Video processing method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a video processing method and device, and relates to the technical field of computers, in particular to the technical fields of large models, deep learning, image processing and the like. The specific implementation scheme is as follows: playing a first video in a first video list; in response to the received list refreshing operation, updating the first video list into a second video list, and playing a second video in the second video list; obtaining operation behavior information of operating the second video by the user; in response to the fact that the list refreshing operation is determined to be the mistaken refreshing operation based on the operation behavior information, the recommended video related to the first video is generated, and the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computers, specifically to technical fields such as large models, deep learning, and image processing, and in particular to a video processing method and device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] When watching a video, the user may refresh the video playlist due to an accidental touch or system error, and then lose the current video list being watched or miss some video content. Existing solutions mainly rely on browsing history or platform recommendation systems, which cannot identify the behavior of accidentally refreshing the video list. Summary of the invention

[0003] The present disclosure provides a video processing method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0004] According to a first aspect, a video processing method is provided, the method comprising: playing a first video in a first video list; in response to receiving a list refresh operation, updating the first video list to a second video list, and playing a second video in the second video list; obtaining operation behavior information of a user operating the second video; in response to determining that the list refresh operation is an erroneous refresh operation based on the operation behavior information, generating a recommended video related to the first video.

[0005] According to a second aspect, a video processing device is provided, which includes: a playback unit, configured to play a first video in a first video list; an update unit, configured to update the first video list to a second video list in response to receiving a list refresh operation, and play the second video in the second video list; an acquisition unit, configured to acquire operation behavior information of a user operating the second video; and a video generation unit, configured to generate a recommended video related to the first video in response to determining that the list refresh operation is an erroneous refresh operation based on the operation behavior information.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0008] According to a fifth aspect, a computer program product is provided, comprising a computer program, which implements the method described in any implementation manner of the first aspect when executed by a processor.

[0009] The video processing method and device provided by the embodiments of the present disclosure firstly play the first video in the first video list; secondly, in response to receiving a list refresh operation, update the first video list to a second video list, and play the second video in the second video list; thirdly, obtain the operation behavior information of the user on the second video; finally, in response to determining that the list refresh operation is a false refresh operation based on the operation behavior information, generate a recommended video related to the first video. Thus, after receiving the list refresh operation, the false refresh operation of the list refresh is judged by the operation behavior information of the user on the video, and the false touch behavior can be quickly identified; when the false refresh operation is identified, the recommended video is generated, which can help the user quickly jump to the new video content, avoid the viewing interruption caused by the false refresh, and improve the user experience.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is a flow chart of an embodiment of a video processing method according to the present disclosure;

[0013] Figure 2 is a structural diagram of a display recommendation control in the present disclosure;

[0014] Figure 3 is a structural schematic diagram of displaying recommended videos in the present disclosure;

[0015] Figure 4 It is a structural diagram of a list refresh control in the present disclosure;

[0016] Figure 5 is a structural schematic diagram of an embodiment of a video processing device according to the present disclosure;

[0017] Figure 6 The block diagram is a block diagram of an electronic device for implementing the video processing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] In view of the defects in the traditional technology, the present invention proposes a video processing method, which can generate recommended videos for users in time after the video list is refreshed by mistake, thereby improving the user experience. Figure 1 A process 100 according to an embodiment of a video processing method of the present disclosure is shown. The video processing method comprises the following steps:

[0020] Step 101, play the first video in the first video list.

[0021] In this embodiment, the execution subject on which the video processing method runs may be a video on demand system, and the video on demand architecture of the video on demand system enables users to watch, like, comment on and upload videos.

[0022] In this embodiment, the first video list can be a series of videos recommended to the user by the executing entity on which the video processing method runs. The first video in the first video list is replaced by the user operation (such as swiping up or down) after playing. The first video can be a video clip. The video clip has a shorter video length, for example, the video length is only 10 to 15 minutes. The video content of the first video can be a part of a film or TV series, or it can be some content shot by the user independently.

[0023] In this embodiment, the execution entity on which the video processing method runs can record the user, the number of plays, and the play progress and the number of plays of the first video in the first video list each time the first video in the first video list is played, wherein the number of plays is the number of times the user independently plays the first video.

[0024] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of the first video are performed after authorization and in compliance with relevant laws and regulations. The information related to the user in the first video is obtained with the user's permission, and the video processing related to the user is performed under confidentiality conditions.

[0025] Step 102, in response to receiving a list refresh operation, updating the first video list to a second video list, and playing a second video in the second video list.

[0026] In this embodiment, the list refresh operation can be an operation triggered by the video on demand system or the user to replace the first video in the current first video list, wherein the list refresh operation can be a normal refresh operation actively triggered based on user or system requirements, and the list refresh operation can also be an erroneous refresh operation caused by an abnormality of the video on demand system or an erroneous operation of the user.

[0027] In this embodiment, the second video list can be another series of videos recommended to the user by the executing entity on which the video processing method runs. The second video in the second video list is replaced by user operation (such as swiping up or down) after playing. The second video can be a video clip. The video content of the second video can be a part of a film or TV series, or it can be some content shot by the user independently.

[0028] In this embodiment, the execution entity on which the video processing method runs can record the user of the second video list, the number of times the second video is played, and the playback progress and the number of times the second video is played in the second video list each time the second video in the second video list is played.

[0029] Step 103: Obtain operation behavior information of the user operating the second video.

[0030] In this embodiment, when the user is watching the second video in the second video list, the user will change the content of the second video through operation, so as to achieve the purpose of playing all the second videos in the second video list in sequence.

[0031] In this embodiment, the operation behavior information is the user's specific operation on the second video. The operation behavior information may include: operation name, operation duration, operation type, etc. All operations of the user on the second video can be obtained through operation monitoring software to obtain the operation behavior information.

[0032] Step 104 , in response to determining that the list refresh operation is an erroneous refresh operation based on the operation behavior information, generating a recommended video related to the first video.

[0033] In this embodiment, regardless of whether it is an erroneous refresh operation by the user or an erroneous refresh operation by the video on demand system, after the user discovers that the played video has changed, he or she will often try to return to the previously watched video. The execution entity on which the video processing method runs determines the erroneous refresh operation by capturing such operation behavior information.

[0034] In this embodiment, the recommended video is a video recommended to the user. The recommended video can be a video clip. The video content of the recommended video can be a part of a film or TV series, or can be some content shot by the user. After determining the erroneous refresh operation, the recommended video can be generated based on the interest data of the user who is currently operating the video. The recommended video is consistent with the user's interests and meets the user's viewing needs, which can maximize the user's viewing experience.

[0035] The video processing method provided by the embodiment of the present disclosure firstly plays the first video in the first video list; secondly, in response to receiving a list refresh operation, updates the first video list to a second video list, and plays the second video in the second video list; thirdly, obtains the operation behavior information of the user operating the second video; finally, in response to determining that the list refresh operation is a false refresh operation based on the operation behavior information, generates a recommended video related to the first video. Thus, after receiving the list refresh operation, the false refresh operation of the list refresh is judged by the operation behavior information of the user operating the video, and the false touch behavior can be quickly identified; when the false refresh operation is identified, the recommended video is generated, which can help the user quickly jump to the new video content, avoid the viewing interruption caused by the false refresh, and improve the user experience.

[0036] In some optional implementations of the present disclosure, the above method also includes: generating and displaying a recommendation control; in response to receiving a first trigger operation on the recommendation control, displaying a thumbnail of the recommended video; in response to receiving a second trigger operation on the thumbnail, adding the recommended video to the second video list to obtain a third video list; and playing a third video in the third video list.

[0037] In this embodiment, the recommendation control is a control that implements user operations. The display position and display appearance of the recommendation control can be set based on development requirements. Figure 2 The following is a schematic diagram of the recommended control structure. Figure 2 The word "Entrance" is displayed in the recommendation control.

[0038] In this embodiment, the first trigger operation is an operation of the user on the recommendation control, and the operation type of the operation can be set based on demand. For example, the first trigger operation is a click operation.

[0039] In this embodiment, the thumbnail is a small image on a web page or in a computer that is compressed, and usually contains a hyperlink to the full-size video. The thumbnails of the recommended videos include: the thumbnail of the video you want to restore and the thumbnails of related videos, such as Figure 3The large frame in the upper middle part is the thumbnail of the video you want to restore, and the small frame in the lower part is the thumbnail of related videos. The video you want to restore can be a video in the first video, and the related videos are videos related to the first video in the plot or name or text in the video.

[0040] In this embodiment, the second trigger operation on the thumbnail refers to the operation performed on the displayed thumbnail. The operation on each thumbnail can enter the playback of the corresponding video. The operation type of the second trigger operation can be set based on needs. For example, the second trigger operation is a click operation.

[0041] The video processing method provided by this optional implementation generates and displays a recommendation control; in response to receiving a first trigger operation on the recommendation control, displays a thumbnail of the recommended video; in response to receiving a second trigger operation on the thumbnail, adds the recommended video to the second video list to obtain a third video list; plays the third video in the third video list, and by displaying the recommendation control to the user, provides a reliable entry for the display of the recommended video in a timely manner, thereby improving the user operation experience; adding the recommended video to the second video list to obtain the third video list provides a reliable implementation method for obtaining the third video list, thereby improving the accuracy of obtaining the third video list.

[0042] Optionally, the above method also includes: displaying an accidental touch operation prompt message; in response to receiving a reply operation to the accidental touch operation prompt message, adding a recommended video to the second video list, and playing a third video in the third video list.

[0043] Optionally, the above method further includes: based on a recommended video generation configuration pre-set by a user, adding the recommended video to the second video list, obtaining a third video list, and playing a third video in the third video list.

[0044] In some optional implementations of the present disclosure, the above method also includes: in response to not receiving a second trigger operation on the thumbnail within a set time, generating a list refresh control; in response to detecting a third trigger operation on the list refresh control, updating the second video list to the first video list, and playing the first video.

[0045] In this embodiment, the set time is a preset time period, and the set time can be set based on development requirements, for example, the set time is 5 seconds.

[0046] In this embodiment, the list refresh control is a control for implementing user operations, and the display position and display appearance of the list refresh control can be set based on development requirements. Figure 4 The following is a schematic diagram of the structure of the list refresh control. Figure 3 The list refresh control shown has a prompt "Do you want to use the first video list before the wrong refresh?" Figure 3 The list refresh control shown also has buttons for users to select. When the user wants to use the first video list before the mistaken refresh, the user can directly click the "Yes" button; when the user does not want to use the first video list before the mistaken refresh, the user can directly click the "No" button.

[0047] The video processing method provided in this embodiment generates a list refresh control, and in response to detecting a third trigger operation on the list refresh control, updates the second video list to the first video list and plays the first video. After an erroneous refresh operation occurs when playing the first video in the first video list, the method can promptly restore the first video in the first video list, thereby correcting the deviation caused by the erroneous refresh and improving the user's video viewing experience.

[0048] In some optional implementations of the present disclosure, the above-mentioned response determines that the list refresh operation is a false refresh operation based on the operational behavior information, and generates a recommended video related to the first video, including: based on the operational behavior information, detecting whether the list refresh operation is a false refresh operation; in response to detecting that the list refresh operation is a false refresh operation, generating a recommended video related to the first video based on historical videos played historically.

[0049] In this optional implementation, the historical video is a video that has been played historically by the current user, wherein the historical video includes a first video and a second video that has been played completely; the above-mentioned generation of a recommended video related to the first video based on the historical video played historically includes: selecting the first video from the historical video and using the first video as the recommended video.

[0050] The method for generating recommended videos provided by this optional implementation detects whether a list refresh operation is an erroneous refresh operation based on operational behavior information. In response to detecting that the list refresh operation is an erroneous refresh operation, a recommended video related to the first video is generated based on historical videos that have been played historically. After the erroneous refresh operation is detected, a recommended video is generated based on the historical video, and the recommended video is obtained from the historical video, thereby improving the accuracy of obtaining the recommended video.

[0051] Optionally, the above response determines that the list refresh operation is a false refresh operation based on the operation behavior information, and generates a recommended video related to the first video, including: based on the operation behavior information, detecting whether the list refresh operation is a false refresh operation; in response to detecting that the list refresh operation is a false refresh operation, selecting a video with the highest similarity to the first video from a preset video set, to obtain a recommended video related to the first video.

[0052] Optionally, the above response determines that the list refresh operation is a false refresh operation based on the operation behavior information, and generates a recommended video related to the first video, including: based on the operation behavior information, detecting whether the list refresh operation is a false refresh operation; in response to detecting that the list refresh operation is a false refresh operation, using the first video and a video clip belonging to the same plot as the first video as recommended videos.

[0053] In some embodiments of the present disclosure, the above-mentioned list refresh operation includes: a first refresh operation of the user, in response to detecting that the list refresh operation is a false refresh operation, generating a recommended video related to the first video based on historical videos that have been historically played, including: in response to detecting that the first list refresh operation is a false refresh operation, using an image recognition model to obtain a fourth video related to the user from the historical videos; based on the identification of the fourth video and the video progress, determining the recommended video related to the first video.

[0054] In this optional implementation, the first refresh operation of the user is a refresh operation caused by the user. When the first refresh operation of the system is an erroneous refresh operation, it is determined that the user has mistakenly triggered the refresh function of the system.

[0055] In this optional implementation, the image recognition model uses a trained deep learning model to identify key frames in the video. The execution subject on which the video processing method runs will periodically extract the key frame images (such as characters, scenes, objects, etc.) of the video when the user is watching the video, and store the key frame images in the historical video, so that each video in the historical video has corresponding key frame information. When the execution subject on which the video processing method runs detects an erroneous refresh operation, the previously saved historical video is input into the image recognition model to identify features and find the fourth video with key frames related to the user.

[0056] In this optional implementation, video progress refers to the playback progress in historical playback. The above-mentioned determination of recommended videos related to the first video based on the identifier and video progress of the fourth video includes: based on the video progress of each video in the fourth video (such as the video progress is greater than 70%), determining the identifier of the video that the user is interested in, and using the video with the identifier as a recommended video related to the first video.

[0057] The method for generating a first video provided by this optional implementation adopts an image recognition model to obtain a fourth video related to the user from historical videos in response to detecting that the first list refresh operation is an erroneous refresh operation; based on the identification of the fourth video and the video progress, a recommended video related to the first video is determined. Determining the recommended video based on the identification of the fourth video and the video progress can link the recommended video with the user's preferences, thereby improving the reliability of obtaining the recommended video and improving the user experience.

[0058] In some optional implementations of the present disclosure, the above-mentioned list refresh operation includes: a second refresh operation of the system, in response to detecting that the list refresh operation is a false refresh operation, generating a recommended video related to the first video based on a third video played historically, including: in response to detecting that the second list refresh operation is a false refresh operation, selecting a fifth video related to the first video list from the historical videos; and determining the fifth video as a recommended video related to the first video.

[0059] In this optional implementation, the second refresh operation of the system is a refresh operation caused autonomously by the video-on-demand system. When the second refresh operation of the system is an erroneous refresh operation, it is determined that a system error occurs in the video-on-demand system.

[0060] In this optional implementation, the fifth video is a video recommended to the user. Specifically, a video with the same plot or story as the first video in the first video list can be selected from historical videos as the fifth video.

[0061] The method for generating recommended videos provided by this optional implementation selects a fifth video related to the first video list from historical videos when it is detected that the refresh operation of the second list is an erroneous refresh operation, and determines the fifth video as a recommended video related to the first video, thereby improving the reliability of obtaining recommended videos.

[0062] In some optional implementations of the present disclosure, the above-mentioned operation behavior information includes: the number of slide back actions of the second video and the slide back time interval of the second video; based on the operation behavior information, detecting whether the list refresh operation is a false refresh operation includes: in response to detecting that the number of slide back actions is greater than a preset number, detecting whether the slide back time interval between any adjacent slide back actions is less than a preset time value; in response to detecting that the slide back time interval between any adjacent slide back actions is less than a preset time value, determining that the list refresh operation is a false refresh operation.

[0063] In this optional implementation, the user's operating behavior is monitored, especially the action of quickly sliding back the page after the refresh operation is triggered, so that erroneous refresh operations can be effectively identified.

[0064] In this optional implementation, the number of predictions and the preset time value can be determined based on the user's behavioral habits. For example, the preset number of times is 5 times and the preset time value is 3s.

[0065] The method for detecting erroneous refresh operations provided by this optional implementation first detects whether the number of sliding back actions is greater than a preset number; secondly, when the number of sliding back actions is greater than the preset number, detects whether the sliding back time interval between any adjacent sliding back actions is less than a preset time value; finally, when the sliding back time interval between any adjacent sliding back actions is less than the preset time value, determines that the list refresh operation is a erroneous refresh operation, thereby monitoring the erroneous refresh operation from the aspects of the user's sliding back action and the sliding back time interval of the second video, thereby improving the reliability of erroneous refresh operation detection.

[0066] Optionally, the above-mentioned operation behavior information includes: the number of slide back actions of the second video and the slide back time interval of the second video; the above-mentioned detection of whether the list refresh operation is an erroneous refresh operation based on the operation behavior information includes: in response to detecting that the number of slide back actions is less than or equal to a preset number, detecting whether the slide back time interval between any adjacent slide back actions is less than a preset time value; in response to detecting that the slide back time interval between at least one adjacent slide back action is greater than or equal to a preset time value, determining that the list refresh operation is not an erroneous operation or an erroneous refresh operation.

[0067] Optionally, the above-mentioned operation behavior information includes: the number of slide back actions of the second video and the slide back time interval of the second video; the above-mentioned detection of whether the list refresh operation is an erroneous refresh operation based on the operation behavior information includes: in response to detecting that the number of slide back actions is greater than a preset number, detecting whether the slide back time interval between any adjacent slide back actions is less than a preset time value; in response to detecting that the slide back time interval between at least one adjacent slide back action is greater than or equal to the preset time value, determining that the list refresh operation is not an erroneous operation or an erroneous refresh operation.

[0068] In some optional implementations of the present disclosure, the above-mentioned operation behavior information also includes: the first interaction frequency of the second video, the video playback time, the historical playback time and the historical interaction frequency of the historical videos; based on the operation behavior information, detecting whether the list refresh operation is an erroneous refresh operation also includes: based on the video playback time, calculating the average playback time of the second video; detecting whether the historical playback time is greater than the average playback time; in response to detecting that the historical playback time is greater than the average playback time, detecting whether the first interaction frequency is less than the historical interaction frequency; in response to detecting that the first interaction frequency is less than the historical interaction frequency, detecting whether the number of slide back operations is greater than a preset number.

[0069] In this optional implementation, when the user refreshes the video, he or she immediately swipes quickly to try to return to the previously watched video. The system determines whether the behavior is an erroneous operation by monitoring the swiping action and time interval after the refresh, combined with the user's playback time, interaction frequency and other data in the historically watched videos.

[0070] In this optional implementation, the video playback duration is the duration that the user plays the second video. There are multiple videos in the second video, and each video has a corresponding video playback duration. The average playback duration is the average of the video playback durations of each video in the second video during a historical time period (such as the past month).

[0071] In this optional implementation, the historical playback duration is the average of the playback durations of all videos played by the user in the historical time period. By comparing the average playback duration with the historical playback duration, the length of the user's playback time for the second video can be detected.

[0072] In this optional implementation, the first interaction frequency is the frequency of feedback given by the user to the video when watching the second video, for example, the number of likes and comments.

[0073] In this optional implementation, the historical interaction frequency is the average of the feedback frequencies of the user's feedback on all videos in the historical time period. By comparing the first interaction frequency with the historical interaction frequency, the user's attention to the second video can be detected.

[0074] The method for detecting erroneous refresh operations provided by this optional implementation calculates the average playback time of the second video before detecting whether the number of scroll back operations is greater than a preset number, detects whether the historical playback time is greater than the average playback time, and when the historical playback time is greater than the average playback time, detects whether the first interaction frequency is less than the historical interaction frequency. In response to detecting that the first interaction frequency is less than the historical interaction frequency, it then detects whether the number of scroll back operations is greater than a preset number. The average playback time and the first interaction frequency are used as means for detecting erroneous refresh operations, thereby improving the accuracy of erroneous refresh operation detection.

[0075] In some optional implementations of the present disclosure, the above-mentioned operation behavior information includes: operation mode data of the second video; based on the operation behavior information, detecting whether the list refresh operation is an erroneous refresh operation includes: inputting the operation mode data into a pre-trained behavior analysis model to obtain a behavior analysis result output by the behavior analysis model; in response to the behavior analysis result being an abnormal behavior result, determining that the list refresh operation is an erroneous refresh operation.

[0076] In this optional implementation, the operation mode data is data such as the user's preferences and habits for operating the second video during the playback of the second video. For example, a user's operation mode data for the second video is: first fast forward to watch the entire second video, and when the overall development of the second video is more attractive, play the second video according to the playback progress of the player.

[0077] In this optional implementation, the operation mode data can reflect whether the user's operation is normal or not. The operation mode data can be used to determine if the user's operation behavior is suddenly inconsistent with the usual, such as sliding quickly after refreshing, staying for a very short time, or frequent operation behaviors. The behavior analysis model can determine that this is an abnormal behavior result that does not conform to the norm.

[0078] In this optional implementation, the behavior analysis model is a model that analyzes the user's behavior of playing videos. The behavior analysis model is a pre-trained model for classifying user behaviors. The user's operation mode data is input into the behavior analysis model to obtain a behavior analysis result output by the behavior analysis model, wherein the analysis result includes: normal behavior results and abnormal behavior results. When the behavior analysis model outputs an abnormal behavior result, it is determined that the user's operation behavior information is abnormal. At this time, the list refresh operation is an erroneous refresh operation. The operation behavior information is analyzed by the behavior analysis model to improve the accuracy of the list refresh operation analysis.

[0079] In some optional implementations of the present disclosure, the above-mentioned operation behavior information includes: user search information; based on the operation behavior information, detecting whether the list refresh operation is an erroneous refresh operation includes: detecting whether the search information matches the first video; in response to the search information matching the first video, determining that the list refresh operation is an erroneous refresh operation.

[0080] In this optional implementation, the search information is the video information that the user searches for when watching the second video. For the first video that the user likes, if an erroneous refresh operation is performed, the user may obtain the video information of the first video through the search.

[0081] In this optional implementation, the search information matches the first video when: the text information of the search information is the same as the name of the first video, or the text information of the search information is the same as the description of a partial segment of the first video.

[0082] In this optional implementation, the user uses the platform's search function to enter search information such as keywords or words related to previously watched videos, which can also serve as a signal that the user wants to return to the previous video.

[0083] The method for detecting erroneous refresh operations provided by this optional implementation detects whether the search information matches the first video, and in response to the search information matching the first video, determines that the list refresh operation is an erroneous refresh operation, thereby improving the reliability of erroneous refresh operation detection.

[0084] In some optional implementations of the present disclosure, in response to receiving a list refresh operation, updating the first video list to a second video list includes: in response to receiving a list refresh operation, obtaining a sixth video to be added; adding the sixth video to the first video list to obtain a second video list.

[0085] In this optional implementation, the sixth video can be a video randomly obtained from a video library that stores videos, or the sixth video can be a video of interest to the user selected from the video library based on the user's attribute information. The sixth video is added to the first video list, the video length of the first video list is changed, and the second video list is obtained.

[0086] This optional implementation provides a method for updating the second video list, obtaining the sixth video, and adding the sixth video to the first video list to obtain the second video list, which provides a reliable implementation method for obtaining the second video list. The second video list can be obtained by simply adding the sixth video to the second video list, thereby improving the diversity and convenience of obtaining the second video list.

[0087] In some optional implementations of the present disclosure, in response to receiving a list refresh operation, updating the first video list to a second video list includes: in response to receiving a list refresh operation, selecting a second video list from a list collection based on user interest data; and replacing the first video list with the second video list.

[0088] In this optional implementation, the user's interest data is data reflecting the user's actual interests and hobbies. The interest data particularly reflects the user's viewing interest in watching videos, for example, the user likes to watch variety shows.

[0089] In this optional implementation, the list set includes at least one video list, and the videos in each video list can be arranged based on different video categories.

[0090] The method for updating the second video list provided by this optional implementation is, in response to receiving a list refresh operation, selecting a second video list from a list collection based on the user's interest data; using the second video list to replace the first video list provides a reliable implementation method for obtaining the second video list, and selecting the second video list through the list collection improves the diversity and convenience of obtaining the second video list.

[0091] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a video processing device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically implemented in various electronic devices.

[0092] like Figure 5As shown, the video processing device 500 provided in this embodiment includes: a playback unit 501, an update unit 502, an acquisition unit 503, and a video generation unit 504. Among them, the above-mentioned playback unit 501 can be configured to play the first video in the first video list. The above-mentioned update unit 502 can be configured to update the first video list to the second video list in response to receiving a list refresh operation, and play the second video in the second video list. The above-mentioned acquisition unit 503 can be configured to obtain the operation behavior information of the user operating the second video. The above-mentioned video generation unit 504 can be configured to generate a recommended video related to the first video in response to determining that the list refresh operation is an erroneous refresh operation based on the operation behavior information.

[0093] In this embodiment, the specific processing of the playback unit 501, the update unit 502, the acquisition unit 503, and the video generation unit 504 and the technical effects thereof can be referred to in detail. Figure 1 The relevant descriptions of step 101, step 102, step 103, and step 104 in the corresponding embodiment are not repeated here.

[0094] In some optional implementations of the present embodiment, the above-mentioned device 500 also includes: a first control generating unit (not shown in the figure), the above-mentioned first control generating unit is configured to generate and display a recommendation control; in response to receiving a first trigger operation on the recommendation control, display a thumbnail of the recommended video; in response to receiving a second trigger operation on the thumbnail, add the recommended video to the second video list to obtain a third video list; and play the third video in the third video list.

[0095] In some optional implementations of the present embodiment, the above-mentioned device also includes: a second control generating unit (not shown in the figure), and the above-mentioned second control generating unit is configured to: in response to not receiving a second trigger operation on the thumbnail within a set time, generate a list refresh control; in response to detecting a third trigger operation on the list refresh control, update the second video list to the first video list, and play the first video.

[0096] In some optional implementations of this embodiment, the above-mentioned video generation unit 504 is configured to: detect whether the list refresh operation is an erroneous refresh operation based on the operation behavior information; in response to detecting that the list refresh operation is an erroneous refresh operation, generate a recommended video related to the first video based on historical videos played historically.

[0097] In some optional implementations of this embodiment, the above-mentioned list refresh operation includes: a first refresh operation of the user, and the above-mentioned video generation unit 504 is configured to: in response to detecting that the first list refresh operation is an erroneous refresh operation, use an image recognition model to obtain a fourth video related to the user from historical videos; based on the identification of the fourth video and the video progress, determine the recommended video related to the first video.

[0098] In some optional implementations of this embodiment, the above-mentioned list refresh operation includes: a second refresh operation of the system, and the above-mentioned video generation unit 504 is configured to: in response to detecting that the second list refresh operation is an erroneous refresh operation, select a fifth video related to the first video list from the historical videos; and determine the fifth video as a recommended video related to the first video.

[0099] In some optional implementations of the present embodiment, the above-mentioned operation behavior information includes: the number of rewind actions of the second video and the rewind time interval of the second video; the above-mentioned video generation unit 504 is configured to: in response to detecting that the number of rewind actions is greater than a preset number, detect whether the rewind time interval between any adjacent rewind actions is less than a preset time value; in response to detecting that the rewind time interval between any adjacent rewind actions is less than a preset time value, determine that the list refresh operation is a false refresh operation.

[0100] In some optional implementations of this embodiment, the above-mentioned operation behavior information also includes: the first interaction frequency of the second video, the video playback time, the historical playback time and the historical interaction frequency of historical videos; the above-mentioned video generation unit 504 is configured to: calculate the average playback time of the second video based on the video playback time; detect whether the historical playback time is greater than the average playback time; in response to detecting that the historical playback time is greater than the average playback time, detect whether the first interaction frequency is less than the historical interaction frequency; in response to detecting that the first interaction frequency is less than the historical interaction frequency, detect whether the number of scroll back actions is greater than a preset number.

[0101] In some optional implementations of this embodiment, the above-mentioned operation behavior information includes: operation mode data of the second video; the video generation unit is configured to: input the operation mode data into a pre-trained behavior analysis model to obtain a behavior analysis result output by the behavior analysis model; in response to the behavior analysis result being an abnormal behavior result, determine that the list refresh operation is an erroneous refresh operation.

[0102] In some optional implementations of the present disclosure, the above-mentioned operation behavior information includes: user search information; the video generation unit is configured to: detect whether the search information matches the first video; in response to the search information matching the first video, determine that the list refresh operation is an erroneous refresh operation.

[0103] In some optional implementations of the present disclosure, the updating unit is configured to: in response to receiving a list refresh operation, obtain a sixth video to be added; and add the sixth video to the first video list to obtain a second video list.

[0104] In some optional implementations of the present disclosure, the updating unit is configured to: in response to receiving a list refresh operation, select a second video list from the list set based on the user's interest data; and replace the first video list with the second video list.

[0105] The video processing device provided by the embodiment of the present disclosure, first, the playing unit 501 plays the first video in the first video list; secondly, the updating unit 502 updates the first video list to the second video list in response to receiving the list refresh operation, and plays the second video in the second video list; thirdly, the acquiring unit 503 acquires the operation behavior information of the user operating the second video, and finally, the video generating unit 504 generates a recommended video related to the first video in response to determining that the list refresh operation is a false refresh operation based on the operation behavior information. Thus, after receiving the list refresh operation, the false refresh operation of the list refresh is judged by the operation behavior information of the user operating the video, and the false touch behavior can be quickly identified; when the false refresh operation is identified, the recommended video is generated, which can help the user quickly jump to the new video content, avoid the viewing interruption caused by the false refresh, and improve the user experience.

[0106] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0107] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0108] Figure 4 Figure 6 A schematic block diagram of an example electronic device 40600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0109] like Figure 6As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 40603 are connected to each other via a bus 40604. An input / output (I / O) interface 40605 is also connected to the bus 604.

[0110] A number of components in the device 600 are connected to the I / O interface 40605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0111] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as video processing methods. For example, in some embodiments, the video processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the video processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the video processing method in any other appropriate manner (e.g., by means of firmware).

[0112] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable video processing device, so that the program code, when executed by the processor or controller, causes the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0114] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an information server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0117] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0118] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0119] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A video processing method, wherein: The method comprises: Play the first video in the first video list; In response to receiving a list refresh operation, updating the first video list to a second video list, and playing a second video in the second video list; Acquire operation behavior information of the user on the second video; In response to determining that the list refresh operation is an erroneous refresh operation based on the operation behavior information, a recommended video related to the first video is generated.

2. The method according to claim 1, further comprising: Generate and display recommended controls; In response to receiving a first trigger operation on the recommendation control, displaying a thumbnail of the recommended video; In response to receiving a second trigger operation on the thumbnail, adding the recommended video to the second video list to obtain a third video list; Play the third video in the third video list.

3. The method according to claim 1, further comprising: In response to not receiving a second trigger operation on the thumbnail within a set time, generating a list refresh control; In response to detecting a third trigger operation on the list refresh control, the second video list is updated to the first video list, and the first video is played.

4. The method according to any one of claims 1 to 3, wherein: The response determines that the list refresh operation is an erroneous refresh operation based on the operation behavior information, and generates a recommended video related to the first video, comprising: Based on the operation behavior information, detecting whether the list refresh operation is an erroneous refresh operation; In response to detecting that the list refresh operation is an erroneous refresh operation, a recommended video related to the first video is generated based on historical videos that have been played historically.

5. The method according to claim 4, wherein: The list refresh operation includes: a first refresh operation of a user, and in response to detecting that the list refresh operation is an erroneous refresh operation, generating a recommended video related to the first video based on historical videos played in history includes: In response to detecting that the first list refresh operation is an erroneous refresh operation, acquiring a fourth video related to the user from the historical videos using an image recognition model; Based on the identifier of the fourth video and the video progress, a recommended video related to the first video is determined.

6. The method according to claim 4, wherein: The list refresh operation includes: a second refresh operation of the system, wherein in response to detecting that the list refresh operation is an erroneous refresh operation, generating a recommended video related to the first video based on a third video played historically includes: In response to detecting that the second list refresh operation is an erroneous refresh operation, selecting a fifth video related to the first video list from the historical videos; The fifth video is determined to be a recommended video related to the first video.

7. The method according to claim 4, wherein: The operation behavior information includes: the number of slide-back operations of the second video and the slide-back time interval of the second video; and the detecting whether the list refresh operation is an erroneous refresh operation based on the operation behavior information includes: In response to detecting that the number of sliding back actions is greater than a preset number, detecting whether a sliding back time interval between any adjacent sliding back actions is less than a preset time value; In response to detecting that a sliding back time interval between any adjacent sliding back operations is less than a preset time value, it is determined that the list refresh operation is a false refresh operation.

8. The method according to claim 7, wherein: The operation behavior information further includes: the first interaction frequency and video playback duration of the second video, the historical playback duration and historical interaction frequency of the historical video; and the detecting whether the list refresh operation is an erroneous refresh operation based on the operation behavior information further includes: Based on the video playback duration, calculating the average playback duration of the second video; Detecting whether the historical playback duration is greater than the average playback duration; In response to detecting that the historical playback duration is greater than the average playback duration, detecting whether the first interaction frequency is less than the historical interaction frequency; In response to detecting that the first interaction frequency is less than the historical interaction frequency, detecting whether the number of sliding back actions is greater than a preset number.

9. The method according to claim 4, wherein: The operation behavior information includes: operation mode data of the second video; and the detecting whether the list refresh operation is an erroneous refresh operation based on the operation behavior information includes: Inputting the operation mode data into a pre-trained behavior analysis model to obtain a behavior analysis result output by the behavior analysis model; In response to the behavior analysis result being an abnormal behavior result, determining that the list refresh operation is an erroneous refresh operation.

10. The method according to claim 4, wherein: The operation behavior information includes: user search information; and the detecting whether the list refresh operation is an erroneous refresh operation based on the operation behavior information includes: Detecting whether the search information matches the first video; In response to the search information matching the first video, it is determined that the list refresh operation is a false refresh operation.

11. The method according to any one of claims 1 to 3, wherein: In response to receiving a list refresh operation, updating the first video list to a second video list includes: In response to receiving the list refresh operation, obtaining a sixth video to be added; The sixth video is added to the first video list to obtain a second video list.

12. The method according to any one of claims 1 to 3, wherein: In response to receiving the list refresh operation, updating the first video list to the second video list comprises: In response to receiving the list refresh operation, selecting a second video list from the list set based on the user's interest data; The second video list is used to replace the first video list.

13. A video processing device, comprising: A playback unit, configured to play the first video in the first video list; an updating unit, configured to update the first video list to a second video list in response to receiving a list refresh operation, and play a second video in the second video list; An acquisition unit is configured to acquire operation behavior information of a user operating the second video; The video generating unit is configured to generate a recommended video related to the first video in response to determining that the list refreshing operation is a false refreshing operation based on the operation behavior information.

14. The apparatus according to claim 13, further comprising: A first control generating unit, configured to generate and display a recommended control; In response to receiving a first trigger operation on the recommendation control, displaying a thumbnail of the recommended video; In response to receiving a second trigger operation on the thumbnail, the recommended video is added to the second video list to obtain a third video list; and the third video in the third video list is played.

15. The apparatus according to claim 13, further comprising: A second control generating unit is configured to generate a list refresh control in response to not receiving a second triggering operation on the thumbnail within a set time; In response to detecting a third trigger operation on the list refresh control, the second video list is updated to the first video list, and the first video is played.

16. The device according to any one of claims 13 to 15, wherein: The video generation unit is configured to: detect whether the list refresh operation is an erroneous refresh operation based on the operation behavior information; in response to detecting that the list refresh operation is an erroneous refresh operation, generate a recommended video related to the first video based on historical videos played historically.

17. The device according to claim 16, wherein: The list refresh operation includes: a first refresh operation of the user, and the video generation unit is configured to: in response to detecting that the first list refresh operation is an erroneous refresh operation, use an image recognition model to obtain a fourth video related to the user from the historical videos; based on the identification of the fourth video and the video progress, determine a recommended video related to the first video.

18. The device according to claim 16, wherein: The list refresh operation includes: a second refresh operation of the system, the video generation unit is configured to: in response to detecting that the second list refresh operation is a false refresh operation, select a fifth video related to the first video list from the historical videos; and determine the fifth video as a recommended video related to the first video.

19. The device according to claim 16, wherein: The operation behavior information includes: the number of rewind operations of the second video and the rewind time interval of the second video; the video generation unit is configured to: in response to detecting that the number of rewind operations is greater than a preset number, detect whether the rewind time interval between any adjacent rewind operations is less than a preset time value; in response to detecting that the rewind time interval between any adjacent rewind operations is less than a preset time value, determine that the list refresh operation is a false refresh operation.

20. The device according to claim 19, wherein The operation behavior information also includes: the first interaction frequency and video playback time of the second video, the historical playback time and historical interaction frequency of the historical video; the video generation unit is configured to: calculate the average playback time of the second video based on the video playback time; detect whether the historical playback time is greater than the average playback time; in response to detecting that the historical playback time is greater than the average playback time, detect whether the first interaction frequency is less than the historical interaction frequency; in response to detecting that the first interaction frequency is less than the historical interaction frequency, detect whether the number of scroll back actions is greater than a preset number.

21. The device according to claim 16, wherein: The operation behavior information includes: the operation mode data of the second video; the video generation unit is configured to: input the operation mode data into a pre-trained behavior analysis model to obtain a behavior analysis result output by the behavior analysis model; in response to the behavior analysis result being an abnormal behavior result, determine that the list refresh operation is an erroneous refresh operation.

22. The device according to claim 16, wherein: The operation behavior information includes: user's search information; the video generation unit is configured to: detect whether the search information matches the first video; in response to the search information matching the first video, determine that the list refresh operation is an erroneous refresh operation.

23. The device according to any one of claims 13 to 15, wherein: The updating unit is configured to: in response to receiving a list refresh operation, obtain a sixth video to be added; and add the sixth video to the first video list to obtain a second video list.

24. The device according to any one of claims 13 to 15, wherein: The updating unit is configured to: in response to receiving a list refresh operation, select a second video list from the list set based on user interest data; and replace the first video list with the second video list.

25. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 12.

26. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 12.

27. A computer program product, comprising a computer program, which, when executed by a processor, implements the method of any one of claims 1 to 12.

Images