A method, apparatus and electronic device for video data processing

Abstract

An embodiment of this specification discloses a method, apparatus, and electronic device for video data processing. The method for video data processing includes: receiving a target video to be published input by a user; obtaining risk factors belonging to multiple risk detection stages set for video publishing, where the risk detection times corresponding to different risk detection stages are different; sequentially using the risk factors of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video; and adjusting the publishing status of the target video based on the risk detection result.

Description

Technical Field

[0001] This document belongs to the technical field of data processing, and specifically relates to a method, device, and electronic device for video data processing. Background Art

[0002] User-generated content (UGC) refers to content originally created and uploaded to a network platform by Internet users. These contents are diverse in form, including but not limited to text, pictures, videos, audios, etc., and are created by users according to their own experiences, feelings, or creativity during the use of the Internet.

[0003] With the explosive growth of user-generated content, various short-video platforms are facing increasingly severe content risk challenges, including content compliance supervision (such as filtering of prohibited content), user security requirements (such as avoiding user privacy leakage), and user experience maintenance (such as the speed of risk detection), etc. To address these challenges, a unified standard is mostly adopted to conduct a detailed inspection of all uploaded videos to avoid the wide spread of content risks.

[0004] However, although this integrated detection method has comprehensive detection content, it consumes a huge amount of resources. Therefore, it is necessary to provide a better risk detection solution to improve the effect of reducing resource consumption in the risk detection process. Summary of the Invention

[0005] Embodiments of this specification provide a method, device, and electronic device for video data processing to provide a risk detection solution.

[0006] In a first aspect, embodiments of this specification provide a method for video data processing, the method including: receiving a target video to be published input by a user; obtaining risk elements belonging to multiple risk detection stages set for video publication, where the risk detection times corresponding to different risk detection stages are different; sequentially using the risk elements of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video; and adjusting the publication status of the target video based on the risk detection result.

[0007] Second aspect, an embodiment of this specification provides a video data processing device, including: a video receiving module, configured to receive a target video to be published input by a user; a feature obtaining module, configured to obtain risk features belonging to multiple risk detection stages set for video publishing, where the risk detection times corresponding to different risk detection stages are different; a risk detection module, configured to sequentially use the risk features of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video; and a status adjustment module, configured to adjust the publishing status of the target video based on the risk detection result.

[0008] Third aspect, an embodiment of this specification provides an electronic device, which includes: a processor, and a memory arranged to store computer-executable instructions, when the executable instructions are executed, enabling the processor to: receive a target video to be published input by a user; obtain risk features belonging to multiple risk detection stages set for video publishing, where the risk detection times corresponding to different risk detection stages are different; sequentially use the risk features of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video; and adjust the publishing status of the target video based on the risk detection result.

[0009] Fourth aspect, an embodiment of this specification provides a storage medium for storing a computer program, and the computer program can be executed by a processor to implement the following process: receive a target video to be published input by a user; obtain risk features belonging to multiple risk detection stages set for video publishing, where the risk detection times corresponding to different risk detection stages are different; sequentially use the risk features of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video; and adjust the publishing status of the target video based on the risk detection result.

[0010] Fifth aspect, an embodiment of this specification provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the following process: receive a target video to be published input by a user; obtain risk features belonging to multiple risk detection stages set for video publishing, where the risk detection times corresponding to different risk detection stages are different; sequentially use the risk features of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video; and adjust the publishing status of the target video based on the risk detection result. Description of the Drawings

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments described in one or more embodiments of this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0012] Figure 1 is a schematic flowchart of a method for video data processing provided by an embodiment of this specification;

[0013] Figure 2 is a schematic diagram of an application scenario of a method for video data processing provided by an embodiment of this specification;

[0014] Figure 3 is a schematic structural diagram of a risk detection system provided by an embodiment of this specification;

[0015] Figure 4 is a schematic structural diagram of a device for video data processing provided by an embodiment of this specification;

[0016] Figure 5 is a schematic structural diagram of an electronic device provided by an embodiment of this specification. Detailed implementation manners

[0017] The following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are some, but not all, of the embodiments of this specification. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this document.

[0018] The terms "first", "second", etc. in the specification and claims of this document are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this specification can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects. The character " / ", generally represents an "or" relationship between the associated objects before and after.

[0019] The following will, in conjunction with the accompanying drawings, describe in detail the method, device, and electronic device for video data processing provided by the embodiments of this specification through specific embodiments and their application scenarios.

[0020] Figure 1 A method for processing video data provided by an embodiment of the present invention can be executed by an electronic device, which may include: a server and / or a terminal device, where the terminal device may be, for example, an in-vehicle terminal or a mobile phone terminal, etc. In other words, this method can be executed by software or hardware installed in the aforementioned electronic device. The method for processing video data includes the following steps:

[0021] Step S102: Receive a target video to be published input by the user.

[0022] Among them, the target video can be a video source file (i.e., a user-generated video), or a video stream obtained after secondary processing (such as adding music, text, etc.) to the video source file; the target video can be a movie, a TV drama, etc. with a complete plot, a video generated after secondary processing of a movie or a TV drama, etc., or a video obtained by a simple combination of music and one or more pictures. In this specification, the type of the target video is not specifically limited and can be determined according to the actual situation.

[0023] The target video can be published on a video publishing platform. In this specification, the video publishing platform is not specifically limited and can be determined according to the actual situation. The user is a person using the video publishing platform. In this specification, the user who inputs the target video can be the source provider who uploads the video source file, or an individual or organization that performs secondary processing on the video source file after obtaining the permission of the source provider.

[0024] Step S104: Obtain risk factors belonging to multiple risk detection stages set for video publishing.

[0025] Among them, the risk factor is a factor with risk determined by the video publishing platform for video publishing. The risk factor can be promotion and drainage, illegal advertisement, sensitive content, copyright infringement, etc. In order to better avoid risk factors, it is necessary to reasonably divide and evaluate various risk factors, that is, to divide the risk factors into levels. The risk levels of risk factors in different risk levels are often different.

[0026] The risk urgency refers to the urgency of taking actions to deal with risk factors. Some risk factors require immediate measures to deal with, while some risk factors can be processed later. In one example, the risk factors can be divided into levels based on the urgency of the occurrence of the risk factors. For example, based on the risk urgency, the risk factors can be divided into three risk levels: low, medium, and high.

[0027] The risk impact degree is used to measure the potential loss degree of risk factors to an organization or an individual. Generally, the risk impact degree can be evaluated from aspects such as finance, security, reputation, etc. In an example, the risk factors can be classified based on the risk impact degree of the risk factors. For example, the risk factors can be classified into three risk levels: low, medium, and high based on the risk impact degree.

[0028] The risk likelihood refers to the possibility of a risk factor occurring. Usually, it can be determined by methods such as historical data, statistical analysis, and expert judgment. In an example, the risk factors can be classified based on the risk likelihood of the risk factors. For example, the risk factors can be classified into three risk levels: low, medium, and high based on the risk likelihood.

[0029] In addition to classifying the risk factors using the aforementioned risk urgency degree, risk impact degree, and risk likelihood, experts in the risk field can also be invited to score each risk factor. The scoring results can reflect the importance of each risk factor. Furthermore, based on the scoring results, the risk levels of the risk factors can be determined, and the three risk levels of low, medium, and high can be obtained as in the aforementioned three classification methods.

[0030] After obtaining the risk levels of different risk factors, the risk factors can be classified into at least two risk detection stages to achieve multi-stage detection of the target video. For example, the risk factors with a high risk level can be classified into the first risk detection stage, and the risk factors with medium and low risk levels can be classified into the second risk detection stage; or the risk factors with high and medium risk levels can be classified into the first risk detection stage, and the risk factors with a low risk level can be classified into the second risk detection stage; or the risk factors with a high risk level can be classified into the first risk detection stage, the risk factors with a medium risk level can be classified into the second risk detection stage, and the risk factors with a low risk level can be classified into the third risk detection stage. In this specification, there is no specific requirement for the method of determining the risk detection stage to which a risk factor belongs, and it can be determined according to the actual situation.

[0031] It should be noted that the detection times corresponding to different risk detection stages are different. The risk level of the risk factors included in the first risk detection stage is relatively high, and the detection time corresponding to the first risk detection stage can be when the user inputs the target video, while the risk level of the risk factors included in the second and / or third risk detection stages is relatively low, and the detection time corresponding to the second risk detection stage and / or the third risk detection stage can be some time after the user inputs the target video.

[0032] Step S106: Use the risk factors of different risk detection stages in sequence to perform risk detection on the target video, and obtain the risk detection result corresponding to the target video.

[0033] After obtaining risk factors belonging to multiple risk detection stages, the risk factors of each risk detection stage can be used in sequence to detect risks for the target video. Specifically, when the user uploads the target video, the risk factors of the first risk detection stage can be used to detect risks for the target video, and the first risk detection result corresponding to the first risk detection stage can be obtained; after the target inputs the target video for a period of time, the risk factors of the second risk detection stage and / or the third risk detection stage can be used to detect risks for the target video, and the second risk detection result corresponding to the second risk detection stage and / or the third risk detection result corresponding to the third risk detection stage can be obtained.

[0034] The risk detection result, the first risk detection result, the second risk detection result, etc. can all include two situations: there is a risk and there is no risk. Since the risk level of the risk factors included in the first risk detection stage is relatively high, when the first risk detection result is that there is a risk, the first risk detection result can be directly used as the risk detection result of the target video (that is, there is a risk); otherwise, when the first risk detection result is that there is no risk, the second risk detection result or the third risk detection result can be used as the risk detection result of the target video (that is, there is a risk or there is no risk).

[0035] Step S108: Adjust the release status of the target video based on the risk detection result.

[0036] Among them, the release status can include statuses such as on the shelf and / or off the shelf.

[0037] Specifically, when the risk detection result of the target video is that there is a risk, the release status of the target video can be adjusted to off the shelf; when the risk detection result of the target video is that there is no risk, the release status of the target video can be adjusted to on the shelf.

[0038] In the embodiments of this specification, after obtaining risk factors belonging to multiple risk detection stages, the risk factors are used to detect risks for the received target video to obtain a risk detection result, and the release status of the target video is adjusted according to this risk detection result. Since the risk detection times corresponding to different risk detection stages are different, this process realizes the staged detection of the target video through risk factors belonging to multiple risk detection stages. On the one hand, it reduces the over-detection of the target video when the target video is uploaded, greatly improving the resource utilization efficiency. On the other hand, it ensures the continuous detection of the target video with potential risks and ensures the effective management of the risks of the target video.

[0039] Figure 2 A schematic diagram of an application scenario of a video data processing method is provided, as Figure 2As shown, the user sends a service request for risk detection to the server through a terminal such as a mobile phone. The service request includes: for the target video provided by the user, performing a target task of risk detection for the target video. After receiving the service request, the server uses the video data processing method in this specification to determine the risk detection result and release status of the target video, and sends the risk detection result and release status to the terminal for the user's reference.

[0040] In one implementation, the risk detection phase includes a first risk detection phase and a second risk detection phase. Step S106 can be performed as the following steps A1 - A2:

[0041] Step A1, use multiple risk factors included in the first risk detection phase to perform a first risk detection on the target video, obtain a first risk detection result, and in the case where the first risk detection result indicates a risk, use the first risk detection result as the risk detection result;

[0042] Step A2, in the case where the first risk detection result indicates no risk, use multiple risk factors included in the second risk detection phase to perform a second risk detection on the target video, obtain a second risk detection result, and use the second risk detection result as the risk detection result.

[0043] Figure 3 A risk detection system is shown. As Figure 3 shown, the risk detection system includes two detection modules: a bottom - line risk detection module and a business risk detection module. The bottom - line risk detection module (corresponding to the first risk detection phase) is used to immediately block and report bottom - line risks (such as sensitive content, etc.). After the first phase is completed, only videos with a first risk detection result of no risk are put on the shelf, and the popularity (i.e., spread) of the videos on the shelf will be continuously monitored, and the risk detection and processing of the business risk detection module (corresponding to the second risk detection phase) will be triggered as needed. Among them, when performing risk detection in the first risk detection phase and the second detection phase, the data used can be one or more of the image frames, titles, comments, music, etc. of the uploaded video.

[0044] As mentioned above, the risk levels of the risk factors included in the first risk detection phase are usually relatively high (at this time, the first risk detection phase can be called the high - risk detection phase (Phase - I HRD)). Therefore, in the case where the first risk detection result indicates a risk, the first risk detection result can be directly used as the risk detection result, and at this time, the second risk detection phase can be avoided from being triggered.

[0045] Since the risk levels of the individual risk factors included in the first risk detection phase are all relatively high, in order to avoid the release of risk videos, in one implementation, step A1 can be performed as the following steps B1 - B2:

[0046] Step B1: Use multiple risk factors included in the first risk detection stage to perform the first risk detection on the target video, and obtain the first sub-risk detection results corresponding to each risk factor.

[0047] Step B2: When there is a first sub-risk detection result indicating the existence of risk, determine that the first risk detection result is the existence of risk.

[0048] Among them, the first sub-risk detection result is the risk detection result corresponding to the risk factor included in the first risk detection stage. Specifically, multiple risk factors included in the first risk detection stage can be used to perform the first risk detection on the target video simultaneously, and the first sub-risk detection results corresponding to each risk factor can be obtained.

[0049] Furthermore, among the obtained first sub-risk detection results, if there is one or more first sub-risk detection results indicating the existence of risk, then determine that the first risk detection result is the existence of risk.

[0050] In the above process, when there is a first sub-risk detection result indicating the existence of risk, determine that the first risk detection result is the existence of risk. This process can determine the first risk detection result as the existence of risk without multiple first sub-risk detection results indicating the existence of risk, improving the sensitive perception of the risk detection process for target videos with risks, effectively avoiding the release of risk videos, and improving the accuracy of risk detection.

[0051] In the case where the first risk detection result is the non-existence of risk, the second risk detection stage can be triggered. When the second risk detection result is obtained and the risk detection stage only includes the first risk detection stage and the second risk detection stage, regardless of whether the second risk detection result is the existence of risk or the non-existence of risk, the second risk detection result can be used as the risk detection result.

[0052] After the video is released, after a period of fermentation, some videos will attract the wide attention of platform users, while some videos will be generally ignored by platform users. If there is a risk in the videos that attract wide attention, a crisis will occur. In one implementation, step A2 can be executed as the following steps C1 - C3:

[0053] Step C1: When the first risk detection result is the non-existence of risk, obtain multiple dissemination metrics related to the dissemination degree.

[0054] Step C2: Obtain the dissemination data corresponding to the target video and the dissemination metrics, and use the dissemination metrics to evaluate the dissemination data to obtain the dissemination value of the target video.

[0055] Step C3: When the dissemination value exceeds a preset dissemination threshold, use multiple risk factors included in the second risk detection phase to perform a second risk detection on the target video to obtain a second risk detection result.

[0056] Among them, dissemination is an important indicator to measure the influence and popularity of a video, and the dissemination index is an index that constitutes the dissemination system. Specifically, the dissemination index can be one or more of indicators such as the number of views, the number of likes, the number of shares, the number of comments, and the viewing duration.

[0057] Specifically, after the risk detection in the first phase passes and the target video is put on the shelf, multiple dissemination indicators determined through expert evaluation or other means can be obtained. Then, the dissemination data corresponding to each dissemination indicator can be obtained from the platform, and based on this dissemination data, the current dissemination value of the target video can be obtained. When this dissemination value exceeds the preset dissemination threshold, the second risk detection phase is triggered, and the risk factors included in the second risk detection phase are used to perform a second risk detection on the target video.

[0058] In the above process, when the first risk detection result is that there is no risk, the dissemination indicator and the dissemination data corresponding to the dissemination indicator are obtained, and whether to enter the second risk detection phase is determined through the dissemination value corresponding to the dissemination data (at this time, the second risk detection phase can be called the high-risk detection phase (Phase-II TD-Triggered)). This process identifies the dissemination trend of the target video through the dissemination data, timely starts the second risk detection phase, realizes continuous monitoring of the target video, and reduces resource waste while strictly supervising the target video with potential risks.

[0059] Since each dissemination indicator will affect the dissemination, in order to accurately obtain the dissemination, each dissemination indicator can be used to comprehensively evaluate the dissemination. In one implementation, step C2 can be performed as steps D1 - D2 as follows:

[0060] Step D1: Evaluate the dissemination data to obtain the sub-dissemination value corresponding to the dissemination indicator to which the dissemination data belongs;

[0061] Step D2: Determine the dissemination value of the target video based on the sub-dissemination value corresponding to the dissemination indicator and the weight value.

[0062] Specifically, for each dissemination indicator related to the dissemination value, based on the gap between the dissemination data and the benchmark data, the dissemination data can be evaluated to obtain the sub-dissemination value, where the benchmark data is preset data used to distinguish whether a video has been widely disseminated.

[0063] Furthermore, different weight values can be assigned to each dissemination metric related to the dissemination value. Since the positioning and target user groups of different types of videos are different, the influence of the dissemination metrics of different types of videos on the dissemination value is also different. For example, food-related videos may pay more attention to user interaction, and the dissemination metric of the number of shares may have a greater impact on the dissemination value, while current affairs news videos may pay more attention to information dissemination, and the dissemination metric of the number of views may have a greater impact on the dissemination value. In one implementation, before determining the dissemination value of the target video based on the sub-dissemination value and weight value corresponding to the dissemination metric, the video data processing method further includes the following steps E1-E2:

[0064] Step E1, classifying the target video to obtain the classification result of the target video;

[0065] Step E2, based on the classification result, determining the weight value of each dissemination metric from the weight values of the dissemination metrics of multiple categories.

[0066] Specifically, according to the characteristics of each category of videos, the weight values corresponding to each dissemination metric can be determined in advance for each category of videos. Furthermore, when triggering the second risk detection stage for the target video, the target video can be classified to obtain the classification result of the target video. Furthermore, based on the classification result, the weight values corresponding to each dissemination metric of the target video can be determined from the preset weight values.

[0067] Next, the sub-dissemination values corresponding to different dissemination metrics can be fused through the weight values to obtain the dissemination value, and when the dissemination value exceeds the preset dissemination threshold, the second risk detection stage is triggered.

[0068] In the embodiments of this specification, using the first risk detection result and / or the dissemination value being detected as passed as the trigger condition for the second risk detection stage realizes conditional triggering of the second risk detection stage and effectively reduces resource waste.

[0069] In addition to triggering the second risk detection stage based on the dissemination value as described above, the second risk detection stage can also be triggered based on the data uploaded by the user. In one implementation, step A2 can be performed as the following steps F1-F3:

[0070] Step F1, when the first risk detection result is that there is no risk, obtaining the user feedback data of the target video;

[0071] Step F2, using the preset scoring metrics to score the user feedback data to obtain the feedback score;

[0072] Step F3: When the feedback score is greater than a preset feedback threshold, use multiple risk factors included in the second risk detection stage to perform a second risk detection on the target video to obtain a second risk detection result.

[0073] Among them, the user feedback data is the feedback data submitted by the viewing users of the target video. The user feedback data can be a hint of unreasonable information in the target video or a hint of illegal content in the target video. In this specification, the content of the user feedback data is not specifically limited and can be determined according to the actual situation.

[0074] The feedback score is a score representing the possibility that the target video has risks determined based on the user feedback data. A threshold (i.e., the preset feedback threshold) can be set in advance for the feedback score, and this threshold is used to trigger the second risk detection stage. Specifically, when the first risk detection result is that there is no risk, the user feedback data corresponding to the target video can be obtained, and the preset scoring index is used to score the user feedback data to obtain the feedback score. When the feedback score is greater than the preset feedback threshold, the second risk detection stage is triggered, that is, multiple risk factors included in the second risk detection stage are used to perform a second risk detection on the target video to obtain a second risk detection result.

[0075] As Figure 3 shown, the risk detection system can include a user feedback system for processing user feedback data to continuously optimize the detection algorithm through the user feedback data.

[0076] In the embodiments of this specification, when the first risk detection result is that there is no risk, it is determined whether to perform a second risk detection based on the feedback score corresponding to the user feedback data and the preset feedback threshold. This process triggers the second risk detection stage through the user feedback data, realizes the optimization of the supervision process of the target video, helps to improve the sensitivity of the risk detection process, and further can avoid the continuous spread of target videos with risks.

[0077] In addition to the foregoing method of determining the risk detection stage to which the risk factor belongs through various risk level classification methods, the risk detection stage to which the risk factor belongs can also be determined using a risk score. In one implementation, before obtaining risk factors belonging to multiple risk detection stages, the method for processing video data can further include the following steps G1 - G4:

[0078] Step G1: Obtain a risk evaluation criterion for judging the risk level of the risk factor, where the risk evaluation criterion includes one or more of the risk impact degree, risk possibility, and risk urgency;

[0079] Step G2: Use the risk evaluation criteria to evaluate the preset risk factors and obtain the first risk scores of the risk factors.

[0080] Step G3: Obtain the second risk scores of the preset risk factors from experts in the risk field, and fuse the first risk scores and the second risk scores of the preset risk factors to obtain the target risk scores of the risk factors.

[0081] Step G4: Based on the target risk scores of the risk factors, determine the risk detection stages to which the risk factors belong.

[0082] Among them, the target risk score is the comprehensive score of the risk factor. The level of the target risk score reflects the degree of importance of the risk factor.

[0083] Specifically, one or more of the risk impact degree, risk possibility, and risk urgency can be used as the risk evaluation criteria to evaluate multiple preset risk factors and obtain the first risk scores of the risk factors. At the same time, the opinions of experts in the risk field can also be adopted to obtain the second risk scores of multiple preset risk factors.

[0084] Next, the first risk scores and the second risk scores can be fused based on the preset weights to obtain the target risk scores. Furthermore, the risk detection stages to which the risk factors belong can be determined through the target risk scores. For example, when there are two risk detection stages, a threshold can be preset. The risk factors corresponding to the target risk scores greater than or equal to the threshold have a higher degree of importance and can be placed in the first risk detection stage. Conversely, the risk factors corresponding to the target risk scores less than the threshold have a lower degree of importance and can be placed in the second risk detection stage. The case of three risk detection stages can be deduced by analogy and will not be elaborated in this specification.

[0085] In the embodiments of this specification, the first risk scores corresponding to the risk evaluation criteria and the second risk scores corresponding to the experts in the risk field are fused, and the risk detection stages to which the risk factors belong are determined through the target risk scores obtained by the fusion. This process improves the accuracy of the risk detection stages to which the risk factors belong through the fusion of the first risk scores and the second risk scores, and thus helps to improve the rationality of the method for video data processing.

[0086] It can be understood that the above-mentioned various method embodiments mentioned in this specification can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, they will not be elaborated in this specification. Those skilled in the art can understand that in the above methods of the specific implementation manner, the specific execution order of each step should be determined according to its function and possible internal logic.

[0087] It should be noted that for the method for processing video data provided in the embodiments of this specification, the execution subject may be a device for processing video data, or a control module in the device for processing video data that executes the method for processing video data. In the embodiments of this specification, the method for processing video data executed by the device for processing video data is taken as an example to illustrate the device for processing video data provided in the embodiments of this specification.

[0088] Figure 4 It is a schematic structural diagram of a device for processing video data according to an embodiment of the present invention. As Figure 4 shown, the device 400 for processing video data includes:

[0089] A video receiving module 410, configured to receive a target video to be published input by a user;

[0090] An element obtaining module 420, configured to obtain risk elements belonging to multiple risk detection stages set for video publishing, where the risk detection times corresponding to different risk detection stages are different;

[0091] A risk detection module 430, configured to sequentially use the risk elements of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video;

[0092] A status adjustment module 440, configured to adjust the publishing status of the target video based on the risk detection result.

[0093] In one embodiment, the risk detection stage includes a first risk detection stage and a second risk detection stage. The risk detection module 430 includes:

[0094] A first detection unit, configured to use multiple risk elements included in the first risk detection stage to perform first risk detection on the target video to obtain a first risk detection result, and in the case where the first risk detection result indicates a risk, use the first risk detection result as the risk detection result;

[0095] A second detection unit, configured to, in the case where the first risk detection result indicates no risk, use multiple risk elements included in the second risk detection stage to perform second risk detection on the target video to obtain a second risk detection result, and use the second risk detection result as the risk detection result.

[0096] In one embodiment, using multiple risk elements included in the first risk detection stage to perform first risk detection on the target video to obtain a first risk detection result includes:

[0097] Respectively using multiple risk elements included in the first risk detection stage to perform first risk detection on the target video to obtain first sub-risk detection results corresponding to each risk element;

[0098] In the case where the first sub-risk detection result is a risk, determine that the first risk detection result is a risk.

[0099] In one embodiment, in the case where the first risk detection result is no risk, use multiple risk elements included in the second risk detection stage to perform a second risk detection on the target video to obtain a second risk detection result, including:

[0100] In the case where the first risk detection result is no risk, obtain multiple dissemination metrics related to the dissemination degree;

[0101] Obtain the dissemination data corresponding to the target video and the dissemination metric, and perform an evaluation process on the dissemination data to obtain the dissemination value of the target video;

[0102] In the case where the dissemination value exceeds a preset dissemination threshold, use multiple risk elements included in the second risk detection stage to perform a second risk detection on the target video to obtain a second risk detection result.

[0103] In one embodiment, performing an evaluation process on the dissemination data to obtain the dissemination value of the target video includes:

[0104] Perform an evaluation process on the dissemination data to obtain the sub-dissemination value corresponding to the dissemination metric to which the dissemination data belongs;

[0105] Determine the dissemination value of the target video according to the sub-dissemination value corresponding to the dissemination metric and the weight value.

[0106] In one embodiment, the video data processing apparatus 400 further includes:

[0107] A classification module, configured to perform a classification process on the target video to obtain a classification result of the target video before determining the dissemination value of the target video according to the sub-dissemination value corresponding to the dissemination metric and the weight value;

[0108] A weight value module, configured to determine the weight value of each dissemination metric from the weight values of the dissemination metrics of multiple categories based on the classification result.

[0109] In one embodiment, in the case where the first risk detection result is no risk, use multiple risk elements included in the second risk detection stage to perform a second risk detection on the target video to obtain a second risk detection result, including:

[0110] In the case where the first risk detection result is no risk, obtain the user feedback data of the target video;

[0111] Use a preset scoring metric to score the user feedback data to obtain a feedback score;

[0112] When the feedback score is greater than a preset feedback threshold, multiple risk factors included in the second risk detection stage are used to perform a second risk detection on the target video, and a second risk detection result is obtained.

[0113] In one embodiment, the video data processing device 400 further includes:

[0114] An evaluation criterion module, configured to obtain a risk evaluation criterion for determining the risk level of risk factors before obtaining risk factors belonging to multiple risk detection stages, where the risk evaluation criterion includes one or more of a risk impact degree, a risk possibility, and a risk urgency;

[0115] A first risk score module, configured to use the risk evaluation criterion to perform an evaluation process on preset risk factors to obtain a first risk score of the risk factors;

[0116] A second risk score module, configured to obtain a second risk score of preset risk factors from experts in the risk field, and fuse the first risk score and the second risk score of the preset risk factors to obtain a target risk score of the risk factors;

[0117] A detection stage determination module, configured to determine the risk detection stage to which the risk factors belong based on the target risk score of the risk factors.

[0118] It should be noted that the embodiments of the video data processing device in this specification and the embodiments of the video data processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the corresponding implementation of the foregoing video data processing method, and the repeated parts will not be elaborated.

[0119] Each module in the above video data processing device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the terminal device or the processor in the server in the form of hardware or be independent of it, or can be stored in the memory in the terminal device or the memory in the server in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0120] Furthermore, corresponding to the above-described video data processing method, based on the same technical concept, one or more embodiments of this specification further provide an electronic device, which is used to execute the above video data processing method, Figure 5 which is a schematic structural diagram of an electronic device provided by one or more embodiments of this specification.

[0121] Based on the same idea, one or more embodiments of this specification further provide an electronic device, such as Figure 5As shown. Electronic devices can vary significantly due to differences in configuration or performance, and may include one or more processors 501 and a memory 502. One or more application programs or data may be stored in the memory 502. Among them, the memory 502 can be short-term storage or persistent storage. The application programs stored in the memory 502 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the electronic device. Further, the processor 501 can be set to communicate with the memory 502 and execute a series of computer-executable instructions in the memory 502 on the electronic device. The electronic device may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input / output interfaces 505, and one or more keyboards 506.

[0122] In a specific embodiment, the electronic device includes a memory and one or more programs. One or more of the programs are stored in the memory, and one or more of the programs may include one or more modules. Each module may include a series of computer-executable instructions in the electronic device and is configured to be executed by one or more processors. The one or more programs include the following computer-executable instructions for:

[0123] Receive the target video to be published input by the user;

[0124] Obtain risk factors belonging to multiple risk detection stages set for video publication. The risk detection times corresponding to different risk detection stages are different;

[0125] Successively use the risk factors of different risk detection stages to perform risk detection on the target video to obtain the risk detection result corresponding to the target video;

[0126] Adjust the publication status of the target video based on the risk detection result.

[0127] It should be noted that the embodiments of the electronic device in this specification and the embodiments of the method for video data processing in this specification are based on the same inventive concept. Therefore, for the specific implementation of this embodiment, reference can be made to the corresponding implementation of the method for video data processing described above, and repeated parts will not be elaborated.

[0128] Further, corresponding to the method for video data processing described above, based on the same technical concept, one or more embodiments of this specification also provide a storage medium for storing computer-executable instructions. In a specific embodiment, the storage medium can be a USB flash drive, an optical disc, a hard disk, etc. When the computer-executable instructions stored in the storage medium are executed by a processor, the following process can be implemented:

[0129] Receive a target video to be published input by a user;

[0130] Obtain risk factors belonging to multiple risk detection stages set for video publication, where the risk detection times corresponding to different risk detection stages are different;

[0131] Successively use the risk factors of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video;

[0132] Adjust the publication status of the target video based on the risk detection result.

[0133] It should be noted that the embodiments of the storage medium in this specification and the method for video data processing in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding method for video data processing described above, and the repeated parts will not be elaborated.

[0134] Furthermore, corresponding to the method for video data processing described above, based on the same technical concept, one or more embodiments of this specification also provide a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, it can implement the following process:

[0135] Receive a target video to be published input by a user;

[0136] Obtain risk factors belonging to multiple risk detection stages set for video publication, where the risk detection times corresponding to different risk detection stages are different;

[0137] Successively use the risk factors of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video;

[0138] Adjust the publication status of the target video based on the risk detection result.

[0139] It should be noted that the embodiments of the computer program product in this specification and the embodiments of the method for video data processing in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding method for video data processing described above, and the repeated parts will not be elaborated.

[0140] The above description has been made of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0141] In the 1990s, it was obvious to distinguish whether an improvement in a technology was an improvement in hardware (e.g., improvement in circuit structures such as diodes, transistors, switches, etc.) or an improvement in software (improvement in method flows). However, with the development of technology, many improvements in method flows today can be regarded as direct improvements in hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structures by programming the improved method flows into the hardware circuits. Therefore, it cannot be said that an improvement in a method flow cannot be implemented with a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logical function is determined by the user programming the device. The designer can program by himself to "integrate" a digital system on a PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow with the above-mentioned several hardware description languages and programming it into the integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0142] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0143] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0144] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0145] Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0146] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows 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 the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0147] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0149] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0150] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0151] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0152] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0153] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0154] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0155] The above are only examples of this document and are not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this document shall be included within the scope of the claims of this document.

Claims

1. A method for video data processing, comprising: Receiving a target video to be published input by a user; Obtaining risk factors belonging to multiple risk detection stages set for video publication, where the risk detection times corresponding to different risk detection stages are different. The risk factors are risk factors determined by a video publication platform for video publication that have risks. The risk factors include promotion and drainage, illegal advertisements, sensitive content, and copyright infringement. The multiple risk detection stages are divided according to different risk levels corresponding to the risk factors. The different risk levels corresponding to the risk factors are determined by one or more of risk urgency, risk impact degree, risk possibility, and the importance degree of risk factors based on expert scoring; Successively using the risk factors of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video; Adjusting the publication status of the target video based on the risk detection result.

2. The method according to claim 1, wherein the risk detection stage includes a first risk detection stage and a second risk detection stage. The successively using the risk factors of different risk detection stages to perform risk detection on the target video to obtain a risk detection result corresponding to the target video includes: Using multiple risk factors included in the first risk detection stage to perform a first risk detection on the target video to obtain a first risk detection result, and in the case where the first risk detection result indicates the existence of a risk, using the first risk detection result as the risk detection result; In the case where the first risk detection result indicates the non-existence of a risk, using multiple risk factors included in the second risk detection stage to perform a second risk detection on the target video to obtain a second risk detection result, and using the second risk detection result as the risk detection result.

3. The method according to claim 2, wherein the using multiple risk factors included in the first risk detection stage to perform a first risk detection on the target video to obtain a first risk detection result includes: Respectively using multiple risk factors included in the first risk detection stage to perform a first risk detection on the target video to obtain first sub-risk detection results corresponding to each of the risk factors; In the case where there is a first sub-risk detection result indicating the existence of a risk, determining that the first risk detection result indicates the existence of a risk.

4. The method according to claim 2, wherein the in the case where the first risk detection result indicates the non-existence of a risk, using multiple risk factors included in the second risk detection stage to perform a second risk detection on the target video to obtain a second risk detection result includes: In the case where the first risk detection result indicates the non-existence of a risk, obtaining multiple dissemination indicators related to dissemination; Obtaining dissemination data corresponding to the target video and the dissemination indicators, and performing an evaluation process on the dissemination data to obtain a dissemination value of the target video; When the popularity value exceeds a preset popularity threshold, use multiple risk factors included in the second risk detection stage to perform a second risk detection on the target video to obtain the second risk detection result.

5. The method according to claim 4, wherein the evaluating the dissemination data to obtain the popularity value of the target video comprises: Evaluating the dissemination data to obtain a sub-popularity value corresponding to the dissemination index to which the dissemination data belongs; Determine the popularity value of the target video according to the sub-popularity value corresponding to the dissemination index and the weight value.

6. The method according to claim 5, before determining the popularity value of the target video according to the sub-popularity value corresponding to the dissemination index and the weight value, the method further comprises: Classifying the target video to obtain a classification result of the target video; Based on the classification result, determine the weight value of each dissemination index from the weight values of the dissemination indexes of multiple categories.

7. The method according to claim 2, wherein when the first risk detection result is that there is no risk, using multiple risk factors included in the second risk detection stage to perform a second risk detection on the target video to obtain a second risk detection result, comprising: When the first risk detection result is that there is no risk, obtain the user feedback data of the target video; Use a preset scoring index to score the user feedback data to obtain a feedback score; When the feedback score is greater than a preset feedback threshold, use multiple risk factors included in the second risk detection stage to perform a second risk detection on the target video to obtain the second risk detection result.

8. The method according to claim 1, before obtaining risk factors belonging to multiple risk detection stages, the method further comprises: Obtain a risk evaluation criterion for judging the risk level of risk factors, the risk evaluation criterion including one or more of risk impact degree, risk possibility and risk urgency; Use the risk evaluation criterion to evaluate the preset risk factors to obtain the first risk score of the risk factors; Obtain the second risk score of the preset risk factors by an expert in the risk field, and fuse the first risk score and the second risk score of the preset risk factors to obtain the target risk score of the risk factors; Based on the target risk score of the risk factors, determine the risk detection stage to which the risk factors belong.

9. A video data processing device, comprising: A video receiving module for receiving a target video to be published input by a user; An element acquisition module, configured to acquire risk elements belonging to multiple risk detection stages set for video publishing. The risk detection times corresponding to different risk detection stages are different. The risk elements are elements determined by the video publishing platform to be risky for video publishing. The risk elements include promotion and drainage, illegal advertisements, sensitive content, and copyright infringement. The multiple risk detection stages are divided according to different risk levels corresponding to the risk elements. The different risk levels corresponding to the risk elements are determined by one or more of risk urgency, risk impact degree, risk possibility, and the importance degree of risk elements based on expert scoring; A risk detection module, configured to sequentially use the risk elements of different risk detection stages to perform risk detection on the target video, and obtain a risk detection result corresponding to the target video; A status adjustment module, configured to adjust the publishing status of the target video based on the risk detection result.

10. An electronic device, comprising: A processor, and A memory arranged to store computer-executable instructions, which when executed, can cause the processor to: Receive a target video to be published input by a user; Acquire risk elements belonging to multiple risk detection stages set for video publishing. The risk detection times corresponding to different risk detection stages are different. The risk elements are elements determined by the video publishing platform to be risky for video publishing. The risk elements include promotion and drainage, illegal advertisements, sensitive content, and copyright infringement. The multiple risk detection stages are divided according to different risk levels corresponding to the risk elements. The different risk levels corresponding to the risk elements are determined by one or more of risk urgency, risk impact degree, risk possibility, and the importance degree of risk elements based on expert scoring; Sequentially use the risk elements of different risk detection stages to perform risk detection on the target video, and obtain a risk detection result corresponding to the target video; Adjust the publishing status of the target video based on the risk detection result.

Images