video similarity being greater than a preset video similarity threshold in the video resource library;

[0014] When the picture matching ratio between the selected preset video and the current video is greater than a preset ratio, the preset video corresponding to the picture matching ratio greater than the preset ratio is determined as the associated video.

[0015] Optionally, the step of determining the video similarity between the current video and a preset video in a preset video resource library includes:

[0016] Obtaining a video fingerprint corresponding to the current video;

[0017] Determining a fingerprint similarity between the video fingerprint and a preset video fingerprint of the preset video;

[0018] The video similarity is determined according to the fingerprint similarity.

[0019] Optionally, the step of determining the degree of association between the current video and the associated video includes:

[0020] The degree of association is determined according to the picture matching ratio.

[0021] Optionally, the step of determining a correction value of a statistical value of the operation behavior data of the associated video according to the association degree and the operation behavior data includes:

[0022] Obtaining a target correction coefficient of the correction value corresponding to the associated video;

[0023] Based on the product of the operation behavior data, the correlation degree and the target correction coefficient, a correction value of the statistical value of the operation behavior data of the associated video is determined.

[0024] Optionally, the step of obtaining a target correction coefficient of the correction value corresponding to the associated video includes:

[0025] When the associated video is an original video, using a first preset correction coefficient as the target correction coefficient;

[0026] When the associated video is a reference video, a second preset correction coefficient is used as the target correction coefficient; wherein the first preset correction coefficient is greater than the second preset correction coefficient.

[0027] In addition, to achieve the above-mentioned purpose, the present invention also provides a video operation behavior data updating device, the video operation behavior data updating device comprising:

[0028] A video selection module, used to determine the associated videos associated with the current video;

[0029] A first calculation module, configured to determine the degree of association between the current video and the associated video when detecting that the current video corresponds to a user operation behavior;

[0030] A second calculation module is used to obtain the operation behavior data corresponding to the user operation behavior, and determine the correction value of the operation behavior data statistics of the associated video according to the correlation degree and the operation behavior data;

[0031] A data updating module is used to update the operation behavior data statistics based on the correction value.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal device, which includes: a memory, a processor, and a video operation behavior data update program stored in the memory and executable on the processor, and the video operation behavior data update program, when executed by the processor, implements the steps of the above-mentioned video operation behavior data update method.

[0033] In addition, to achieve the above-mentioned purpose, the present invention further provides a storage medium on which a video operation behavior data update program is stored, and when the video operation behavior data update program is executed by a processor, the steps of the above-mentioned video operation behavior data update method are implemented.

[0034] The technical solution of a video operation behavior data updating method, device, equipment and storage medium provided in the embodiments of the present invention has at least the following technical effects or advantages:

[0035] Due to the adoption of determining the associated video associated with the current video, when the current video is detected to correspond to the user operation behavior, the association degree between the current video and the associated video is determined, the operation behavior data corresponding to the user operation behavior is obtained, and the correction value of the operation behavior data statistics of the associated video is determined based on the association degree and the operation behavior data; the technical solution of updating the operation behavior data statistics based on the correction value solves the technical problem that after the original video of the original video creator is used by others to generate a new video, the page views of the original video will not increase due to the update of the page views of the new video, resulting in inaccurate page view statistics of the original video. While the present invention realizes the update of the operation behavior data statistics of the current video, it also updates the operation behavior data statistics of the associated video, thereby increasing the operation behavior data statistics of the associated video, not only realizing the fair distribution of video traffic, so that the current video and the associated video obtain video revenue at the same time, but also avoiding the situation that others steal the original video to obtain benefits, causing the video revenue of the original video creator to suffer losses, which is conducive to combating pirated videos and stolen stream videos. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of the structure of the hardware operating environment involved in the embodiment of the present invention;

[0037] Figure 2 A schematic diagram of a flow chart of an embodiment of a method for updating video operation behavior data of the present invention;

[0038] Figure 3 Schematic diagram of the process of step S210 of the method for updating video operation behavior data of the present invention;

[0039] Figure 4 Schematic diagram of the process of step S230 of the method for updating video operation behavior data of the present invention;

[0040] Figure 5 It is a functional module diagram of the video operation behavior data updating device of the present invention. DETAILED DESCRIPTION

[0041] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0042] like Figure 1 As shown, Figure 1 It is a schematic diagram of the structure of the hardware operating environment involved in the embodiment of the present invention.

[0043] It should be noted that Figure 1 This can be a structural diagram of the hardware operating environment of the terminal device.

[0044] As a way to implement this, Figure 1 As shown, the embodiment of the present invention relates to a terminal device, which includes: a processor 1001, such as a CPU, a memory 1002, and a communication bus 1003. The communication bus 1003 is used to realize the connection and communication between these components.

[0045] The memory 1002 may be a high-speed RAX memory or a stable memory (non-volatile XeXory), such as a disk memory. Figure 1 As shown, the memory 1002 as a storage medium may include a video operation behavior data update program; and the processor 1001 may be used to call the video operation behavior data update program stored in the memory 1002, and perform the following operations:

[0046] Determine the associated videos associated with the current video;

[0047] When detecting that the current video corresponds to a user operation behavior, determining a correlation degree between the current video and the associated video;

[0048] Acquire operation behavior data corresponding to the user operation behavior, and determine a correction value of a statistical value of the operation behavior data of the associated video according to the correlation degree and the operation behavior data;

[0049] The operation behavior data statistics are updated based on the correction value.

[0050] Further, the processor 1001 may be used to call the video operation behavior data update program stored in the memory 1002, and perform the following operations:

[0051] Determine the video similarity and / or picture matching ratio between the current video and a preset video in a preset video resource library;

[0052] According to the video similarity and / or the picture matching ratio, an associated video associated with the current video is determined from the video resource library.

[0053] Further, the processor 1001 may be used to call the video operation behavior data update program stored in the memory 1002, and perform the following operations:

[0054] Selecting a preset video corresponding to the video similarity being greater than a preset video similarity threshold in the video resource library;

[0055] When the picture matching ratio between the selected preset video and the current video is greater than a preset ratio, the preset video corresponding to the picture matching ratio greater than the preset ratio is determined as the associated video.

[0056] Further, the processor 1001 may be used to call the video operation behavior data update program stored in the memory 1002, and perform the following operations:

[0057] Obtaining a video fingerprint corresponding to the current video;

[0058] Determining a fingerprint similarity between the video fingerprint and a preset video fingerprint of the preset video;

[0059] The video similarity is determined according to the fingerprint similarity.

[0060] Further, the processor 1001 may be used to call the video operation behavior data update program stored in the memory 1002, and perform the following operations:

[0061] The degree of association is determined according to the picture matching ratio.

[0062] Further, the processor 1001 may be used to call the video operation behavior data update program stored in the memory 1002, and perform the following operations:

[0063] Obtaining a target correction coefficient of the correction value corresponding to the associated video;

[0064] Based on the product of the operation behavior data, the correlation degree and the target correction coefficient, a correction value of the statistical value of the operation behavior data of the associated video is determined.

[0065] Further, the processor 1001 may be used to call the video operation behavior data update program stored in the memory 1002, and perform the following operations:

[0066] When the associated video is an original video, using a first preset correction coefficient as the target correction coefficient;

[0067] When the associated video is a reference video, a second preset correction coefficient is used as the target correction coefficient; wherein the first preset correction coefficient is greater than the second preset correction coefficient.

[0068] The embodiment of the present invention provides an embodiment of a method for updating video operation behavior data. It should be noted that although a logical order is shown in the flow chart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0069] like Figure 2 As shown, in one embodiment of the present invention, the video operation behavior data updating method of the present invention includes the following steps:

[0070] Step S210: Determine the associated videos associated with the current video.

[0071] In this embodiment, the current video can be understood as the video that the user is browsing, and the associated video may be the original video or the referenced video. The original video can be understood as the video created by the original video creator. For example, user A shot a 15-second sunset video on January 1, 2022, and then uploaded it to the Internet at 15:00 on January 2, 2022, and named it Video A (assuming that there was no video A on the Internet before), that is, the video A uploaded to the Internet at 15:00 on January 2, 2022 can be understood as the original video. If user A sees video A and uses part of the clips in video A to make video B, video B is a referenced video because video B quotes part of the clips in video A. Then, if the video lens included in the current video that the user is browsing belongs to video A and also belongs to video B, then video A and video B are associated with the current video, the current video also belongs to the referenced video, and video B is also a referenced video of the current video.

[0072] Specifically, a video resource library is pre-established, and a large number of preset videos are stored in the video resource library. When a user browses a video, the associated video associated with the current video can be found from the video resource library, that is, one of the original video and the referenced video associated with the current video can be found from the video resource library. If the associated video found is the original video, there is one original video, and if the associated video found is the referenced video, there may be one or more referenced videos.

[0073] Step S220: When it is detected that the current video corresponds to a user operation behavior, the degree of association between the current video and the associated video is determined.

[0074] In this embodiment, user operation behavior can be understood as a series of behavioral operations performed on the current video when the user browses the current video, such as like, favorite, comment, forward, download, etc. There is operation behavior data corresponding to the user operation behavior, and the operation behavior data includes at least one of the number of likes, number of favorites, number of downloads, number of comments, number of forwards, etc. For example, if the user comments on the current video, that is, the user operation behavior is a comment, the corresponding operation behavior data will increase, that is, the number of comments will increase. The correlation between the current video and the associated video is determined based on the video shots included in the current video. Because the associated video also includes the video shots included in the current video, the greater the proportion of the video shots included in the current video, the higher the correlation.

[0075] Specifically, when a user operation behavior corresponding to the current video is detected, it means that the user has performed a behavioral operation on the current video (such as liking it), and then based on the video shot displayed by the current video when the user performs the behavioral operation on the current video, the correlation between the current video and the original video is determined.

[0076] Step S230: obtaining the operation behavior data corresponding to the user operation behavior, and determining a correction value of the operation behavior data statistics of the associated video according to the correlation degree and the operation behavior data.

[0077] Step S240: updating the operation behavior data statistics based on the correction value.

[0078] In this embodiment, the operation behavior data statistics can be understood as the numerical value of the operation behavior data counted after the user performs a behavior operation on the video. The operation behavior data statistics include at least one of the likes statistics, the favorites statistics, the download statistics, the comments statistics, the forwarding statistics, etc. For example, the operation behavior data statistics are the likes statistics. The user visits to the video can be characterized by the operation behavior data statistics, and the video can be recommended by the operation behavior data statistics. Considering that if a user quotes part of the original video to make a new video, if the video made by the user is published, the video obtains traffic due to the quoted part of the video, so that the operation behavior data statistics of the video increases, but the operation behavior data statistics of the original video does not increase, so there will be a problem of unfairness to the original video creator of the original video. Based on this, after obtaining the correlation between the current video and the associated video, the present embodiment allows the current video to obtain video traffic while allowing the associated video associated with the current video to obtain video traffic at the same time. That is, while updating the operational behavior data statistics of the current video, the operational behavior data statistics of the associated videos are also updated, thereby increasing the operational behavior data statistics of the associated videos. This not only achieves fair distribution of video traffic, allowing the current video and the associated videos to obtain video revenue at the same time, but also prevents others from stealing the original video to gain profits, thereby causing the original video creator to suffer losses in video revenue. This is beneficial to combating pirated videos and stolen streams.

[0079] Specifically, after or at the same time as determining the correlation between the current video and the associated video, the operation behavior data corresponding to the user's operation behavior is also obtained, for example, if the user's operation behavior is to like, the number of likes of the operation behavior is obtained. Then, based on the obtained correlation and operation behavior data, the correction value of the statistical value of the operation behavior data of the associated video is calculated, and then the statistical value of the operation behavior data of the associated video is updated according to the correction value, thereby increasing the statistical value of the operation behavior data of the associated video, so that the associated video associated with the current video also obtains video traffic at the same time. Among them, after the operation behavior data is determined, the operation behavior data is unchanged, and the size of the correlation is related to whether the associated video is the original video or the referenced video. If the associated video is the original video, the correlation is larger, the correction value is larger, and the increase in the statistical value of the operation behavior data of the associated video is larger; if the associated video is a referenced video, the correlation is smaller, the correction value is smaller, and the increase in the statistical value of the operation behavior data of the associated video is smaller. Among them, when the associated video is a reference video and there is only one reference video, the calculated correction value has one, that is, the updated operation behavior data statistical value of the associated video = the operation behavior data statistical value + the correction value; when the associated video is a reference video and there are multiple reference videos, the calculated correction value has multiple, that is, the updated operation behavior data statistical value of the associated video = the operation behavior data statistical value + correction value 1 + correction value 2 +... + correction value N.

[0080] This embodiment adopts the method of determining the associated videos associated with the current video. When detecting the user operation behavior corresponding to the current video, the association degree between the current video and the associated videos is determined, the operation behavior data corresponding to the user operation behavior is obtained, and the correction value of the operation behavior data statistical value of the associated video is determined based on the association degree and the operation behavior data. The technical solution of updating the operation behavior data statistical value based on the correction value realizes the fair distribution of video traffic, so that the current video and the associated videos can obtain video revenue at the same time, and can also prevent others from stealing the original video to obtain benefits, thereby causing the original video creator to suffer losses in video revenue, which is beneficial to combating pirated videos and stolen stream videos.

[0081] Optional, such as Figure 3 As shown, based on the above embodiment, step S210 includes the following steps:

[0082] Step S211: Determine the video similarity and / or picture matching ratio between the current video and a preset video in a preset video resource library;

[0083] Step S212: determining, from the video resource library, associated videos associated with the current video according to the video similarity and / or the picture matching ratio.

[0084] The preset video is a video in the video resource library. The video resource library is pre-set. A large number of preset videos are stored in the video resource library. The preset videos in the video resource library may be original videos or reference videos. Whether the preset video is an original video can be determined in the following ways: (1) Videos without copyright authorization files are uniformly defined as reference videos, otherwise they are original videos. Among them, the copyright authorization file can be queried through the media asset information management platform and the copyright management platform of the video. (2) Determined by the video release date, the video with an earlier release date is the original video. (3) If it is impossible to query through the copyright authorization file, it is determined according to the video entry time in the media asset, and the video with a longer video entry time is the original video.

[0085] The video similarity between the current video and the preset videos in the preset video resource library can be understood as the similarity between the video shots in the current video and the video shots in each preset video; the picture matching ratio between the current video and the preset videos in the preset video resource library, the picture matching ratio is calculated as follows:

[0086] Picture matching ratio = (image picture in current video ∩image picture in preset video) / image picture in preset video.

[0087] After determining the video similarity and / or picture matching ratio between the current video and the preset videos in the preset video resource library, the associated videos associated with the current video can be found from the multiple preset videos stored in the video resource library according to the video similarity, the associated videos associated with the current video can be found from the multiple preset videos stored in the video resource library according to the picture matching ratio, or the associated videos associated with the current video can be found from the multiple preset videos stored in the video resource library according to the video similarity and the picture matching ratio.

[0088] Optionally, step S212 specifically includes the following steps:

[0089] Selecting a preset video corresponding to the video similarity being greater than a preset video similarity threshold in the video resource library;

[0090] When the picture matching ratio between the selected preset video and the current video is greater than a preset ratio, the preset video corresponding to the picture matching ratio greater than the preset ratio is determined as the associated video.

[0091] It should be understood that the video similarity between the current video and each preset video is first compared, and then the preset video corresponding to the video similarity greater than the preset video similarity threshold is selected from the video resource library, and the selected preset video is used as the candidate video, taking into account the situation that there are multiple candidate videos, and then it is determined whether the screen matching ratio between each candidate video and the current video is greater than the preset ratio, and then the candidate video corresponding to the screen matching ratio greater than the preset ratio is determined as the associated video. For example, when the user is browsing the current video, the video fingerprint technology detects that the current video currently watched by the user in the current video, and the preset video with a video similarity greater than 80% is found from the preset videos in the preset video resource library as the candidate video, and then the preset video with a screen matching ratio greater than 60% is selected from the candidate video as the associated video, which can improve the accuracy of determining the associated video associated with the current video.

[0092] Optionally, the step of determining the video similarity between the current video and a preset video in a preset video resource library includes:

[0093] Obtaining a video fingerprint corresponding to the current video;

[0094] Determining a fingerprint similarity between the video fingerprint and a preset video fingerprint of the preset video;

[0095] The video similarity is determined according to the fingerprint similarity.

[0096] Video fingerprint is a technology for software to identify, extract, and compress videos, which can generate a unique "fingerprint" to represent a video file. The current video has its own video fingerprint, and the preset videos in the video resource library also have their own video fingerprints. Specifically, when the user browses the video, the video fingerprint of the current video and the video fingerprint of the preset video are extracted, and then the fingerprint similarity between the video fingerprint of the current video and the preset video fingerprint of the preset video in the video resource library is calculated. The calculated fingerprint similarity is the video similarity between the current video and the preset video in the preset video resource library. Among them, the calculation of fingerprint similarity can be calculated by methods such as cosine similarity and Euclidean distance.

[0097] Optionally, the step of determining the degree of association between the current video and the associated video includes: determining the degree of association according to the screen matching ratio. It should be understood that after obtaining the associated video associated with the current video, the screen matching ratio between the current video and the associated video can also be obtained, that is, the screen matching ratio between the current video and the associated video is used as the degree of association between the two. Among them, the screen matching ratio is positively correlated with the degree of association, and the greater the screen matching ratio between the current video and the associated video, the greater the degree of association between the two.

[0098] Optional, such as Figure 4 As shown, based on the above embodiment, step S230 includes the following steps:

[0099] Step S231: obtaining a target correction coefficient of the correction value corresponding to the associated video;

[0100] Step S232: Determine a correction value of the statistical value of the operation behavior data of the associated video based on the product of the operation behavior data, the correlation degree and the target correction coefficient.

[0101] It should be understood that the target correction coefficient is used to correct the correction value, and each preset video in the video resource library is associated with a corresponding target correction coefficient, and the corresponding associated video is also associated with a corresponding target correction coefficient. After finding the associated video from the video resource library, the target correction coefficient of the correction value corresponding to the associated video can be obtained.

[0102] After obtaining the target correction coefficient, the correction value of the operation behavior data statistics of the associated video is calculated according to the preset calculation formula, that is:

[0103] The correction value of the operation behavior data statistic=operation behavior data×association×target correction coefficient. For example, if the operation behavior data statistic is collection, the correction value of the collection statistic=number of collections×association×target correction coefficient.

[0104] Optionally, step S231 specifically includes the following steps:

[0105] When the associated video is an original video, using a first preset correction coefficient as the target correction coefficient;

[0106] When the associated video is a reference video, the second preset correction coefficient is used as the target correction coefficient.

[0107] Since the preset video is the original video or the referenced video, the associated video obtained is also the original video or the referenced video. The target correction coefficient is set according to the original video and the referenced video. The first preset correction coefficient is set corresponding to the original video, such as the first preset correction coefficient = 1, that is, the target correction coefficient = 1, and the second preset correction coefficient is set corresponding to the referenced video, such as 0<second preset correction coefficient<1, that is, the first preset correction coefficient is greater than the second preset correction coefficient, that is, when the associated video is the original video, the target correction coefficient is larger, and the calculated correction value is larger; when the associated video is the referenced video, the target correction coefficient is smaller, and the calculated correction value is smaller, so that the associated video can obtain video traffic fairly and evenly.

[0108] like Figure 5As shown, the present invention provides a video operation behavior data updating device, the video operation behavior data updating device comprising:

[0109] The video selection module 310 is used to determine the associated videos associated with the current video;

[0110] A first calculation module 320 is used to determine the correlation between the current video and the associated video when detecting that the current video corresponds to a user operation behavior;

[0111] A second calculation module 330 is used to obtain the operation behavior data corresponding to the user operation behavior, and determine the correction value of the operation behavior data statistics of the associated video according to the correlation degree and the operation behavior data;

[0112] The data updating module 340 is used to update the operation behavior data statistics based on the correction value.

[0113] Optionally, the video selection module 310 includes:

[0114] A parameter calculation unit, used to determine the video similarity and / or picture matching ratio between the current video and a preset video in a preset video resource library;

[0115] The video search unit is used to determine the associated video associated with the current video from the video resource library according to the video similarity and / or the picture matching ratio.

[0116] Optionally, the video search unit includes:

[0117] A first calculation subunit is used to select, from the video resource library, a preset video corresponding to a video whose video similarity is greater than a preset video similarity threshold;

[0118] The second calculation subunit is used to determine the preset video corresponding to the picture matching ratio greater than the preset ratio as the associated video when the picture matching ratio between the selected preset video and the current video is greater than the preset ratio.

[0119] Optionally, the parameter calculation unit, in determining the video similarity between the current video and a preset video in a preset video resource library, includes:

[0120] A fingerprint acquisition unit, used to acquire a video fingerprint corresponding to the current video;

[0121] The similarity unit is used to determine the fingerprint similarity between the video fingerprint and the preset video fingerprint of the preset video, and determine the video similarity according to the fingerprint similarity.

[0122] Optionally, in determining the degree of association between the current video and the associated video, the first calculation module 320 is specifically configured to determine the degree of association according to the picture matching ratio.

[0123] Optionally, the second calculation module 330 includes:

[0124] A coefficient acquisition unit, used to acquire a target correction coefficient of the correction value corresponding to the associated video;

[0125] The numerical correction unit is used to determine the correction value of the statistical value of the operation behavior data of the associated video based on the product of the operation behavior data, the correlation degree and the target correction coefficient.

[0126] Optionally, the coefficient acquisition unit is specifically used to use a first preset correction coefficient as the target correction coefficient when the associated video is an original video; and use a second preset correction coefficient as the target correction coefficient when the associated video is a referenced video; wherein the first preset correction coefficient is greater than the second preset correction coefficient.

[0127] The specific implementation of the video operation behavior data updating device of the present invention is basically the same as the above-mentioned video operation behavior data updating method embodiments, and will not be repeated here.

[0128] Optionally, the present invention also provides a terminal device, comprising: a memory, a processor, and a video operation behavior data update program stored in the memory and executable on the processor, wherein the video operation behavior data update program implements the steps of the above-mentioned video operation behavior data update method when executed by the processor.

[0129] Optionally, the present invention further provides a storage medium on which a video operation behavior data updating program is stored, and when the video operation behavior data updating program is executed by a processor, the steps of the above-mentioned video operation behavior data updating method are implemented.

[0130] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] It should be noted that in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0135] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for updating video operation behavior data, characterized in that: The video operation behavior data updating method comprises: Determine the associated videos associated with the current video; When detecting that the current video corresponds to a user operation behavior, determining a correlation degree between the current video and the associated video; Acquire operation behavior data corresponding to the user operation behavior, and when the associated video is an original video, use a first preset correction coefficient as a target correction coefficient; when the associated video is a referenced video, use a second preset correction coefficient as the target correction coefficient; wherein the first preset correction coefficient is greater than the second preset correction coefficient; determine a correction value of a statistical value of the operation behavior data of the associated video based on the product of the operation behavior data, the degree of association, and the target correction coefficient; The operation behavior data statistics are updated based on the correction value.

2. The method according to claim 1, characterized in that The step of determining the associated video associated with the current video comprises: Determine the video similarity and / or picture matching ratio between the current video and a preset video in a preset video resource library; According to the video similarity and / or the picture matching ratio, an associated video associated with the current video is determined from the video resource library.

3. The method according to claim 2, characterized in that The step of determining, from the video resource library, an associated video associated with the current video according to the video similarity and / or the picture matching ratio comprises: Selecting a preset video corresponding to the video similarity being greater than a preset video similarity threshold in the video resource library; When the picture matching ratio between the selected preset video and the current video is greater than a preset ratio, the preset video corresponding to the picture matching ratio greater than the preset ratio is determined as the associated video.

4. The method according to claim 2, characterized in that The step of determining the video similarity between the current video and a preset video in a preset video resource library comprises: Obtaining a video fingerprint corresponding to the current video; Determining a fingerprint similarity between the video fingerprint and a preset video fingerprint of the preset video; The video similarity is determined according to the fingerprint similarity.

5. The method according to claim 2, characterized in that The step of determining the degree of association between the current video and the associated video comprises: The degree of association is determined according to the picture matching ratio.

6. A video operation behavior data updating device, characterized in that: The video operation behavior data updating device comprises: A video selection module, used to determine the associated videos associated with the current video; A first calculation module, configured to determine the degree of association between the current video and the associated video when detecting that the current video corresponds to a user operation behavior; A second calculation module is used to obtain the operation behavior data corresponding to the user operation behavior, and when the associated video is an original video, use the first preset correction coefficient as the target correction coefficient; when the associated video is a referenced video, use the second preset correction coefficient as the target correction coefficient; wherein the first preset correction coefficient is greater than the second preset correction coefficient; based on the operation behavior data, the correlation degree and the product of the target correction coefficient, determine the correction value of the statistical value of the operation behavior data of the associated video; A data updating module is used to update the operation behavior data statistics based on the correction value.

7. A terminal device, characterized in that: The terminal device includes: a memory, a processor, and a video operation behavior data update program stored in the memory and executable on the processor. When the video operation behavior data update program is executed by the processor, the steps of the video operation behavior data update method according to any one of claims 1 to 5 are implemented.

8. A storage medium, characterized in that: A video operation behavior data updating program is stored thereon, and when the video operation behavior data updating program is executed by a processor, the steps of the video operation behavior data updating method according to any one of claims 1 to 5 are implemented.

Images