Video Push Method, Device, and Storage Medium

Abstract

The present disclosure relates to a method, apparatus, and storage medium for pushing videos, and pertains to the field of multimedia technology. The method for pushing videos includes obtaining one or more videos including a video with a photosensitive label and a video without a photosensitive label, where each video has a photosensitive label when determined to be a photosensitive video by a photosensitive video identification model, and pushing, to a browsing user, a video without a photosensitive label among the one or more videos when the browsing user is in a state of filtering photosensitive videos.

Description

Technical Field

[0001] [Cross - reference to Related Applications] This application is based on an application with a Chinese application number of 202210769349.6 and a filing date of July 1, 2022, claims its priority, and all of the disclosure content of the Chinese application is incorporated into this application.

[0002] [Technical Field] The present disclosure relates to the field of multimedia technology, and particularly relates to a method, device, and storage medium for pushing videos.

Background Art

[0003] Photosensitive epilepsy is a disease that causes seizures by visual stimuli such as strong light stimuli and flash stimuli. Currently, some game and animation production companies, when producing scenes with strong visual stimuli, use means such as reducing contrast to minimize the possibility of inducing seizures in photosensitive epilepsy, and usually clearly mark a photosensitive epilepsy warning at the beginning of the work.

[0004] With the popularization of the Internet, terminals, and multimedia technology, video creators are no longer limited to professional media companies. Ordinary users can also shoot videos by themselves, post them on the network, and let other users watch them. Some video - based applications predict videos that browsing users may be interested in and push them to the browsing users. Because video production and posting are simple, many video creators have emerged. Currently, some video creators do not have a deep understanding of photosensitive epilepsy.

Summary of the Invention

[0005] According to a first aspect of some embodiments of the present disclosure, there is provided a method for pushing videos, including obtaining one or more videos including a video with a photosensitive label and a video without a photosensitive label, where each video has a photosensitive label when determined to be a photosensitive video by a photosensitive video identification model, and pushing a video without a photosensitive label among the one or more videos to a browsing user when the browsing user is in a state of filtering photosensitive videos.

[0006] In some embodiments, the pushing method further includes obtaining feedback from the browsing user on the viewed videos, and when the feedback indicates that the viewed video is a photosensitive video, marking the viewed video as a photosensitive video and adding it to a training set for training the photosensitive video identification model.

[0007] In some embodiments, each video has a photosensitive label when a photosensitive effect is added.

[0008] In some embodiments, the pushing method further includes pushing one or more videos to the browsing user when the browsing user is not in a state of filtering photosensitive videos.

[0009] In some embodiments, the pushing method further includes displaying a selection control for whether to filter a photosensitive video when the video to be played is a video with a photosensitive label, receiving an operation by the browsing user on the selection control, and setting the browsing user to a state of filtering photosensitive videos when the operation indicates filtering the photosensitive video.

[0010] In some embodiments, when the video to be played is a video with a photosensitive label that the browsing user views for the first time with the same account or on the same terminal, a selection control for whether to filter the photosensitive video is displayed.

[0011] In some embodiments, the selection control is located on a mask layer, and the mask layer is located on top of the video to be played.

[0012] According to a second aspect of some embodiments of the present invention, there is provided a method for pushing a video, including obtaining a video uploaded by a creator, processing the uploaded video using a photosensitive video identification model to determine whether the uploaded video is a photosensitive video, adding a photosensitive label to the uploaded video if the uploaded video is a photosensitive video, and pushing videos without a photosensitive label to a browsing user if the browsing user is in a state of filtering photosensitive videos.

[0013] In some embodiments, the pushing method further includes sending a notification to the creator when it is determined that the uploaded video is a photosensitive video.

[0014] In some embodiments, after sending a notification to the creator, the pushing method further includes receiving feedback sent by the creator, and if the feedback indicates that the uploaded video is not a photosensitive video, marking the uploaded video as a non - photosensitive video and adding it to a training set for training the photosensitive video identification model.

[0015] In some embodiments, the photosensitive video identification model is a neural network model.

[0016] According to a third aspect of some embodiments of the present disclosure, there is provided a video pushing device including a memory and a processor coupled to the memory and configured to execute the video pushing method according to any one of the foregoing based on instructions stored in the memory.

[0017] According to a fourth aspect of some embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements any one of the foregoing video pushing methods.

[0018] According to a fifth aspect of some embodiments of the present invention, there is provided a computer program product which, when running on a computer, causes the computer to implement any one of the foregoing video pushing methods.

[0019] According to a sixth aspect of some embodiments of the present invention, there is provided a computer program which, when executed by a processor, includes instructions for causing the processor to execute any one of the foregoing video pushing methods.

[0020] Other features and advantages of the present disclosure will become apparent from the detailed description of exemplary embodiments of the present disclosure based on the following drawings.

Brief Description of the Drawings

[0021] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following briefly describes the drawings required for the description of the embodiments or the prior art. Needless to say, the drawings in the following description are only some embodiments of the present disclosure, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0022] Hereinafter, with reference to the drawings of the embodiments of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described. However, it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of them. The description of at least one exemplary embodiment below is actually only an illustration and should never be construed as any limitation on the present disclosure and its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of the present disclosure without any special creativity belong to the protection scope of the present disclosure.

[0023] Unless otherwise specified, the relative arrangements, mathematical formulas, and numerical values of the members and steps described in these embodiments do not limit the scope of the present disclosure.

[0024] At the same time, for the convenience of description, it should be understood that the dimensions of each part shown in the drawings are not drawn in actual proportional relationships.

[0025] Although the technologies, methods, and devices known to those skilled in the art may not be described in detail, when appropriate, the above technologies, methods, and devices should be regarded as part of the specification.

[0026] In all the examples shown and described herein, any specific values are not limiting and should be construed as illustrative only. Therefore, other examples of the exemplary embodiments may have different values.

[0027] It should be noted that similar reference numerals and letters refer to similar items in the following drawings. Therefore, once an item is defined in one drawing, there is no need to further explain it in subsequent drawings.

[0028] Some video creators have little understanding of photosensitive epilepsy and are likely to post videos that are likely to trigger seizures of photosensitive epilepsy. Pushing such videos to users sensitive to photosensitive videos is likely to cause discomfort to such users and may even induce the onset of the disease in users.

[0029] One of the technical problems to be solved by the present disclosure is how to reduce the impact on users sensitive to photosensitive videos and improve the security during video viewing in video pushing.

[0030] FIG. 1 shows a flowchart of a video pushing method according to some embodiments of the present disclosure. The embodiment may be deployed on a server of a video pushing application. Optionally, it may be deployed on other devices, and the present disclosure will not explain this further.

[0031] As shown in FIG. 1, the video pushing method of the embodiment includes steps S102 to S108.

[0032] In step S102, a video uploaded by a creator is acquired.

[0033] For example, the creator uploads a video stored in the creator's terminal or stored on the network via the upload interface provided by the video push application. The video may be one shot by the creator or generated by editing video materials, etc., and the present disclosure is not limited thereto.

[0034] In step S104, the uploaded video is processed using the photosensitive video identification model to determine whether the uploaded video is a photosensitive video.

[0035] In some embodiments, the photosensitive video identification model is a neural network model. For example, the uploaded video is input into a pre-trained photosensitive video identification model to obtain a prediction probability calculated by the photosensitive video identification model, and the prediction probability may indicate the probability that the uploaded video is a photosensitive video or the probability that it is not a photosensitive video. By comparing the prediction probability with a predetermined threshold, a determination result as to whether the uploaded video is a photosensitive video can be obtained.

[0036] In step S106, if the uploaded video is a photosensitive video, a photosensitive label is added to the uploaded video.

[0037] The photosensitive label is stored, for example, in the metadata or attribute information of the video. Also, the correspondence between the label of the video and the photosensitive label may be stored in a data table or key-value pair.

[0038] In some embodiments, a field that indicates photosensitivity is newly added to the information corresponding to the video, and different field values indicate whether the corresponding video has a photosensitivity label. For example, a new field "photosensitive" is added. When photosensitive = 1, it indicates that the video has a photosensitivity label; when photosensitive = 0 or photosensitive = NULL (empty), it indicates that the video does not have a photosensitivity label.

[0039] In some embodiments, the video push application provides several preset effects to the creator. After uploading the video, the creator can add these effects to make the video have a richer visual effect. Among these effects, the photosensitivity effect may be pre-marked. When a photosensitivity effect is added to an uploaded video, a photosensitivity label may be added to it. Thus, even if the uploaded video itself does not belong to the photosensitive videos, but after uploading, a photosensitivity effect is added, when the posted video becomes a photosensitive video, it can be accurately marked.

[0040] In some embodiments, when it is determined that the uploaded video is a photosensitive video, a notification is sent to the creator. Thereby, the creator can know that the uploaded video is a photosensitive video. The notification may be sent, for example, by the station email of the video push application, or may be sent through a route other than the video push application, such as mobile email or email, based on the communication information left by the creator. The notification may further include knowledge about photosensitive videos and photosensitive epilepsy in addition to the identification result for the video. Thereby, more creators can pay attention to avoiding related visual effects in subsequent video creation. Thereby, the overall security of video viewing is improved.

[0041] In step S108, when the browsing user is in a state of filtering photosensitive videos, videos without photosensitive labels are pushed to the browsing user.

[0042] The browsing user may set whether to filter photosensitive videos as needed. When the browsing user is in a state of filtering photosensitive videos, the user will not view videos with photosensitive labels.

[0043] It should be noted that the creator and the browsing user in the present disclosure are only identities for a certain video. In an actual application scenario, a certain user may be the creator of a certain video or the browsing user of other videos.

[0044] In some embodiments, the pushed videos are located in a video stream, and the video stream may be a long-time video stream or a shot video stream. The user can view different videos pushed to themselves through a switching operation.

[0045] Hereinafter, with reference to FIG. 2, an embodiment of a video pushing method will be described from the perspective of a browsing user.

[0046] FIG. 2 shows a flowchart of a video pushing method according to some other embodiments of the present invention. This embodiment may be deployed on the server of a video pushing application. As needed, it may also be deployed on other devices, and the present disclosure will not explain this further.

[0047] As shown in FIG. 2, the video pushing method of this embodiment includes steps S202 to S204.

[0048] In step S202, one or more videos including videos with photosensitive labels and videos without photosensitive labels are obtained. Each video has a photosensitive label if it is determined to be a photosensitive video by a photosensitive video identification model.

[0049] One or more videos to be obtained are scheduled to be pushed to the user. For example, based on a recommendation algorithm, the server calculates videos that the user may be interested in and plans to push these videos to the user. Before performing the push operation, according to the identification result of the photosensitive video identification model, the photosensitive videos may be marked. Thereby, it helps the server to further determine whether to push all of these videos to the user.

[0050] In step S204, when the browsing user is in a state of filtering photosensitive videos, videos without photosensitive labels among one or more videos are pushed to the browsing user.

[0051] In some embodiments, when the browsing user is not in a state of filtering photosensitive videos, one or more videos are pushed to the browsing user. That is, the browsing user can watch videos with photosensitive labels and can also watch videos without photosensitive labels.

[0052] In the above embodiments, the uploaded videos are identified by the photosensitive video identification model, and when a video is determined by the model to be a photosensitive video, a photosensitive label is added to the video. Thereby, when the browsing user selects to filter photosensitive videos, by pushing videos without photosensitive labels to the browsing user, the adverse effects on users sensitive to photosensitive videos, such as photosensitive epilepsy patients caused by photosensitive videos, are avoided as much as possible, and the security of video viewing is improved.

[0053] Hereinafter, taking the case where the photosensitive video identification model is a neural network model as an example, the model training process will be exemplarily described.

[0054] First, construct a training set, which includes marked photosensitive videos and marked non-photosensitive videos. These marks are, for example, manually screened and marked. Then, input the videos in the training set into a neural network model to obtain the prediction results of the model. Finally, calculate the loss value of the model from the deviation between the prediction result of the model and the mark, and adjust the parameters of the model based on the loss value. Repeat multiple times. After the convergence condition is satisfied, stop the training to obtain a photosensitive video recognition model.

[0055] Some embodiments of the present disclosure further provide a user feedback mechanism, and through the user's feedback, the training set can be expanded to further improve the accuracy of the model. Hereinafter, with reference to FIGS. 3 and 4 respectively, embodiments of training the model through user feedback will be described.

[0056] FIG. 3 shows a flowchart of a browsing user feedback method according to some embodiments of the present invention. As shown in FIG. 3, the browsing user feedback method of this embodiment includes steps S302 to S306.

[0057] In step S302, push videos without a photosensitive label to a browsing user who has set the state of filtering photosensitive videos.

[0058] In step S304, obtain the feedback from the browsing user on the viewed videos.

[0059] After the browsing user sets the state of filtering photosensitive videos, if a photosensitive video is still pushed during browsing, the user may submit feedback to indicate that the viewed video is a photosensitive video.

[0060] A feedback control may be provided for the video push application. After the browsing user triggers the feedback control, the user may select a type of feedback that indicates that a pre-set photosensitive video has been viewed, or may manually input the feedback content.

[0061] In step S306, if the feedback indicates that the viewed video is a photosensitive video, mark the viewed video as a photosensitive video and add it to the training set for training the photosensitive video identification model.

[0062] In some embodiments, after receiving the feedback from the browsing user, the feedback information may be further reviewed, and after passing the review, the corresponding video may be added to the training set. The review may be completed manually or automatically according to a predetermined review rule or review algorithm.

[0063] Thereby, based on the feedback from the browsing user, the photosensitive videos that the model could not identify can be marked and added to the training set. Thereby, it can contribute to further improving the accuracy of the model.

[0064] Figure 4 shows a flowchart of the author feedback method according to some embodiments of the present invention. As shown in Figure 4, the browsing user feedback method of this embodiment includes steps S402 to S410.

[0065] In step S402, the photosensitive video identification model is used to process the video uploaded by the author to determine whether the uploaded video is a photosensitive video.

[0066] In step S404, if the uploaded video is a photosensitive video, add a photosensitive label to the uploaded video.

[0067] In step S406, if it is determined that the uploaded video is a photosensitive video, a notification is sent to the creator.

[0068] In step S408, after sending the notification to the creator, feedback sent by the creator is received. For example, if the creator thinks that the uploaded video is not a photosensitive video, they may appeal through the feedback.

[0069] In step S410, if the feedback indicates that the uploaded video is not a photosensitive video, the uploaded video is marked as a non - photosensitive video and added to the training set for training the photosensitive video identification model.

[0070] In some embodiments, after receiving the creator's feedback, the feedback information may be further reviewed. After passing the review, the corresponding video may be added to the training set. The review may be completed manually or automatically according to predetermined review rules or review algorithms.

[0071] Thereby, due to the creator's feedback, non - photosensitive videos mis - identified by the model can be marked and added to the training set, which can contribute to further improving the accuracy of the model.

[0072] The above two feedback mechanisms can utilize the user's feedback to obtain the mis - identification situation of the model, collect more training data, and further optimize the model, thereby improving the prediction accuracy of the model. The security during the user's video viewing is also better guaranteed.

[0073] Hereinafter, with reference to FIG. 5, an embodiment of the user state setting method of the present invention will be described.

[0074] FIG. 5 shows a flowchart of a user state setting method according to some embodiments of the present invention. As shown in FIG. 5, the user state setting method of this embodiment includes steps S502 to S506.

[0075] In step S502, when the video to be played is a video with a photosensitive label, a selection control for whether to filter the photosensitive video is displayed.

[0076] For example, a video push application acquires some videos, pushes them to the user for playback in sequence, and before playing each video, checks whether the video to be played has a photosensitive label. If it does not have a photosensitive label, it is played normally. If it has a photosensitive label, a selection control is displayed.

[0077] In some embodiments, in order to prevent the user from frequently making the same settings, the selection control is displayed only when it is the user's "first viewing". "First viewing" refers to the first viewing with the same account or the first viewing on the same terminal. That is, when the video to be played is a video with a photosensitive label that the viewing user views for the first time with the same account or on the same terminal, a selection control for whether to filter the photosensitive video is displayed.

[0078] In some embodiments, the selection control is located on a mask layer, and the mask layer is located on the upper layer of the video to be played. The transparency of the mask layer is lower than a predetermined value or has an effect of blurring the background. Thereby, the underlying photosensitive video is masked to concentrate the user's attention on the selection control.

[0079] In step S504, an operation on the selection control by the viewing user is received.

[0080] In step S506, when the operation indicates filtering the photosensitive video, the viewing user is set to a state of filtering the photosensitive video.

[0081] According to the above embodiments, a user can set whether to filter photosensitive videos according to needs, thereby not only improving the viewing security of users sensitive to photosensitive videos, but also enhancing the viewing freedom of users not sensitive to photosensitive videos. Moreover, since many browsing users are also video creators, the setting process also serves to popularize knowledge about photosensitive videos.

[0082] Hereinafter, with reference to FIG. 6, an embodiment of the video push device of the present invention will be described.

[0083] FIG. 6 shows a schematic configuration diagram of a video push device according to some embodiments of the present invention. As shown in FIG. 6, the video push device 60 of this embodiment is an acquisition module configured to acquire one or more videos including videos with photosensitive labels and videos without photosensitive labels. Each video, when determined to be a photosensitive video by a photosensitive video identification model, has an acquisition module 610 with a photosensitive label, and a push module 620 configured to push a video without a photosensitive label among one or more videos to a browsing user when the browsing user is in a state of filtering photosensitive videos.

[0084] In the above embodiment, the uploaded video is identified by a photosensitive video identification model. When the video is determined to be a photosensitive video by the model, a photosensitive label is added to the video. Thereby, when a browsing user selects to filter photosensitive videos, by pushing videos without photosensitive labels to the browsing user, the adverse effects on users sensitive to photosensitive videos, such as photosensitive epilepsy patients caused by photosensitive videos, can be avoided as much as possible, and the security of video viewing can be improved.

[0085] In some embodiments, the push device 60 further includes a feedback module 630 configured to obtain feedback from a browsing user regarding a viewed video and, if the feedback indicates that the viewed video is a photosensitive video, mark the viewed video as a photosensitive video and add it to a training set for training a photosensitive video identification model.

[0086] In some embodiments, each video has a photosensitive label if a photosensitive effect is added.

[0087] In some embodiments, the push module 620 is further configured to push one or more videos to the browsing user if the browsing user is not in a state of filtering photosensitive videos.

[0088] In some embodiments, the push device 60 further includes a setting module 640 configured to display a selection control for whether to filter a photosensitive video if the video to be played is a video with a photosensitive label, receive an operation on the selection control by the browsing user, and set the browsing user to a state of filtering the photosensitive video if the operation indicates filtering the photosensitive video.

[0089] In some embodiments, the setting module 640 is further configured to display a selection control for whether to filter a photosensitive video if the video to be played is a video with a photosensitive label that the browsing user views for the first time on the same account or on the same terminal.

[0090] In some embodiments, the selection control is located on a mask layer, and the mask layer is located on an upper layer of the video to be played.

[0091] Hereinafter, with reference to FIG. 7, an embodiment of the video push device of the present invention will be described.

[0092] FIG. 7 shows a schematic configuration diagram of a video push device according to some other embodiments of the present invention. As shown in FIG. 7, the video push device 70 of this embodiment includes an upload module 710 configured to obtain a video uploaded by a creator, an identification module 720 configured to process the uploaded video using a photosensitive video identification model to determine whether the uploaded video is a photosensitive video, an addition module 730 configured to add a photosensitive label to the uploaded video if the uploaded video is a photosensitive video, and a push module 740 configured to push videos without a photosensitive label to a browsing user when the browsing user is in a state of filtering photosensitive videos.

[0093] In the above embodiment, the uploaded video is identified by the photosensitive video identification model, and if the video is determined by the model to be a photosensitive video, a photosensitive label is added to the video. Thereby, when the browsing user selects to filter photosensitive videos, by pushing videos without a photosensitive label to the browsing user, the adverse effects on users sensitive to photosensitive videos, such as photosensitive epilepsy patients caused by photosensitive videos, are avoided as much as possible, and the security of video viewing is improved.

[0094] In some embodiments, the push device 70 further includes a notification module 750 configured to send a notification to the creator when it is determined that the uploaded video is a photosensitive video.

[0095] In some embodiments, after sending a notification to the creator, the push device 70 receives feedback sent by the creator, and if the feedback indicates that the uploaded video is not a photosensitive video, the uploaded video is marked as a non-photosensitive video and further includes a feedback module 760 configured to add it to a training set for training the photosensitive video identification model.

[0096] In some embodiments, the photosensitive video identification model is a neural network model.

[0097] If necessary, the push device 60 and the push device 70 may be provided together in the same device, or may be provided in different devices respectively. The present disclosure will not describe this any further.

[0098] FIG. 8 shows a schematic configuration diagram of a video push device according to still other embodiments of the present disclosure. As shown in FIG. 8, the video push device 80 of this embodiment includes a memory 810 and a processor 820 coupled to the memory 810 and configured to execute the video push method in any one of the foregoing embodiments based on instructions stored in the memory 810.

[0099] Here, the memory 810 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory stores, for example, an operating system, an application, a boot loader, and other programs.

[0100] FIG. 9 shows a schematic configuration diagram of a video push device according to yet other embodiments of the present disclosure. As shown in FIG. 9, the video push device 90 of this embodiment includes a memory 910 and a processor 920, and may further include an input / output interface 930, a network interface 940, a storage interface 950, etc. These interfaces 930, 940, 950, and the memory 910 and the processor 920 may be connected via, for example, a bus 980. Here, the input / output interface 930 provides a connection interface to input / output devices such as a display, a mouse, a keyboard, and a touch panel. The network interface 940 provides a connection interface to various devices connected to the network. The storage interface 950 provides a connection interface to external storage devices such as an SD card and a USB drive.

[0101] Embodiments of the present disclosure further provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements any one of the above-described video pushing methods.

[0102] As will be appreciated by those skilled in the art, embodiments of the present disclosure may be provided as a method, a system, or a computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Further, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including, but not limited to, magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0103] The present disclosure has been described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing apparatus create means for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0104] These computer program instructions may be stored in a computer-readable memory that can guide a computer or other programmable data processing apparatus to operate in a specific manner. Thereby, the instructions stored in this computer-readable memory are caused to produce a manufactured article that includes instruction means for realizing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0105] These computer program instructions may be loaded into a computer or other programmable data processing apparatus. Thereby, the computer or other programmable apparatus is caused to execute a series of operation steps to generate a process implemented by the computer, so that the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0106] What is described above is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any corrections, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should all be included within the scope of the claims of the present disclosure.

Claims

1. Obtaining one or more videos including a video with a photosensitive label and a video without a photosensitive label, wherein each video has a photosensitive label when determined to be a photosensitive video by a photosensitive video identification model; When a viewing user is in a state of filtering photosensitive videos, pushing to the viewing user a video without a photosensitive label among the one or more videos. A video pushing method.

2. Obtaining feedback on a viewed video by the viewing user; When the feedback indicates that the viewed video is a photosensitive video, marking the viewed video as a photosensitive video and adding it to a training set for training the photosensitive video identification model. The pushing method according to claim 1.

3. Each video has a photosensitive label when a photosensitive effect is added. The pushing method according to claim 1 or 2.

4. When the viewing user is not in a state of filtering photosensitive videos, further including pushing the one or more videos to the viewing user. The pushing method according to any one of claims 1 to 3.

5. When the video to be played is a video with a photosensitive label, displaying a selection control for whether to filter the photosensitive video; Receiving an operation by the viewing user on the selection control; When the operation indicates filtering the photosensitive video, further including setting the viewing user to a state of filtering photosensitive videos. The pushing method according to any one of claims 1 to 4.

6. When the video to be played is a video with a photosensitive label that the viewing user views for the first time with the same account or on the same terminal, displaying a selection control for whether to filter the photosensitive video. The pushing method according to claim 5.

7. The selection control is located on a mask layer, and the mask layer is located on the upper layer of the video to be played. The pushing method according to claim 5 or 6.

8. Obtaining videos uploaded by the creator; Processing the uploaded video using a photosensitivity video identification model to determine whether the uploaded video is a photosensitivity video; When the uploaded video is a photosensitivity video, adding a photosensitivity label to the uploaded video; A video pushing method, including pushing videos without photosensitivity labels to the browsing user when the browsing user is in a state of filtering photosensitivity videos.

9. The pushing method according to claim 8, further including sending a notification to the creator when it is determined that the uploaded video is a photosensitivity video.

10. After sending a notification to the creator, receiving feedback sent by the creator; When the feedback indicates that the uploaded video is not a photosensitivity video, marking the uploaded video as a non-photosensitivity video and adding it to a training set for training the photosensitivity video identification model. The pushing method according to claim 9.

11. The pushing method according to any one of claims 8 to 10, wherein the photosensitivity video identification model is a neural network model.

12. A memory; A video pushing device, including a processor coupled to the memory and configured to execute the video pushing method according to any one of claims 1 to 11 based on instructions stored in the memory.

13. A computer-readable storage medium storing a computer program that, when executed by a processor, realizes the video pushing method according to any one of claims 1 to 11.

14. A computer program product that, when running on a computer, realizes the video pushing method according to any one of claims 1 to 11 on the computer.

15. A computer program including instructions that, when executed by a processor, cause the processor to execute the video pushing method according to any one of claims 1 to 11.

Images