A video analysis method, device, apparatus and storage medium

Abstract

Embodiments of the present disclosure provide a video analysis method, device, equipment and storage medium. The method comprises: determining a target video meeting a first analysis trigger condition from at least one video to be analyzed, and detecting whether the target video has a video feature; determining a corresponding condition determination strategy according to the detection result of the video feature; if a condition determination result corresponding to the condition determination strategy meets a second analysis trigger condition, performing video feature analysis on the target video to obtain a current video feature of the target video. By using the method, the video feature analysis timing of the video in different video life cycle stages can be determined more accurately, the effective use of video analysis computing resources is ensured, the computing resource consumption is reduced, the effective determination of the video feature on the video optimization and promotion strategy is ensured, and the overall improvement of the video viewing experience is realized.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a video analysis method, apparatus, device, and storage medium. Background Technology

[0002] As the object consumed or created in video business applications, the playback characteristics of videos have a significant impact on the viewer's viewing experience. For example, when watching landscape videos, viewers have high requirements for video clarity, while when watching game videos, viewers have high requirements for smooth playback. Therefore, choosing to improve video clarity or improve playback smoothness can be seen as determining optimization strategies to enhance the video viewing experience.

[0003] In practical applications, technicians have found that optimization strategies for video playback can be determined in advance based on certain video characteristics inherent in the video itself. Therefore, video feature analysis can be performed before determining the optimization strategy. However, for the same video, its video characteristics often change throughout its lifecycle. Therefore, as the video lifecycle progresses, it is necessary to repeatedly analyze the video features to determine optimization strategies that better match the viewing experience based on the new video characteristics.

[0004] However, if the process of performing video feature analysis is too frequent, the differences in the results determined by each analysis may be very small, which will not affect the determination of the optimization and improvement strategy. Instead, it will lead to a waste of computing resources, especially as the number of videos to be analyzed increases, which will increase the burden of allocating computing resources. If the analysis frequency is too slow, the problem of not being able to obtain video features in a timely and accurate manner will occur, which will affect the determination of video optimization and improvement strategies and thus affect the video viewing experience. Summary of the Invention

[0005] This disclosure provides a video analysis method, apparatus, device, and storage medium to effectively determine the timing of video analysis execution.

[0006] In a first aspect, embodiments of this disclosure provide a video analysis method, the method comprising:

[0007] From at least one video to be analyzed, identify a target video that meets the first analysis trigger condition, and detect whether the target video already has video features;

[0008] Determine the corresponding conditional judgment strategy based on the detection results of video features;

[0009] If the condition determination result corresponding to the condition determination strategy satisfies the second analysis trigger condition, then video feature analysis is performed on the target video to obtain the current video features of the target video.

[0010] Secondly, embodiments of this disclosure also provide a video analysis device, the device comprising:

[0011] The first determining module is used to determine a target video that meets the first analysis triggering condition from at least one video to be analyzed, and to detect whether the target video already has video features;

[0012] The second determination module is used to determine the corresponding condition judgment strategy based on the detection results of video features;

[0013] The feature analysis module is used to perform video feature analysis on the target video and obtain the current video features of the target video if the condition determination result corresponding to the condition determination strategy meets the second analysis trigger condition.

[0014] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0015] One or more processors;

[0016] Storage device for storing one or more programs.

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the video analysis method provided in the first aspect of the present disclosure.

[0018] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the video analysis method provided in the first aspect of embodiments of this disclosure.

[0019] This disclosure provides a video analysis method, apparatus, device, and storage medium. The method includes: identifying target videos that meet a first analysis trigger condition from at least one video to be analyzed, and detecting whether the target video already possesses video features; determining a corresponding condition judgment strategy based on the detection result of the video features; and if the condition judgment result corresponding to the condition judgment strategy meets a second analysis trigger condition, performing video feature analysis on the target video to obtain the current video features of the target video. This embodiment's technical solution can control the timing of video feature analysis of the video to be analyzed by setting analysis trigger conditions. It first filters out target videos that meet the first analysis trigger condition from the video to be analyzed, then performs a second filtering on the target videos using a matching condition judgment strategy, and finally only filters out target videos that meet the second analysis trigger condition for video feature analysis. Compared with existing technologies, this technical solution can more accurately determine the timing of video feature analysis at different stages of the video lifecycle, ensuring the effective utilization of video analysis computing resources and reducing computing resource consumption; it also better ensures the effective determination of video feature optimization and improvement strategies, thereby achieving an overall improvement in the video viewing experience. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 This is a flowchart illustrating a video analysis method provided in an embodiment of the present disclosure;

[0022] Figure 2 This is a schematic diagram of the structure of a video analysis device provided in an embodiment of the present disclosure;

[0023] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0024] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0025] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0026] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0027] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0028] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0029] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0030] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0031] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0032] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0033] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0034] It's important to note that in practical applications requiring video viewing experience optimization, the effectiveness of these optimizations can often be achieved by analyzing the acquired video features. These video features are determined through video analysis. Generally, the video features present at different stages of a video's lifecycle differ, and the effectiveness of these features in improving the viewing experience varies. Therefore, for a single video, video feature analysis should be considered throughout its entire lifecycle. However, since video feature analysis requires computational resources, frequent analysis consumes even more. Furthermore, the differences between the video features obtained from frequent analysis are often small and do not significantly impact the determination of the viewing experience optimization strategy, thus wasting resources. Conversely, if video analysis is performed too infrequently, the video features may not be obtained accurately and promptly, also affecting the effectiveness of the optimization.

[0035] The existing methods for controlling the timing of video analytics cannot effectively solve the above problems, while the method provided in this embodiment can achieve effective control over the timing of video analytics execution.

[0036] Figure 1 This is a flowchart illustrating a video analysis method provided in an embodiment of this disclosure. This embodiment is applicable to situations involving video feature analysis. The method can be executed by a video analysis device, which can be implemented in software and / or hardware. Optionally, it can be implemented using an electronic device as the execution terminal, such as a mobile terminal, PC, or server. This embodiment uses a server or platform device that manages videos uploaded by clients as a preferred example for illustration.

[0037] like Figure 1 As shown in the embodiments of this disclosure, a video analysis method specifically includes the following operations:

[0038] S110. Determine a target video that meets the first analysis trigger condition from at least one video to be analyzed, and detect whether the target video already has video features.

[0039] In this embodiment, taking a server for video management as an example, the video to be analyzed can be a video received by the executing entity for feature analysis. The received video can be uploaded by a video production client, and the video to be analyzed can be a newly added video received for the first time at the current execution time, or a video that has been received but has not disappeared during the video lifecycle evolution. The number of videos to be analyzed is often large, at least one.

[0040] In this embodiment, after determining the video to be analyzed, video feature analysis is not performed directly on the video to be analyzed. Instead, this step is used to perform an initial screening of the video to be analyzed according to the first analysis triggering condition, so as to select target videos that meet the first analysis triggering condition at the current execution time, that is, suitable for video analysis.

[0041] In this embodiment, the first analysis trigger condition can be understood as the first trigger condition for video analysis of the video to be analyzed. This embodiment can set the first analysis trigger condition according to the characteristics of the video to be analyzed. For example, the video to be analyzed is mainly a newly uploaded video created by the client, or a video that has evolved according to the video lifecycle. For newly uploaded videos, feature analysis may not have been performed before, and video features may not exist; while for videos that have already participated in the evolution of the video lifecycle, the video features corresponding to the video may change as the attributes of the video change at different stages of the video lifecycle, and the originally determined video features are no longer suitable.

[0042] Based on the above analysis, determining whether the video is uploaded or received for the first time can be used as one of the triggering conditions, and determining whether the video attributes have changed at the current execution time can be used as another triggering condition.

[0043] Preferably, this embodiment provides an optimized limitation on the first analysis triggering condition, which can be specifically defined as: the video to be analyzed is the first video received; or, the first attribute information of the video to be analyzed changes relative to the set attribute item. Here, the set attribute item can be considered as an attribute item selected from the attributes possessed by the video, such as the number of times the video has been played, the title of the video, and the permission status of the video, etc. Correspondingly, this embodiment can also record the specific attribute information corresponding to the set attribute item as the first attribute information, such as the actual number of plays, the currently used title information, or the permission status information that is private or public, all of which can be considered as the first attribute information.

[0044] For example, for the video to be analyzed, it can be determined whether the video is being received for the first time. If so, it can be considered the target video. Alternatively, it can be determined whether the video to be analyzed has changed relative to the first attribute information of the set attribute item at the current execution time. If so, it can also be considered the target video. It should be noted that in this embodiment, the video to be analyzed can be monitored in real time or periodically. When a video that meets the first analysis trigger condition is detected at the current execution time or at the current detection node, the video can be identified as the target video.

[0045] In this embodiment, after the target video is determined, it can be detected whether the target video already has video features. The video features can be stored in a video feature database. By using the unique identifier of the target video, it can be searched in the video feature database to see if the target video already has video features. The search result can be used as the detection result to be obtained in this step. The detection result can include whether the target video has video features or not.

[0046] The above-described limitation on the first analysis triggering condition in this embodiment comprehensively and effectively considers the impact of the video source of the video to be analyzed (such as when the video to be analyzed is received for the first time, or when the video attributes of a video that is already within its life cycle change) on its analysis timing, ensuring the normal progress of the initial screening of video analysis timing.

[0047] S120. Determine the corresponding condition judgment strategy based on the detection results of video features.

[0048] In this embodiment, the above steps can be considered as the initial screening of the video to be analyzed before video analysis, while this step can be considered as a secondary screening to determine whether the target video identified in the initial screening is currently suitable for video analysis. The specific judgment conditions for the secondary screening vary depending on the detection results obtained in the above steps. In this embodiment, the corresponding condition judgment strategy can be determined based on the detection results, and the judgment conditions for the secondary screening are constituted by executing the condition judgment strategy, thereby obtaining the corresponding condition judgment results.

[0049] In this embodiment, the condition judgment strategy used during secondary screening varies depending on the specific content contained in the detection results. For example, the detection results mainly describe whether the target video already possesses video features. The detection result may indicate that the target video currently does not possess video features, in which case it can be considered a newly received video that has not yet undergone video analysis. For such videos, when determining the timing for secondary screening and video analysis, the condition judgment strategy used may be to predict the video popularity trend of the target video. The predicted video popularity value after executing this condition judgment strategy can be used to determine the condition judgment result corresponding to the secondary screening by comparing it with a set score threshold.

[0050] For example, when the video popularity value is higher than or equal to the set score threshold as the comparison result, the second analysis trigger condition can be met as the condition judgment result; otherwise, the second analysis trigger condition can be not met as the condition judgment result.

[0051] As described above, if the detection result indicates that the target video currently possesses video features, then the target video can be considered no longer a newly received video. The key to selecting it as the target video in the initial screening might be that the relevant attribute settings of the video have changed. For target videos identified in this situation, when determining the timing for video analysis through secondary screening, the conditional judgment strategy used could be to evaluate whether there are feature differences in the target video. The evaluation result obtained after executing this conditional judgment strategy can be used to determine the conditional judgment result corresponding to the secondary screening.

[0052] For example, if the evaluation result shows that the video features have changed significantly due to changes in the attribute items, then the failure to meet the second analysis trigger condition can be taken as the condition judgment result; otherwise, the satisfaction of the second analysis trigger condition can be taken as the condition judgment result.

[0053] S130. If the condition determination result corresponding to the condition determination strategy satisfies the second analysis trigger condition, then video feature analysis is performed on the target video to obtain the current video features of the target video.

[0054] In this embodiment, the specific timing for video analysis of the target video using the conditional judgment strategy can be determined through the above steps. After the conditional judgment strategy is executed, a corresponding conditional judgment result can be obtained. The specific content of the conditional judgment result can be either that the second analysis trigger condition is not met or that the second analysis trigger condition is met. In this embodiment, target videos that meet the second analysis trigger condition can be filtered out, and the current execution time can be considered as the video analysis execution time for this type of target video. Thus, this step can be used to perform video feature analysis on this type of target video and obtain the current video features corresponding to each type of target video.

[0055] In this embodiment, the video features can be considered as information characterizing the specific features of the target video itself. For example, they may include information reflecting the category to which the video content belongs, or information reflecting the business value of the video. In this embodiment, the relevant attributes inherent in the video can be obtained by using a pre-trained video feature analysis model, and the current video features of the target video can be obtained based on the output of the video feature analysis model.

[0056] For example, the target video attributes input into the video feature analysis model as input data may include the current number of times the target video has been played, the current playback permission status of the target video (e.g., public or private playback), the current title of the target video, and the duration of reception of the target video. Based on the above input data, the video feature analysis model can obtain the corresponding video features output by the model through logical operation.

[0057] This embodiment provides a video analysis method that can control the timing of video feature analysis by setting analysis trigger conditions. First, it filters out target videos that meet the first analysis trigger condition from the videos to be analyzed. Then, it performs a second filtering of the target videos using a matching condition judgment strategy, ultimately selecting only target videos that meet the second analysis trigger condition for video feature analysis. Compared with existing technologies, this technical solution can more accurately determine the timing of video feature analysis at different stages of the video lifecycle, ensuring the effective utilization of video analysis computing resources and reducing computing resource consumption. It also better ensures the effective determination of video feature optimization and improvement strategies, thereby achieving an overall improvement in the video viewing experience.

[0058] As a first optional embodiment of this example, based on the above embodiments, a method for determining the condition determination strategy is provided. Further, this first optional embodiment can determine the corresponding condition determination strategy based on the detection results of video features, specifically as follows:

[0059] If the detection result of the video feature is that there is currently no video feature, then the video popularity prediction of the target video will be determined as the conditional judgment strategy.

[0060] In this embodiment, as one implementation of the conditional decision-making strategy, this step may consider performing video popularity prediction on the target video as a conditional decision-making strategy when the detection result indicates that the target video currently does not possess video features. It is understood that when the detection result indicates that the target video currently does not possess video features, the target video is considered to be a newly received video that has not yet undergone video feature analysis.

[0061] For the newly received target videos that have not undergone video feature analysis, this embodiment can use this step to determine the video popularity prediction of the target video as a conditional decision strategy required for secondary screening of video analysis. After determining the conditional decision strategy in this case through this step, the execution of the determined conditional decision strategy can be started, that is, the execution of video popularity prediction of the target video can be started.

[0062] In this first optional embodiment, the steps for performing video popularity prediction on the target video can be specified as follows:

[0063] a1) Obtain the second attribute information of the target video relative to the set popularity-related attribute items.

[0064] In this embodiment, the popularity-related attribute items can be considered as attribute items selected from the attributes possessed by the target video for predicting video popularity. These popularity-related attribute items may include the number of followers of the uploader corresponding to the target video, the total number of video uploads by the uploader corresponding to the target video, the number of video uploads by the uploader corresponding to the target video on the day the target video was uploaded, the cumulative number of visits to videos uploaded by the uploader corresponding to the target video within a certain time period, the total cumulative number of plays of all videos uploaded by the uploader corresponding to the target video, the number of plays of the target video, the playback permission status of the target video (which can be public or private), and the number of days the target video has been viewed, etc. In this embodiment, the specific attribute information corresponding to the popularity-related attribute items can be recorded as the second attribute information.

[0065] In this embodiment, as an implementation method, the attribute information of each attribute item involved in the target video can be obtained through the attribute information collection platform. The execution subject of this method can obtain it from the attribute information collection platform when needed. At the same time, the obtained attribute information can also be converted and processed in a format readable by the execution subject to obtain the second attribute information involved in this step.

[0066] b1) Input the second attribute information as input data into the given popularity prediction model, and use the output popularity prediction value as the video popularity prediction result.

[0067] In this embodiment, the second attribute information can be used as input data to the trained popularity prediction model. This step can obtain the popularity prediction value output by the popularity prediction model. In this embodiment, the popularity prediction value can be used to perform a secondary screening of the video analysis timing of the target video. The screening result can be determined as the condition judgment result corresponding to the current embodiment.

[0068] In this embodiment, the second analysis triggering condition can be understood as the judgment condition on which the secondary screening of the target video for video analysis is based. When the second triggering condition is met, the target video is considered to meet the conditions for video analysis. When the second triggering condition is not met, the target video is considered not to meet the conditions for video analysis.

[0069] Based on the above condition judgment strategy execution logic, the second analysis trigger condition can be optimized to be that the video popularity prediction result is greater than the set score threshold.

[0070] In this embodiment, the set score threshold can be understood as a pre-set threshold value used as a secondary screening for video analysis. This embodiment can compare the popularity prediction value with the set score threshold, and can consider that the second analysis trigger condition is met when the popularity prediction value is greater than the set score threshold; or consider that the second analysis trigger condition is not met when the popularity prediction value is less than or equal to the set score threshold.

[0071] The above-described technical solution in this embodiment provides an implementation method for determining the condition judgment result. By implementing this method, the secondary screening of target videos that meet the timing of video analysis can be effectively achieved. This embodiment, through the secondary screening of the timing of video analysis, can achieve effective video analysis, which ensures the accurate utilization of the video features obtained from the analysis and improves resource utilization.

[0072] As a second optional embodiment of this example, based on the above embodiment, another method for determining the condition determination strategy is given. Furthermore, this second optional embodiment can further specify the determination of the corresponding condition determination strategy based on the detection results of video features as follows:

[0073] If the detection result of the video features indicates that the video features are already present, then the video attribute difference identification of the target video will be determined as the conditional judgment strategy.

[0074] In this embodiment, as another implementation of the conditional judgment strategy, this step can consider using video attribute difference identification of the target video as a conditional judgment strategy when the detection result indicates that the target video currently possesses video features. It is understood that when the detection result indicates that the target video currently possesses video features, it is assumed that the target video has been active on the video playback platform for a period of time according to its video lifecycle, and that video feature analysis has been performed on the target video during this period, obtaining the corresponding video features.

[0075] For the target videos that have been active for a period of time and possess video characteristics, this embodiment can use this group to determine the video attribute difference identification of the target videos as the condition judgment strategy required for secondary screening of video analysis. Subsequently, this step can also initiate the operation of the determined condition judgment strategy, that is, initiate the video attribute difference identification of the target videos.

[0076] In this second optional embodiment, the steps for performing video attribute difference recognition on the target video can be further specified as follows:

[0077] a2) Obtain the third attribute information of the target video relative to the set difference recognition related attribute items.

[0078] In this embodiment, the difference recognition related attribute items can be considered as attribute items selected from the attributes possessed by the target video for determining video attribute differences. These difference recognition related attribute items may include the previous playback count, previous video playback permission status, previous video title, and the number of days the previous video was received, as well as the current playback count, current playback permission status, current playback title, and the number of days the current video was received. In this embodiment, the specific attribute information corresponding to the difference recognition related attribute items can be recorded as third attribute information.

[0079] b2) Input the third attribute information as input data into the given attribute difference recognition model and obtain the output attribute difference recognition result.

[0080] In this embodiment, the third attribute information can be used as input data to the trained attribute difference recognition model. This step can obtain the attribute difference recognition result output by the attribute difference recognition model. The attribute difference recognition result can show whether there is a difference between the attribute information of the target video at the current execution time and the attribute information corresponding to the previous video analysis execution time, and whether the existing differences will cause changes in the video's feature content.

[0081] In this embodiment, the attribute difference identification result obtained above can be either an attribute difference that currently causes changes in video features, or an attribute difference that currently does not cause changes in video features. This step can use the attribute difference identification result to perform a secondary screening of the video analysis timing of the target video, and the determined condition judgment result can be considered as the screening result of the secondary screening.

[0082] Based on the above condition determination strategy execution logic, the second analysis trigger condition can be optimized to be that the attribute difference identification result is that there is currently an attribute difference that causes changes in video features.

[0083] It is known that if the attribute information of the target video at the current stage of its video lifecycle causes changes in video features, then it can be considered that the time has come to perform video analysis again. Based on this, this step can directly determine the second analysis trigger condition as the condition judgment result when there is an attribute difference that causes changes in video features; otherwise, it can be considered that the second analysis trigger condition is not met at the current execution time.

[0084] The above-described technical solution in this embodiment provides another way to determine the condition judgment result. By implementing this method, the secondary screening of target videos that meet the timing of video analysis can also be effectively achieved. This embodiment can achieve effective video analysis by performing secondary screening of the timing of video analysis, which ensures the accurate use of the video features obtained from the analysis and improves the resource utilization rate.

[0085] Based on the above embodiments, it can also be optimized to include storing the current video features relative to the target video in a set video feature database.

[0086] By executing the method provided above in this embodiment, effective analysis of video features can be achieved. In order to ensure the effective use of video features in subsequent video playback optimization, this embodiment can also save the current video features determined relative to the target video in the video feature database. The saved current video features can also be used to determine the timing of subsequent analysis of the target video.

[0087] In one storage implementation, the video identifier of the target video can be associated with the current video features and stored in a video feature database.

[0088] Figure 2 This is a schematic diagram of the structure of a video analysis device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, the device includes: a first determining module 210, a second determining module 220, and a feature analysis module 230.

[0089] The first determining module 210 is used to determine a target video that meets the first analysis triggering condition from at least one video to be analyzed, and to detect whether the target video already has video features;

[0090] The second determining module 220 is used to determine the corresponding conditional judgment strategy based on the detection results of video features;

[0091] The feature analysis module 230 is used to perform video feature analysis on the target video and obtain the current video features of the target video if the condition determination result corresponding to the condition determination strategy meets the second analysis trigger condition.

[0092] The technical solution provided in this disclosure can control the timing of video feature analysis of the video to be analyzed by setting analysis trigger conditions. First, it can filter out target videos that meet the first analysis trigger condition from the videos to be analyzed. Then, it performs a second filtering of the target videos using a matching condition judgment strategy, ultimately selecting only target videos that meet the second analysis trigger condition for video feature analysis. Compared with existing technologies, this technical solution can more accurately determine the timing of video feature analysis at different stages of the video lifecycle, ensuring the effective utilization of video analysis computing resources and reducing computing resource consumption; it also better ensures the effective determination of video feature optimization and improvement strategies, thereby achieving an overall improvement in the video viewing experience.

[0093] Furthermore, the first analysis triggering condition is: the video to be analyzed is the first video received at this time; or, the first attribute information of the video to be analyzed has changed relative to the set attribute item.

[0094] Furthermore, the second determining module 220 specifically includes:

[0095] The first determining unit is used to determine the video popularity prediction of the target video as the conditional judgment strategy when the detection result of the video feature is that there is currently no video feature.

[0096] Furthermore, the execution steps of the first determining unit in predicting the video popularity of the target video include:

[0097] Obtain the second attribute information of the target video relative to the set popularity-related attribute items;

[0098] The second attribute information is used as input data to the given popularity prediction model, and the output popularity prediction value is used as the video popularity prediction result.

[0099] The second analysis trigger condition is: the output popularity prediction value is greater than the set score threshold.

[0100] Furthermore, the second determining module 220 may specifically include:

[0101] The second determining unit is used to determine the video attribute difference identification of the target video as the conditional determination strategy when the detection result of the video feature is that the video feature is already present.

[0102] Furthermore, the second determining unit can specifically be used for:

[0103] Obtain the third attribute information of the target video relative to the set difference recognition related attribute items;

[0104] The third attribute information is input as input data into a given attribute difference recognition model, and the output attribute difference recognition result is obtained.

[0105] The second analysis trigger condition is: the attribute difference identification result is that there is currently an attribute difference that causes changes in video features.

[0106] Furthermore, the device may also include:

[0107] The storage module is used to store the current video features relative to the target video in a set video feature database.

[0108] The video analysis device provided in this disclosure can execute the video analysis method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0109] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0110] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Reference is made below. Figure 3 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 3 The diagram below shows the structure of the terminal device or server 300. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0111] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An edit / output (I / O) interface 305 is also connected to the bus 304.

[0112] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0113] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of embodiments of this disclosure.

[0114] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0115] The electronic device provided in this embodiment and the video analysis method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0116] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the video analysis method provided in the above embodiments.

[0117] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0118] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0119] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0120] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0121] The aforementioned computer-readable medium carries one or more programs. When the aforementioned one or more programs are executed by the electronic device, the electronic device causes the electronic device to: determine the current resource usage information corresponding to each resource item on the execution terminal during the operation of the application software; determine the target resource item that currently meets the resource allocation warning conditions based on the current resource usage information; and adjust the resource allocation logic of each target resource item during the operation of the application software.

[0122] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0124] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0125] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0126] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0127] According to one or more embodiments of this disclosure, [Example 1] provides a video analysis method, the method comprising: determining a target video that meets a first analysis triggering condition from at least one video to be analyzed, and detecting whether the target video already possesses video features; determining a corresponding condition determination strategy based on the detection result of the video features; if the condition determination result corresponding to the condition determination strategy meets a second analysis triggering condition, then performing video feature analysis on the target video to obtain the current video features of the target video.

[0128] According to one or more embodiments of this disclosure, [Example 2] provides a video analysis method, the method including the first analysis triggering condition being: the video to be analyzed is the first video received at present; or, the first attribute information of the video to be analyzed relative to the set attribute item has changed.

[0129] According to one or more embodiments of this disclosure, [Example 3] provides a video analysis method, which includes further optimizing the conditional judgment strategy determined based on the detection results of video features. Specifically, it includes: if the detection result of the video features is that there are currently no video features, then the video popularity prediction of the target video is determined as the conditional judgment strategy.

[0130] According to one or more embodiments of this disclosure, [Example 4] provides a video analysis method, which further optimizes the execution step of predicting the popularity of the target video. Specifically, it can be optimized as follows: obtaining second attribute information of the target video relative to a set popularity-related attribute item; inputting the second attribute information as input data into a given popularity prediction model, and using the output popularity prediction value as the video popularity prediction result;

[0131] The second analysis trigger condition is: the output popularity prediction value is greater than the set score threshold.

[0132] According to one or more embodiments of this disclosure, [Example 5] provides a video analysis method, which includes further optimization of determining a corresponding conditional judgment strategy based on the detection results of video features. Specifically, it can be optimized as follows: if the detection result of the video features indicates that video features are already present, then the target video will be identified by video attribute difference recognition as the conditional judgment strategy.

[0133] According to one or more embodiments of this disclosure, [Example Six] provides a video analysis method, which includes the following steps for performing video attribute difference recognition on a target video: obtaining third attribute information of the target video relative to a set difference recognition related attribute item; inputting the third attribute information as input data into a given attribute difference recognition model, and obtaining the output attribute difference recognition result;

[0134] The second analysis trigger condition is: the attribute difference identification result is that there is currently an attribute difference that causes changes in video features.

[0135] According to one or more embodiments of this disclosure, [Example Seven] provides a video analysis method, the method comprising: storing the current video features relative to the target video in a set video feature database.

[0136] According to one or more embodiments of this disclosure, [Example Eight] provides a video analysis apparatus, the apparatus comprising: a first determining module, configured to determine a target video satisfying a first analysis triggering condition from at least one video to be analyzed, and to detect whether the target video already possesses video features; a second determining module, configured to determine a corresponding condition determination strategy based on the detection result of the video features; and a feature analysis module, configured to perform video feature analysis on the target video to obtain the current video features of the target video if the condition determination result corresponding to the condition determination strategy satisfies the second analysis triggering condition.

[0137] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0138] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0139] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A video analysis method, characterized in that, include: From at least one video to be analyzed, identify a target video that meets the first analysis trigger condition, and detect whether the target video already has video features; The first analysis trigger condition is: the video to be analyzed is the first video received at this time; Alternatively, the first attribute information of the video to be analyzed changes; wherein the first attribute information includes: number of plays, video title, or video permission status information; The corresponding condition determination strategy is determined based on the detection results of video features; the condition determination strategy includes: predicting the popularity of the target video; or, identifying video attribute differences in the target video. If the condition determination result corresponding to the condition determination strategy meets the second analysis trigger condition, then video feature analysis is performed on the target video to obtain the current video features of the target video; the second analysis trigger condition is: the video popularity prediction value is greater than a set score threshold; or, the attribute difference identification result is that there are attribute differences that cause changes in video features.

2. The method according to claim 1, characterized in that, The step of determining the corresponding condition judgment strategy based on the detection results of video features includes: If the detection result of the video feature is that there is currently no video feature, then the prediction of the video popularity of the target video is determined as the conditional judgment strategy.

3. The method according to claim 2, characterized in that, The steps for performing video popularity prediction on the target video include: Obtain the second attribute information of the target video relative to the set popularity-related attribute items; The second attribute information is used as input data to the given popularity prediction model, and the popularity prediction value is output.

4. The method according to claim 1, characterized in that, The step of determining the corresponding condition judgment strategy based on the detection results of video features includes: If the detection result of the video features indicates that the video features are already present, then the video attribute difference identification of the target video is determined as the conditional judgment strategy.

5. The method according to claim 4, characterized in that, The steps for performing video attribute difference recognition on the target video include: Obtain the third attribute information of the target video relative to the set difference recognition related attribute items; The third attribute information is input as input data into a given attribute difference recognition model, and the output attribute difference recognition result is obtained.

6. The method according to any one of claims 1-5, characterized in that, Also includes: The current video features are stored relative to the target video in the established video feature database.

7. A video analysis device, characterized in that, include: The first determining module is used to determine a target video that meets the first analysis triggering condition from at least one video to be analyzed, and to detect whether the target video already has video features; The first analysis trigger condition is: the video to be analyzed is the first video received at this time; Alternatively, the first attribute information of the video to be analyzed changes; wherein the first attribute information includes: number of plays, video title, or video permission status information; The second determining module is used to determine the corresponding condition determination strategy based on the detection results of video features; the condition determination strategy includes: predicting the popularity of the target video; or, identifying video attribute differences in the target video. The feature analysis module is used to perform video feature analysis on the target video to obtain the current video features of the target video when the condition judgment result corresponding to the condition judgment strategy meets the second analysis trigger condition; the second analysis trigger condition is: the video popularity prediction value is greater than a set score threshold; or, the attribute difference identification result is that there is an attribute difference that causes the video feature to change.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the video analysis method as described in any one of claims 1-6.

9. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the video analysis method as described in any one of claims 1-6.

Images