Preview video generation method, video previewing method and video previewing device

Abstract

The invention provides a preview video generation method, a video preview method and a video preview device. The method comprises the following steps: acquiring feedback information of a candidate account for a target video; determining a first target video frame from a plurality of candidate video frames of the target video based on the feedback information; and generating a first type of preview video of the target video based on the plurality of first target video frames. Therefore, according to the scheme, the diversity of the generated preview video can be improved, so that the generated preview video is rich in content and relatively high in individuation degree, and the interests of different users can be attracted. In addition, according to the playing time sequence of the video frames, the second type of preview videos can be generated, the preview range of the preview videos can be expanded, and the diversity of the preview videos can be improved by generating the first type of preview videos and the second type of preview videos.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method for generating preview videos, a video preview method, and an apparatus. Background Technology

[0002] Currently, preview videos can be generated by extracting keyframes to create preview thumbnails or dynamic summaries, playing video clips when the mouse hovers over them, or using deep learning to recognize video content and generate personalized preview videos. Preview videos generated using these methods are relatively fixed, contain limited content, and cannot provide users with diverse interactive experiences, resulting in a rather limited selection of preview videos recommended to users. Summary of the Invention

[0003] The purpose of this application is to at least partially solve one of the technical problems in the related art.

[0004] Therefore, the first objective of this application is to propose a method for generating preview videos, so as to improve the diversity of generated preview videos, making the generated preview videos richer in content and more personalized, thereby attracting the interest of different users.

[0005] The second objective of this application is to propose a video preview method.

[0006] The third objective of this application is to provide a device for generating preview videos.

[0007] The fourth objective of this application is to provide a video preview device.

[0008] To achieve the above objectives, a first aspect of this application proposes a method for generating a preview video, comprising: obtaining feedback information from candidate accounts regarding a target video; determining a first target video frame from a plurality of candidate video frames of the target video based on the feedback information; and generating a first type of preview video of the target video based on the plurality of the first target video frames.

[0009] To achieve the above objectives, a first aspect of this application proposes a video preview method, comprising: determining a preview video library; wherein the preview video library includes a first type of preview videos of multiple candidate videos, the first type of preview video of any candidate video is generated based on a first target video frame of the corresponding candidate video, the first target video frame being determined based on feedback information from a candidate account regarding the corresponding candidate video; determining a target preview video from the preview video library based on the account type of the target account and the video preview operation of the target account; and displaying the target preview video.

[0010] To achieve the above objectives, a third aspect of this application provides a preview video generation apparatus, comprising: an acquisition module for acquiring feedback information from candidate accounts regarding a target video; a determination module for determining a first target video frame from a plurality of candidate video frames of the target video based on the feedback information; and a generation module for generating a first type of preview video of the target video based on the plurality of the first target video frames.

[0011] To achieve the above objectives, a fourth aspect of this application provides a video preview device, comprising: a first determining module for determining a preview video library; wherein the preview video library includes a first type of preview videos of multiple candidate videos, and the first type of preview video of any candidate video is generated based on a first target video frame of the corresponding candidate video, the first target video frame being determined based on feedback information from a candidate account regarding the corresponding candidate video; a second determining module for determining a target preview video from the preview video library based on the account type of the target account and the video preview operation of the target account; and a display module for displaying the target preview video.

[0012] The preview video generation method, video preview method, and apparatus provided in this application obtain feedback information from candidate accounts regarding a target video. Based on this feedback information, a first target video frame is determined from multiple candidate video frames of the target video. This allows for the generation of a first type of preview video related to user preferences, increasing the diversity of generated preview videos and resulting in richer, more personalized content that attracts diverse user interests. Furthermore, this application can also generate a second type of preview video based on the playback sequence of video frames, expanding the preview scope. By generating both the first and second types of preview videos, the diversity of preview videos is further enhanced.

[0013] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0014] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart illustrating a method for generating a preview video provided in an embodiment of this application; Figure 2 A flowchart illustrating a video preview method provided in an embodiment of this application; Figure 3 A flowchart illustrating another video preview method provided in an embodiment of this application; Figure 4A flowchart illustrating another video preview method provided in an embodiment of this application; Figure 5 This is a schematic diagram illustrating the determination of a target preview video based on a first operation, as provided in an embodiment of this application. Figure 6 A flowchart illustrating another video preview method provided in an embodiment of this application; Figure 7 A flowchart illustrating another video preview method provided in an embodiment of this application; Figure 8 This is a schematic diagram illustrating the determination of at least one candidate video based on a second operation, as provided in an embodiment of this application. Figure 9 A schematic diagram of the structure of a preview video generation device provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of a video preview device provided in an embodiment of this application. Detailed Implementation

[0015] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0016] The method and apparatus for generating preview videos according to embodiments of this application are described below with reference to the accompanying drawings.

[0017] Figure 1 This is a flowchart of a method for generating a preview video according to an embodiment of this application, such as... Figure 1 As shown, the method for generating a preview video according to an embodiment of this application includes, but is not limited to, the following steps: S101, Obtain feedback information from candidate accounts regarding the target video.

[0018] It should be noted that the execution subject of the preview video generation method provided in this application embodiment is an electronic device, which can be a terminal device. Optionally, the terminal device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be personal computers (PCs), televisions, etc. This application embodiment does not impose specific limitations.

[0019] In some embodiments, video application software is installed in the electronic device so that users can log in to the video application software with different accounts and browse the videos in the video application software.

[0020] In some embodiments, a candidate account refers to an account that has viewed a target video, which can be a video within a video application. Taking a video application as an example, the target video can be a list of videos within the application, i.e., a series of videos, which is a collection of multiple videos; the target video can also be any single video within a series; or it can be a segment of videos within a series.

[0021] For example, accounts 1, 2, and 3 belong to video application A, which includes series 1 and 2. Let the target video be all videos included in series 1. If account 1 has viewed any video in series 1, account 1 is identified as a candidate account. If account 2 has not viewed series 1, but account 3 has, then accounts 1 and 3 are identified as candidate accounts. Furthermore, feedback information from accounts 1 and 3 regarding the target video can be obtained.

[0022] In some embodiments, the operation information of different accounts can be obtained, and based on the operation information, it can be determined whether different accounts are candidate accounts that have viewed the target video. For example, if the operation information includes the target video, the account can be determined as a candidate account.

[0023] In some embodiments, when a candidate account views a target video, it can provide feedback on the target video and associate the feedback information with the candidate account. Thus, when determining a candidate account, the feedback information of the candidate account regarding the target video can be obtained based on this association.

[0024] In some embodiments, feedback information may be comments on the target video, emotional information, audio information, body language information, etc.

[0025] In some embodiments, the comment information is a comment sent by the candidate account, and the comment information can be a comment on any frame of the target video. Emotional information, voice information, and body language information can be information collected by the video application software when the candidate account browses the target video.

[0026] It should be noted that the process of obtaining feedback information is carried out with the user's authorization and in strict accordance with relevant laws and regulations on privacy and security. Furthermore, the information obtained is only for feedback and does not involve reading any user privacy information.

[0027] In some embodiments, the process of acquiring emotional information may involve using computer vision and deep learning technologies, based on the camera of an electronic device, to collect image data containing facial information of candidate accounts, and then performing real-time or offline analysis on the image data to obtain the emotional information of the candidate accounts from the image data. For example, emotional information includes: happiness, anger, sadness, etc.

[0028] Optionally, emotional information in image data can be obtained through steps such as preprocessing, face detection, key point localization, feature extraction, feature alignment, task model inference, and result output. Any feature extraction method from relevant technologies can be used to determine the emotional information; no specific limitation is made.

[0029] In some embodiments, the camera and microphone of an electronic device can be used to collect the voice and body movements of candidate accounts in real time. By combining deep learning technology with computer vision, audio processing, multimodal fusion and other technologies, the voice and body movement information of candidate accounts can be extracted from the voice and body movements through steps such as multi-source data acquisition, data preprocessing, single-modal feature extraction, spatiotemporal alignment, multimodal fusion, task reasoning, and feedback system, and used as feedback information.

[0030] For example, taking body movement information as an example, the camera of an electronic device is used to capture the body movements of a candidate account browsing a target video, and features are extracted from the captured body movements. The extracted features are then used to infer the body movement information.

[0031] It should be noted that when obtaining feedback information from the candidate account's voice and body movements, interfering information can also be removed. For example, responding to others, answering phone calls, drinking water, etc. are interfering information. When performing feature extraction, features that are interfering information can be removed, so as to obtain only the voice and body movements of the candidate account in response to the target video.

[0032] S102, based on feedback information, determine the first target video frame from multiple candidate video frames of the target video.

[0033] It should be noted that the feedback information is provided for candidate video frames within the target video; that is, the target video is composed of candidate video frames. The preview video, in turn, is composed of different candidate video frames from the target video.

[0034] In some embodiments, the duration of the preview video can be predetermined, and the target number of the first target video frames can be determined based on the duration, thereby determining the target number of the first target video frames from a plurality of candidate video frames.

[0035] In some embodiments, the feedback information includes, but is not limited to, comment information, emotional information, audio information, and body language information from candidate accounts regarding candidate video frames in the target video. After receiving the feedback information, it can be associated with candidate video frames, and candidate video frames whose number of associated feedback messages reaches a set value can be used as the first target video frames.

[0036] In some embodiments, different filtering rules can be determined based on different types of feedback information to determine whether the feedback information of the candidate video frame meets the filtering rules, thereby selecting the candidate video frame that meets the filtering rules as the first target video frame.

[0037] For example, the first target video frame can be determined based on comment information. A first filtering rule is then determined for the candidate video frames associated with the comment information. If a candidate video frame associated with the comment information satisfies the first filtering rule, that candidate video frame is determined as the first target video frame.

[0038] For example, the first target video frame can be determined based on emotion information. By determining the second filtering rule corresponding to the candidate video frames associated with the emotion information, if there is a candidate video frame that satisfies the second filtering rule, that candidate video frame is determined as the first target video frame.

[0039] For example, the first target video frame can be determined based on sound information and body movement information. By determining the third filtering rule corresponding to the candidate video frames associated with the sound information and body movement information, if there is a candidate video frame that satisfies the third filtering rule, that candidate video frame is determined as the first target video frame.

[0040] For example, a first filtering rule can be determined based on the number of comment messages. The first filtering rule can be that the number of comment messages is greater than a set value. If there are candidate video frames 1, 2, and 3, and the number of comment messages for candidate video frames 1 and 3 is greater than a set value, then the first target video frames are determined to be candidate video frames 1 and 3.

[0041] S103, based on multiple first target video frames, generate a first type of preview video of the target video.

[0042] In some embodiments, the first target video frames can be combined according to their timestamps to obtain a first type of preview video of the target video. The first target video frames are sorted based on their timestamps, and then combined according to the sorting results to obtain the first type of preview video.

[0043] In some embodiments, when generating a first type of preview video, the target number of video frames required for the first type of preview video is predetermined, and the first type of preview video is obtained by combining the first target number of video frames according to the order of their timestamps.

[0044] In other words, the first type of preview video is a preview video generated based on the feedback information of candidate accounts regarding the target video. The first type of preview video can be a preview video with user preferences.

[0045] In some embodiments, a second type of preview video, independent of user preferences, can also be generated based on the target video. Optionally, the second type of preview video can be generated based on the playback sequence of candidate video frames in the target video.

[0046] In some embodiments, a second target video frame can be determined from multiple candidate video frames based on their playback sequence in the target video, and a second type of preview video of the target video can be generated based on the multiple second target video frames. The candidate video frames are played in playback sequence, and the candidate accounts also browse the target video in playback sequence.

[0047] In some embodiments, different generation rules can be determined based on the playback sequence, thereby generating different second-type preview videos according to the generation rules. Optionally, different generation rules can be determined based on the account type of the candidate account; that is, different account types correspond to different generation rules.

[0048] In some embodiments, a second target video frame can be determined from multiple candidate video frames according to generation rules, so as to generate a second type of preview video of the target video based on the second target video frame. Optionally, the second type of preview video can be generated according to the chronological order of the timestamps of the second target video frames.

[0049] It should be noted that different account types correspond to different viewing permissions for candidate video frames. For example, the candidate video frames in the target video include a first set part and a second set part. The first type of account can view the candidate video frames in the first set part, while the second type of account can view all the candidate video frames, that is, the candidate video frames in the first set part and the second set part. In some embodiments, the generation rules may be related to account type and browsing permissions.

[0050] For example, the generation rule could be: the second type of preview video includes n frames, the second target video frame corresponding to the first type of account is n-1 candidate video frames in the first setting part, and 1 candidate video frame in the second setting part; the second target video frame corresponding to the second type of account is n-10 candidate video frames in the first setting part, and 10 candidate video frames in the second setting part.

[0051] For example, taking a TV series as the target video, the first x episodes are free episodes and the last y episodes are paid episodes. The second type of preview video has a length of 60 seconds. For the first type of account, the first 59 seconds are taken from the first candidate video frame of each episode in the first x episodes as the second target video frame, and the last 1 second is taken from a candidate video frame randomly selected from the last y episodes as the second target video frame, thus forming a 60-second second type of preview video.

[0052] For the second type of account, the first 50 seconds are taken from the first candidate video frame of each episode in the first x episodes as the second target video frame, and the next 10 seconds are taken from a candidate video frame randomly selected from the next y episodes as the second target video frame, thus forming a 60-second preview video for the second type of account.

[0053] For example, if the target video is a TV series, a second type of preview video can be generated for each episode of the series. For instance, if the target video has 100 candidate video frames, and these 100 candidate video frames constitute a TV series, including candidate video frame 1 to candidate video frame 100, and the first episode consists of candidate video frames 1 to 20, then a set number of candidate video frames can be randomly selected from candidate video frames 1 to 20 as the second target video frames, thus obtaining the second type of preview video.

[0054] In some embodiments, the candidate video frames can be divided into intervals based on the playback sequence of multiple candidate video frames in the target video, so as to divide the candidate video frames into different video intervals, and determine the second target video frame of the video interval according to the candidate video frames in each video interval, thereby generating a second type of preview video corresponding to each video interval.

[0055] In the preview video generation method provided in this application embodiment, feedback information from candidate accounts regarding the target video is obtained. Based on this feedback information, a first target video frame is determined from multiple candidate video frames of the target video. This allows for the generation of a first type of preview video related to user preferences, increasing the diversity of generated preview videos and making the generated preview videos richer and more personalized, thereby attracting the interest of different users. This application can also generate a second type of preview video according to the playback sequence of video frames, expanding the preview scope of the preview videos. By generating both the first and second types of preview videos, the diversity of preview videos can be improved.

[0056] Based on any of the above embodiments, this application embodiment can further explain how to determine the first target video frame from multiple video frames of the target video based on feedback information. Optionally, the first target video frame can be determined for different feedback information.

[0057] Optionally, in response to feedback information including comment information on candidate video frames, a first target video frame is determined from the candidate video frames based on a first number of comment information. For example, the candidate video frames can be sorted in descending order based on the first number, and the candidate video frames with the highest number of comment information can be selected as the first target video frame. That is, the candidate video frames with more comment information can be selected as the first target video frame.

[0058] Optionally, in response to feedback information including comment information for candidate video frames, the first target video frame can be determined from the candidate video frames based on the second number, by determining the comment type of the comment information and a second number of comment information corresponding to each comment type.

[0059] In some embodiments, for each comment type, a first target video frame can be determined from candidate video frames based on a second number to generate a first type preview video for each comment type based on the first target video frame.

[0060] For example, comment types include emotional expression, plot discussion, atmosphere creation, timeline, and viral comments. Taking emotional expression as an example, a second number of comment information corresponding to emotional expression for each candidate video frame is determined, and the candidate video frames are sorted in descending order based on this second number. The candidate video frames with the highest ranking are then selected as the first target video frames.

[0061] Optionally, in response to feedback information including emotion information for candidate video frames, the emotion level corresponding to the emotion information is determined, and candidate video frames whose emotion levels meet the set conditions are determined as the first target video frames.

[0062] Optionally, the setting condition can be that the emotion level is greater than a set level. That is, the emotion level of the corresponding emotion information of each candidate video frame can be determined in advance based on the emotion information of each candidate video frame, and the candidate video frames with an emotion level greater than the set level can be used as the first target video frames.

[0063] Optionally, in response to feedback information including emotion information for candidate video frames, the emotion type of the emotion information can be determined, and a first target video frame can be determined from the candidate video frames corresponding to each emotion type.

[0064] Optionally, for any given emotion type, a target number of candidate video frames are selected from the candidate video frames corresponding to that emotion type as the first target video frames. For example, if the emotion type is "happiness" and its corresponding candidate video frames are video frames 1-20, and the target number is 10, then 10 candidate video frames can be randomly selected from video frames 1-20 as the first target video frames.

[0065] Optionally, in response to feedback information including audio information and body movement information for candidate video frames, a first target video frame is determined from the candidate video frames corresponding to the audio information and body movement information.

[0066] Optionally, a target number of candidate video frames can be determined from the candidate video frames corresponding to the sound information and body movement information as the first target video frames.

[0067] Figure 2 This is a flowchart of a video preview method provided according to an embodiment of this application, such as... Figure 2 As shown, the video preview method of this application includes, but is not limited to, the following steps: S201, confirm the preview video library.

[0068] It should be noted that the execution subject of the video preview method provided in this application embodiment is an electronic device, which can be a terminal device. Optionally, the terminal device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be personal computers (PCs), televisions, etc. This application embodiment does not impose specific limitations.

[0069] In some embodiments, video application software is installed in the electronic device so that users can log in to the video application software with different accounts and browse the videos in the video application software.

[0070] In some embodiments, the preview video library includes a first type of preview videos of multiple candidate videos, wherein the first type of preview video of any candidate video is generated based on a first target video frame of the corresponding candidate video, and the first target video frame is determined based on feedback information from the candidate account regarding the corresponding candidate video.

[0071] In some embodiments, a preview video library can be generated based on the first type of preview videos in the above embodiments. For specific implementation methods of generating the first type of preview videos, please refer to the above embodiments, which will not be repeated here.

[0072] It should be noted that the candidate video and the target video in this application may be the same or different. The process of determining the first target video frame in this application is explained using the target video as an example. The process of determining the first target video frame of the candidate video frame is the same as the process of determining the first target video frame of the target video, and will not be repeated here.

[0073] S202, Based on the account type of the target account and the video preview operation of the target account, determine the target preview video from the preview video library.

[0074] In some embodiments, for the target account of the preview video to be displayed, the account type of the target account and the video preview operation of the target account can be determined, so as to determine the target preview video from the preview video library based on the account type and the video preview operation.

[0075] In some embodiments, the time-frequency preview operation of the target account refers to the video preview operation of the target account on the candidate videos associated with the preview video library. That is, a first type of preview video is generated in advance based on the candidate videos, and a preview video library is generated based on the first type of preview video. When the target account performs a video preview operation on the candidate videos, the target preview video can be determined from the first type of preview videos in the preview video library.

[0076] In other words, filtering criteria can be determined based on the target account's account type and video preview actions, and target preview videos can be selected from the preview video library according to these criteria. Optionally, since the first type of preview videos in the preview video library is determined by feedback information from candidate users, the filtering criteria for the target account can also be determined in conjunction with the feedback information from the target account.

[0077] In some embodiments, the target account type includes a first type of account and a second type of account. For example, the first type of account can be an unpaid account, and the second type of account can be a paid account. The video preview operation includes a first operation and a second operation. The first operation can be a click operation, and the second operation can be a long press operation.

[0078] In some embodiments, different filtering conditions can be determined for target accounts of different account types, thereby enabling the determination of different target preview videos for different account types. That is, when different account types perform the same video preview operation, the resulting target preview videos may be different. In other words, when the same account type performs different video preview operations, the resulting target preview videos may be different.

[0079] S203, displaying a preview video of the target.

[0080] In some embodiments, after determining the target preview video for the target account, the target preview video can be displayed in the current display interface of the video application software.

[0081] Optionally, the target preview video can be displayed in a designated area of ​​the current display interface, or it can be displayed as a pop-up window on the current display interface.

[0082] Optionally, after selecting the target preview video, you can also jump to other display interfaces to display the target preview video.

[0083] Optionally, the target preview video can be displayed using any video display technology in the relevant field, without any specific limitation here.

[0084] The video preview method provided in this application constructs a preview video library and determines and displays target preview videos from the library based on the target account's account type and video preview operations. This enables personalized recommendation and display of preview videos, and precise matching between target accounts and target preview videos, thereby increasing user interest. Determining different target preview videos through different video preview operations allows for diverse interactive previews, increasing the diversity of user interaction and thus enhancing the diversity and richness of preview video recommendations.

[0085] Based on the above embodiments, the preview video library in this application embodiment also includes a second type of preview video of multiple candidate videos, wherein the second type of preview video of any candidate video is generated based on the second target video frame of the corresponding candidate video, and the second target video frame is determined based on the playback timing of multiple video frames in the candidate video.

[0086] In some embodiments, the specific implementation of generating the second type of preview video can be found in the above embodiments, and will not be repeated here.

[0087] It should be noted that the candidate video and the target video in this application may be the same or different. The process of determining the second target video frame in this application will be explained using the target video as an example. The process of determining the second target video frame of the candidate video frame is the same as that of determining the second target video frame of the target video, and will not be repeated here.

[0088] Figure 3 This is a flowchart of a video preview method provided according to an embodiment of this application, such as... Figure 3 As shown, the video preview method of this application includes, but is not limited to, the following steps: S301, confirm the preview video library.

[0089] In the embodiments of this application, step S301 can be implemented in any of the ways described in the embodiments of this application. This is not limited here and will not be described in detail.

[0090] S302, in response to the target account being a first type of account and the video preview operation including a first operation on candidate videos in the video list, the second type of preview video of the candidate video corresponding to the first operation is taken as the target preview video.

[0091] S303, in response to feedback information from the target account, including target comment information for video frames in the candidate video, the first type of preview video corresponding to the target comment information is selected as the target preview video.

[0092] In some embodiments, the first operation is a click operation, which can be a click on a candidate video or a click on the video list. That is, the target account can click on the video list, and can also click on any candidate video in the video list.

[0093] In some embodiments, when the target account is a first type of account and the video preview operation is the first operation for candidate videos in the video list, or the video preview operation is the first operation for the video list, by determining whether the target account has feedback information for the candidate video, if there is no feedback information, the second type of preview video of the candidate video corresponding to the first operation can be used as the target preview video.

[0094] In other words, the second category of preview videos selected from the preview video library are used as the target preview videos.

[0095] In some embodiments, if the target user provides feedback information, the target comment information can be determined from the feedback information. Since the target comment information is comment information for video frames, the target comment information for video frames in the candidate video can be determined from the feedback information, so as to determine the target preview video based on the target comment information.

[0096] In some embodiments, the first type of preview video is related to the number and type of comment information. The target comment type of the target comment information can be determined, and the first type of preview video with the comment type of the target comment type can be determined from the preview video library as the target preview video.

[0097] It should be noted that the acquisition of feedback information from the target account was done with the user's authorization and in strict compliance with relevant laws and regulations on privacy and security. Furthermore, the acquisition was limited to feedback information and did not involve reading any user privacy information.

[0098] S304, displaying a preview video of the target.

[0099] In the embodiments of this application, step S304 can be implemented in any of the embodiments of this application, and no limitation is made here, nor will it be described in detail.

[0100] In the video preview method provided in this application embodiment, when the target account's account type is a first type of account, and the video preview operation includes a first operation on candidate videos in the video list, a second type of preview video corresponding to the first operation can be used as the target preview video. Furthermore, if the target account's feedback information includes target comment information on video frames in the candidate videos, the first type of preview video corresponding to the target comment information can be used as the target preview video. This allows for determining the target preview video based on account personalization information, account type, and account interaction method, thereby achieving diversified recommendation and display of target preview videos.

[0101] Figure 4 This is a flowchart of a video preview method provided according to an embodiment of this application, such as... Figure 4 As shown, the video preview method of this application includes, but is not limited to, the following steps: S401, confirm the preview video library.

[0102] In the embodiments of this application, step S401 can be implemented in any of the ways described in the embodiments of this application. This is not limited here and will not be described in detail.

[0103] S402, in response to the target account being a second type of account and the video preview operation including a first operation on candidate videos in the video list, receiving a first instruction message for the target account to preview the video.

[0104] In some embodiments, when the target account is a second type of account and the video preview operation includes a first operation on candidate videos in the video list, when the first operation is detected, different preview types can be displayed on the current display interface for the target account to select. After the target account selects a preview type, first instruction information can be generated.

[0105] In other words, the first instruction information includes the target preview type for the video preview, where the preview type is related to the feedback information. Different feedback information corresponds to different preview types. For example, if the feedback information is a comment, the corresponding preview type is the first preview type; if the feedback information is emotional information, the corresponding preview type is the second preview type; and if the feedback information includes both audio and body language, the corresponding preview type is the third preview type.

[0106] S403, Select the first type of preview video that matches the target preview type from the first type of preview videos as the target preview video.

[0107] In some embodiments, the first type of preview video is determined based on feedback information. Therefore, the feedback information of each of the first type of preview videos can be determined, and the preview type of the first type of preview video can be determined according to the correspondence between the feedback information and the preview type. This allows for matching with the target preview type to identify the first type of preview video that matches the target preview type, and this first type of preview video is then used as the target preview video.

[0108] S404, from the second type of preview videos of the candidate videos corresponding to the first operation, determine the second type of preview videos whose playback timing meets the set conditions as the target preview videos.

[0109] It should be noted that different account types have different second-category preview videos for the same candidate video type, and the playback order of the second target video frames in the different second-category preview videos is different.

[0110] Optionally, by obtaining the second type of preview video corresponding to the candidate video of the first operation and determining the playback sequence of the second target video frame in each second type of preview video, if there is a second type of preview video whose playback sequence meets the set conditions, then the second type of preview video is determined to be the target preview video. In some embodiments, it can also be determined whether a first instruction message has been received when the target account's account type is determined to be a second type of account and the video preview operation includes the first operation for the candidate video in the video list. If the first instruction message is received, the target preview video is determined according to the above steps S402-S403. If the first instruction message is not received, the target preview video can be determined using the method of step S404.

[0111] S405, displaying a preview video of the target.

[0112] In the embodiments of this application, step S405 can be implemented in any of the ways described in the various embodiments of this application. This is not limited here and will not be elaborated further.

[0113] In the video preview method provided in this application embodiment, when the target account's account type is a second type of account, and the video preview operation includes a first operation targeting candidate videos in the video list, the method can receive a first instruction information for the target account to preview the video, and determine the first type of preview video matching the target preview type from the first type of preview videos as the target preview video. It can also determine the second type of preview video whose playback sequence meets set conditions from the second type of preview videos corresponding to the first operation as the target preview video. This allows for determining the target preview video based on account personalization information, account type, and account interaction method, thereby achieving diversified recommendation and display of target preview videos.

[0114] Figure 5 This is a schematic diagram of determining the target preview video based on the first operation. Figure 5 The first operation is to click on the video list. If the target account is a type 1 account, the corresponding type 2 preview video in the video list will be played. If the target account is a type 2 account, the target preview type will be selected, and the corresponding type 1 preview video will be played.

[0115] Figure 6 This is a flowchart of a video preview method provided according to an embodiment of this application, such as... Figure 6 As shown, the video preview method of this application includes, but is not limited to, the following steps: S601, confirm the preview video library.

[0116] In the embodiments of this application, step S601 can be implemented in any of the ways described in the various embodiments of this application. This is not limited here and will not be described in detail.

[0117] S602, in response to the target account being a first-class account and the video preview operation including a second operation for candidate videos in the video list, receiving a second instruction message for the target account to preview the video.

[0118] In some embodiments, the second operation can be a long press operation. When the second operation is detected, the current display interface can show whether to select a different number of candidate videos for preview, thereby determining the number of candidate videos for video preview. Optionally, second indication information can be generated based on the selection of the target account; that is, the second indication information is used to instruct at least one candidate video to be selected from the candidate videos for video preview.

[0119] It should be noted that when the second operation is detected, if the target account is a first-type account, a second instruction message is generated; if the target account is a second-type account, a third instruction message is generated. In other words, the second instruction message is used to instruct the first-type account to select at least one candidate video from the candidate videos for video preview.

[0120] The third instruction information is used to instruct the second type of account to select at least one candidate video from the candidate videos for video preview.

[0121] S603, based on the second indication information, at least one candidate video of the second type of preview video is selected as the target preview video.

[0122] In some embodiments, by determining at least one candidate video for video preview from the second indication information, a second type of preview video corresponding to the at least one candidate video can be determined as the target preview video. When the second indication information indicates that a candidate video is to be previewed, the second type of preview video of that candidate video is taken as the target preview video.

[0123] In some embodiments, the second type of preview video can be generated from the second target video frame of a candidate video, or it can be generated from the second target video frames of multiple candidate videos within different video intervals. When the second indication information instructs multiple candidate videos to preview the video, the first video interval to which the multiple candidate videos belong can be determined, so as to determine the second type of preview video corresponding to the first video interval from the second type of preview videos, and use the second type of preview video as the target preview video.

[0124] S604, in response to feedback information from the target account including target comment information for video frames in at least one candidate video, the first type of preview video corresponding to the target comment information is selected as the target preview video.

[0125] In some embodiments, the target preview video can also be determined based on feedback information from the target account. This involves determining whether the target account has target comment information for at least one video frame in a candidate video; if so, the target preview video can be determined based on the target comment information.

[0126] In some embodiments, the first type of preview video is related to the number and type of comment information. The target comment type of the target comment information can be determined, and the first type of preview video with the comment type of the target comment type can be determined from the preview video library as the target preview video.

[0127] S605 displays a preview video of the target.

[0128] In the embodiments of this application, step S605 can be implemented in any of the embodiments of this application, and no limitation is made here, nor will it be described in detail.

[0129] In the video preview method provided in this application embodiment, when the target account's account type is a first-type account and the video preview operation includes a second operation targeting candidate videos in the video list, the method can receive second instruction information from the target account to preview the video, and based on the second instruction information, select at least one candidate video as a second-type preview video. Furthermore, when the target account's feedback information includes target comment information for video frames in at least one candidate video, the first-type preview video corresponding to the target comment feedback information can be selected as the target preview video. This method enables the determination of target preview videos based on account personalization information, account type, and account interaction methods, thereby achieving diversified recommendation and display of target preview videos.

[0130] Figure 7 This is a flowchart of a video preview method provided according to an embodiment of this application, such as... Figure 7 As shown, the video preview method of this application includes, but is not limited to, the following steps: S701, confirm the preview video library.

[0131] In the embodiments of this application, step S701 can be implemented in any of the ways described in the embodiments of this application. This is not limited here and will not be described in detail.

[0132] S702, in response to the target account being a second type of account and the video preview operation including a second operation for candidate videos in the video list, receiving a first instruction and a third instruction for the target account to preview the video.

[0133] In some embodiments, when the target account is a second type of account and the video preview operation includes a second operation on candidate videos in the video list, different preview types can be displayed on the current display interface for the target account to select. After the target account selects a preview type, first instruction information can be generated.

[0134] Optionally, the current display interface can also show whether to select a different number of candidate videos for preview, thereby determining the number of candidate videos for video preview and generating third-party instruction information based on the target account's selection. In other words, the first instruction information is used to indicate the target preview type for video preview; the third instruction information is used to indicate at least one candidate video to be selected from the candidate videos for video preview.

[0135] S703, based on the third indication information, determine the second type of preview video whose playback timing meets the set conditions from at least one candidate video second type of preview video as the target preview video.

[0136] It should be noted that different account types have different second-category preview videos for the same candidate video type. Furthermore, the playback order of the second target video frames differs among the different second-category preview videos. One approach is to first determine the second-category preview videos for at least one candidate video, and then, based on the playback order of the second target video frames, select the second-category preview videos that meet the set conditions as the target preview videos.

[0137] In some embodiments, when the third indication information indicates that there is only one candidate video for video preview, the second type of preview video whose playback timing meets the set conditions is determined from the second type of preview videos of the candidate video as the target preview video.

[0138] In some embodiments, the second type of preview video can be generated from the second target video frame of a candidate video, or it can be generated from the second target video frames of multiple candidate videos within different video intervals. When the third indication information instructs multiple candidate videos to preview the video, the second video interval to which the multiple candidate videos belong can be determined, so as to determine the second type of preview video corresponding to the second video interval from the second type of preview videos, and determine the second type of preview video whose playback timing meets the set conditions from the second type of preview videos corresponding to the second video interval as the target preview video.

[0139] S704, determine the target preview type corresponding to the first instruction information, and select the first type of preview video that matches the target preview type from the first type of preview videos as the target preview video.

[0140] In some embodiments, the first type of preview video is determined based on feedback information. Therefore, the feedback information of each of the first type of preview videos can be determined, and the preview type of the first type of preview video can be determined according to the correspondence between the feedback information and the preview type. This allows for matching with the target preview type to identify the first type of preview video that matches the target preview type, and this first type of preview video is then used as the target preview video.

[0141] S705, displaying a target preview video.

[0142] In the embodiments of this application, step S705 can be implemented in any of the embodiments of this application, and no limitation is made here, nor will it be described in detail.

[0143] In the video preview method provided in this application embodiment, when the target account's account type is a second type of account, and the video preview operation includes a second operation targeting candidate videos in the video list, by receiving first and third instruction information for the target account to preview the video, based on the third instruction information, a second type of preview video whose playback sequence meets a set condition can be determined from at least one candidate second type of preview videos as the target preview video. It can also determine the target preview type corresponding to the first instruction information, and determine a first type of preview video matching the target preview type from the first type of preview videos as the target preview video. This allows for the determination of target preview videos based on account personalization information, account type, and account interaction methods, thereby achieving diversified recommendation and display of target preview videos.

[0144] Figure 8 This is a diagram illustrating the determination of at least one candidate video based on the second operation. Since the method for determining at least one candidate video is the same for both the first and second types of accounts, Figure 8 The target account's account type can be restricted. When the target account performs a second operation on the video list, a dialog box can be displayed on the current screen. The dialog box includes different candidate videos. The target account can select candidate videos from different video ranges or select a single candidate video. Figure 8 The video intervals in the video include video interval 1, video interval 2, and video interval 3.

[0145] Based on any of the above embodiments, the candidate videos in the video list are divided into non-paid videos and paid videos. When a first-type account selects a candidate video for video preview, it cannot select a paid video. If the browsing time of a first-type account meets the set time requirement, a preview type selection can be added for the first-type account, so that the first-type account can experience the target preview video recommendation method of the second-type account.

[0146] It should be noted that when collecting feedback information from the second type of account, it is possible to determine whether the second type of account has the permission to continuously collect the corresponding feedback information when browsing new videos. If the second type of account authorizes the collection of feedback information, the feedback information of the second type of account can be collected and updated so that when the second type of account determines the target preview video based on the feedback information, it can meet the personalized preferences of the second type of account at different times.

[0147] Corresponding to the preview video generation methods proposed in the above embodiments, an embodiment of this application also proposes a preview video generation apparatus. Since the preview video generation apparatus proposed in this application corresponds to the preview video generation methods proposed in the above embodiments, the implementation methods of the above preview video generation methods are also applicable to the preview video generation apparatus proposed in this application, and will not be described in detail in the following embodiments.

[0148] Figure 9 This is a schematic diagram of a preview video generation device provided in an embodiment of this application.

[0149] like Figure 9 As shown, the preview video generation device 900 includes: The acquisition module 901 is used to acquire feedback information from candidate accounts regarding the target video; The determining module 902 is used to determine a first target video frame from multiple candidate video frames of the target video based on the feedback information; The generation module 903 is used to generate a first type of preview video of the target video based on multiple first target video frames.

[0150] In one possible implementation of this application embodiment, the determining module 902 is further configured to: in response to the feedback information including comment information for the candidate video frame, determine the first target video frame from the candidate video frames based on a first number of the comment information; or, determine the comment type of the comment information and a second number of comment information corresponding to each comment type; and determine the first target video frame from the candidate video frames based on the second number.

[0151] In one possible implementation of this application embodiment, the determining module 902 is further configured to: in response to the feedback information including emotion information for the candidate video frame, determine the emotion level corresponding to the emotion information; determine the candidate video frame whose emotion level meets the set conditions as the first target video frame; or, determine the emotion type of the emotion information, and determine the first target video frame from the candidate video frames corresponding to each emotion type.

[0152] In one possible implementation of this application, the determining module 902 is further configured to: determine the first target video frame from the candidate video frames corresponding to the sound information and body movement information in response to the feedback information including sound information and body movement information for the candidate video frames.

[0153] It should be noted that the foregoing explanation of the method for generating preview videos also applies to the apparatus for generating preview videos in this embodiment, and will not be repeated here.

[0154] In the preview video generation apparatus provided in this application embodiment, feedback information from candidate accounts regarding the target video is obtained. Based on this feedback information, a first target video frame is determined from multiple candidate video frames of the target video. This allows for the generation of a first type of preview video related to user preferences, increasing the diversity of generated preview videos and making the generated preview videos richer and more personalized, thereby attracting the interest of different users. This application can also generate a second type of preview video according to the playback sequence of video frames, expanding the preview range of the preview videos. By generating both the first and second types of preview videos, the diversity of preview videos can be improved.

[0155] Corresponding to the video preview methods proposed in the above embodiments, one embodiment of this application also proposes a video preview device. Since the video preview device proposed in this application corresponds to the video preview methods proposed in the above embodiments, the implementation methods of the above video preview methods are also applicable to the video preview device proposed in this application, and will not be described in detail in the following embodiments.

[0156] Figure 10 This is a schematic diagram of the structure of a video preview device provided in an embodiment of this application.

[0157] like Figure 10 As shown, the video preview device 1000 includes: The first determining module 1001 is used to determine the preview video library; wherein, the preview video library includes a first type of preview video of multiple candidate videos, and the first type of preview video of any candidate video is generated based on the first target video frame of the corresponding candidate video, and the first target video frame is determined based on the feedback information of the candidate account for the corresponding candidate video; The second determining module 1002 is used to determine a target preview video from the preview video library based on the account type of the target account and the video preview operation of the target account; The display module 1003 is used to display the target preview video.

[0158] In one possible implementation of this application embodiment, the preview video library further includes a second type of preview video of multiple candidate videos. The second type of preview video of any candidate video is generated based on the second target video frame of the corresponding candidate video. The second target video frame is determined based on the playback sequence of multiple video frames in the candidate video. The second determining module 1002 is further configured to: in response to the target account being a first type of account and the video preview operation including a first operation on a candidate video in the video list, use the second type of preview video of the candidate video corresponding to the first operation as the target preview video; or, in response to the feedback information of the target account including target comment information on video frames in the candidate video, use the first type of preview video corresponding to the target comment information as the target preview video.

[0159] In one possible implementation of this application, the second determining module 1002 is further configured to: in response to the target account being a second type of account and the video preview operation including a first operation for candidate videos in the video list, receive first instruction information for video preview of the target account, wherein the first instruction information includes a target preview type for the video preview, and the preview type is related to feedback information; determine a first type of preview video matching the target preview type from the first type of preview videos as the target preview video; or, determine a second type of preview video whose playback timing meets set conditions from the second type of preview videos of the candidate videos corresponding to the first operation as the target preview video.

[0160] In one possible implementation of this application embodiment, the second determining module 1002 is further configured to: in response to the target account's account type being a first type of account, and the video preview operation including a second operation for candidate videos in the video list, receive second instruction information for the target account to preview the video, the second instruction information being used to instruct at least one candidate video to be determined from the candidate videos for video preview; based on the second instruction information, use the second type preview video of the at least one candidate video as the target preview video; or, in response to the target account's feedback information including target comment information for video frames in the at least one candidate video, use the first type preview video corresponding to the target comment feedback information as... The target preview video is selected as follows: In response to the target account being a second type of account, and the video preview operation including a second operation for candidate videos in the video list, the system receives a first instruction and a third instruction for the target account to preview the video. The third instruction instructs the system to select at least one candidate video from the candidate videos for preview. Based on the third instruction, from the at least one candidate video, a second type of preview video whose playback sequence meets a set condition is selected as the target preview video. Alternatively, the system determines the target preview type corresponding to the first instruction and selects a first type of preview video matching the target preview type from the first type of preview videos as the target preview video.

[0161] It should be noted that the foregoing explanation of the video preview method embodiment also applies to the video preview device of this embodiment, and will not be repeated here.

[0162] The video preview device provided in this application constructs a preview video library and determines and displays target preview videos from the library based on the target account's account type and video preview operation. This enables personalized recommendation and display of preview videos, and precise matching of target accounts and target preview videos, thereby increasing user interest. Determining different target preview videos through different video preview operations allows for diverse interactive previews, increasing the diversity of user interaction and thus enhancing the diversity and richness of preview video recommendations.

[0163] The collection, storage, use, processing, transmission, provision, and application of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0164] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0165] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this application is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0166] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0167] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0168] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0169] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0170] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0171] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0172] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0173] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for generating a preview video, characterized in that, include: Obtain feedback from candidate accounts regarding the target video; Based on the feedback information, a first target video frame is determined from multiple candidate video frames of the target video; A first type of preview video of the target video is generated based on multiple first target video frames.

2. The method according to claim 1, characterized in that, The step of determining the first target video frame from multiple candidate video frames of the target video based on the feedback information includes: In response to the feedback information including comment information for the candidate video frames, the first target video frame is determined from the candidate video frames based on a first number of comments; or, Determine the comment types of the comment information, and the second number of comment information corresponding to each comment type; Based on the second quantity, the first target video frame is determined from the candidate video frames.

3. The method according to claim 1, characterized in that, The step of determining the first target video frame from multiple candidate video frames of the target video based on the feedback information includes: In response to the feedback information, which includes emotion information for the candidate video frame, the emotion level corresponding to the emotion information is determined; Candidate video frames whose emotion levels meet the set conditions are identified and used as the first target video frame; or... The emotion type of the emotion information is determined, and the first target video frame is determined from the candidate video frames corresponding to each emotion type.

4. The method according to claim 1, characterized in that, The step of determining the first target video frame from multiple candidate video frames of the target video based on the feedback information includes: In response to the feedback information, which includes audio information and body movement information for the candidate video frames, the first target video frame is determined from the candidate video frames corresponding to the audio information and body movement information.

5. A video preview method, characterized in that, The method includes: A preview video library is determined; wherein, the preview video library includes a first type of preview video of multiple candidate videos, and the first type of preview video of any candidate video is generated based on the first target video frame of the corresponding candidate video, and the first target video frame is determined based on the feedback information of the candidate account for the corresponding candidate video; Based on the account type of the target account and the video preview operation of the target account, the target preview video is determined from the preview video library; Show the target preview video.

6. The method according to claim 5, characterized in that, The preview video library also includes a second type of preview video of multiple candidate videos. The second type of preview video of any candidate video is generated based on the second target video frame of the corresponding candidate video. The second target video frame is determined based on the playback sequence of multiple video frames in the candidate video. The video preview operation based on the account type and the target account, determining the target preview video from the preview video library, includes: In response to the target account being a first type of account, and the video preview operation including a first operation on candidate videos in the video list, the second type of preview video of the candidate video corresponding to the first operation is taken as the target preview video; or, In response to feedback information from the target account, including target comment information for video frames in the candidate video, the first type of preview video corresponding to the target comment information is selected as the target preview video.

7. The method according to claim 6, characterized in that, The method of determining the target preview video from the preview video library based on the account type and the target account's video preview operation also includes: In response to the target account being a second type of account, and the video preview operation including a first operation for candidate videos in the video list, the system receives a first instruction message for the target account to preview the video, the first instruction message including the target preview type of the video preview, and the preview type being related to the feedback information; From the first type of preview videos, determine the first type of preview video that matches the target preview type as the target preview video; or... From the second type of preview videos of the candidate videos corresponding to the first operation, determine the second type of preview videos whose playback timing meets the set conditions as the target preview videos.

8. The method according to any one of claims 5-7, characterized in that, The method of determining the target preview video from the preview video library based on the account type and the target account's video preview operation also includes: In response to the target account being a first type of account and the video preview operation including a second operation for candidate videos in the video list, the target account is received with second instruction information for video preview, the second instruction information being used to instruct at least one candidate video to be selected from the candidate videos for video preview. Based on the second indication information, the second type of preview video of the at least one candidate video is selected as the target preview video; or... In response to feedback information from the target account, including target comment information for video frames in at least one candidate video, the first type of preview video corresponding to the target comment feedback information is used as the target preview video; In response to the target account being a second type of account, and the video preview operation including a second operation for candidate videos in the video list, the system receives a first instruction and a third instruction for the target account to preview the video. The third instruction is used to instruct at least one candidate video to be selected from the candidate videos for video preview. Based on the third indication information, from at least one candidate video of the second type of preview videos, the second type of preview video whose playback timing meets the set conditions is determined as the target preview video; or... Determine the target preview type corresponding to the first indication information, and select a first type of preview video that matches the target preview type from the first type of preview videos as the target preview video.

9. A device for generating preview videos, characterized in that, include: The acquisition module is used to obtain feedback information from candidate accounts regarding the target video; The determining module is used to determine a first target video frame from multiple candidate video frames of the target video based on the feedback information; The generation module is used to generate a first type of preview video of the target video based on multiple first target video frames.

10. A video preview device, characterized in that, The device includes: The first determining module is used to determine the preview video library; wherein, the preview video library includes a first type of preview video of multiple candidate videos, and the first type of preview video of any candidate video is generated based on the first target video frame of the corresponding candidate video, and the first target video frame is determined based on the feedback information of the candidate account for the corresponding candidate video; The second determining module is used to determine the target preview video from the preview video library based on the account type of the target account and the video preview operation of the target account; The display module is used to display the target preview video.

Images