CN112235641B - Video recommendation method, device, equipment and medium - Google Patents
Video recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN112235641B CN112235641B CN202011099404.2A CN202011099404A CN112235641B CN 112235641 B CN112235641 B CN 112235641B CN 202011099404 A CN202011099404 A CN 202011099404A CN 112235641 B CN112235641 B CN 112235641B
- Authority
- CN
- China
- Prior art keywords
- video
- target
- playing
- target video
- videos
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/462—Content or additional data management, e.g. creating a master electronic program guide from data received from the Internet and a Head-end, controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/8126—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts
- H04N21/8133—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video program
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a video recommendation method, a video recommendation device, video recommendation equipment and a storage medium, and relates to the technical field of multimedia, in particular to the technical field of video understanding. The video recommendation method comprises the following steps: determining a plurality of target video segments in a target video; determining one or more relevant videos for each of the plurality of target video segments; in response to receiving a playing operation of the target video, playing the target video in a playing area; in response to receiving a first operation on the play area, displaying the related video list of at least one target video clip; and in response to receiving a second operation on one of the displayed related videos in the related video list, playing the one of the related videos.
Description
Technical Field
The present disclosure relates to the field of multimedia technologies, and in particular, to a video recommendation method, apparatus, device, and medium.
Background
With the development of video platforms, video is used as an important medium for transmitting information. When watching a video, a user may be confused about a portion of the content in the video. Especially for some popular science videos or videos aiming at spreading knowledge, the content without understanding can seriously affect the viewing experience of the user. For these unsolvable contents, the user can only understand the contents by looking for the data by himself, and continue to watch the contents after knowing, or directly neglect the unknown place, know nothing, and see the entire video, which affects the user experience.
The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, unless otherwise indicated, the problems mentioned in this section should not be considered as having been acknowledged in any prior art.
Disclosure of Invention
According to an aspect of the present disclosure, there is provided a video recommendation method, the method including: determining a plurality of target video segments in a target video; determining one or more relevant videos for each of the plurality of target video segments; in response to receiving the playing operation of the target video, playing the target video in a playing area; in response to receiving a first operation on a playing area, displaying a related video list of at least one target video clip; and in response to receiving a second operation on one of the displayed related videos in the related video list, playing the one of the related videos.
According to another aspect of the present disclosure, there is also provided a video recommendation apparatus, the apparatus including: a first determining unit configured to determine a plurality of target video segments in a target video; a second determining unit configured to determine one or more relevant videos for each of the plurality of target video segments; a first playing unit configured to play a target video in a playing area in response to receiving a playing operation for the target video; a list display unit configured to display a related video list of at least one of the target video clips in response to receiving a first operation on a play area; and a second playing unit configured to play one of the related videos in the displayed related video list in response to receiving a second operation on the one of the related videos.
According to another aspect of the present disclosure, there is also provided an electronic device including: a processor; and a memory storing a program comprising instructions which, when executed by the processor, cause the processor to perform a video recommendation method according to the above.
According to another aspect of the present disclosure, there is also provided a computer-readable storage medium storing a program, the program comprising instructions that, when executed by a processor of an electronic device, cause the electronic device to perform the video recommendation method according to the above.
According to another aspect of the present disclosure, there is also provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the video recommendation method described above.
According to the technical scheme, the multiple target video segments in the target video are screened out, and one or more relevant videos are respectively determined according to the target video segments, so that the multi-step operation of a user on a playing area can be responded to, the relevant videos of the target video segments are played in the playing process of the target video, the user can obtain all-around information relevant to the target video, the user can better understand the video conveniently, and the problem that the user cannot comprehensively understand the video content due to the fact that the relevant video recommendation is carried out on the basis of the whole video in the relevant technology is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the embodiments and, together with the description, serve to explain the exemplary implementations of the embodiments. The illustrated embodiments are for purposes of illustration only and do not limit the scope of the claims. Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements.
1-2 are flow charts illustrating video recommendation methods according to example embodiments;
FIG. 3 is a flowchart illustrating the determination of a plurality of target video segments in a target video in accordance with an illustrative embodiment;
FIG. 4 is a flowchart illustrating the determination of one or more relevant videos for each of a plurality of target video segments in accordance with an illustrative embodiment;
FIG. 5 is a display diagram illustrating a related video list according to an exemplary embodiment;
FIG. 6 is a diagram illustrating a related video being played through a pop-up window according to an example embodiment;
fig. 7 is a block diagram illustrating a video recommendation apparatus according to an exemplary embodiment;
fig. 8 is a block diagram showing an exemplary computing device to which the exemplary embodiments can be applied.
Detailed Description
In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, the timing relationship, or the importance relationship of the elements, and such terms are used only to distinguish one element from another. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, based on the context, they may also refer to different instances.
The terminology used in the description of the various described examples in this disclosure is for the purpose of describing the particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the elements may be one or more. Furthermore, the term "and/or" as used in this disclosure is intended to encompass any and all possible combinations of the listed items.
In the related art, the existing video recommendation method is to perform related video recommendation based on the whole video. Such recommendation methods are not conducive to the user to fully understand the video content, resulting in poor viewing experience of the video.
In order to solve the technical problem, the present disclosure determines a plurality of video segments in a video, and determines related videos of the video segments, so that when an operation of a user is received, a related video list of the corresponding video segment is displayed, and then the related video is played after the user clicks one of the related videos. Therefore, the recommended video directly related to the key content in the video is obtained, so that the content of the video can be more comprehensively understood, and the watching experience of the video is improved.
The video recommendation method of the present disclosure will be further described below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a video recommendation method according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the video recommendation method may include: s101, determining a plurality of target video clips in a target video; step S102, determining one or more related videos of each of a plurality of target video clips; step S103, responding to the received playing operation of the target video, and playing the target video in a playing area; step S104, responding to the first operation of the playing area, and displaying a related video list of at least one target video clip; and step S105, responding to the received second operation of one related video in the displayed related video list, and playing the related video. Therefore, by determining a plurality of target video segments in the target video and one or more videos related to each target video segment, displaying the related video list in response to the operation of the user in the playing process of the videos, and playing the related videos in response to the operation of the user on one of the related videos, the user can know the content of a certain part in the videos in a more targeted manner, and the whole video can be better understood.
According to some embodiments, as shown in fig. 3, the step S101 of determining a plurality of target video segments in the target video may include: step S1011, obtaining the playing information of the target video; step S1012, based on the play information, determines a plurality of target video segments from the target video. Therefore, based on the playing information of the target video, the segments which are much concerned by the user in the target video are selected to be determined as the target video segments, and the target video segments are used for subsequently generating the related video list.
In an example, step S101 may further include segmenting the target video to obtain a plurality of sub-video segments. The playing information of the target video may include, for example and without limitation, a number of times the target video is played and a number of times each of the plurality of sub video clips is repeatedly played. Therefore, the video clips which are most interesting, least understandable and most frequently watched repeatedly by the user in the video can be determined based on the playing information, and the video clips are determined as the target video clips.
According to some embodiments, as shown in fig. 2, the video recommendation method may further include: step S201, determining video information of each target video segment.
The video information may include, for example, a video category and a video tag. The video category may be, for example, a science popularization category, a knowledge category, a variety program category, a music program category, a movie category, and the like. The video tags may include, for example, keywords and feature words of the video segments, and may also include other tags added by human, such as recommendation scores, etc., which are not limited herein. In an example, a mapping relationship between video segments may be established based on corresponding video information, so that a video segment related to a certain video segment can be obtained.
After determining the video information of each of the plurality of target video segments in the target video, step S102 of determining one or more relevant videos of each of the plurality of target video segments may be performed.
According to some embodiments, as shown in fig. 4, step S102 may comprise: step S1021, a first database is established, wherein the first database comprises a plurality of candidate video clips and video information of each candidate video clip; step S1022, one or more relevant video segments of each target video segment are obtained from the first database based on the relevance of the corresponding video information. Therefore, by establishing the first database comprising a plurality of candidate video clips and video information thereof, the mapping relation between the target video clip and the candidate video clips in the first database can be established based on the correlation degree of the video information, so as to obtain one or more related video clips of the target video clip.
According to some embodiments, the video recommendation method may further include: acquiring a plurality of preset videos and playing information of each preset video from a video database according to preset rules; and establishing a second database based on the plurality of preset videos. Wherein the target video may be a video in the second database. Therefore, by establishing the second database, videos which are interesting to the user but are not easy to understand can be selected as target videos in a more targeted mode, and videos with low recommendation value are filtered out.
The preset video may be, for example, a video obtained from a video database based on the category and playback information of the video. The preset video may include, for example, videos of popular science class and knowledge class, and the playing amount exceeds a set threshold. The videos have certain audience areas, and segments which are not understood by the user easily appear in the videos, so that the videos are placed into a second database as preset videos, and the videos relevant to the video segments are recommended by determining, so that the user can be helped to better understand the video content. The preset video may also include videos of art programs, music programs, movies, and the like, for example, and the playing amount exceeds a set threshold. Such video audiences are wide and some of them may be of interest to the user, as well as elements appearing in the video segments, such as a star appearing in an art program, a track and/or a singer thereof in a music program, a plot of a movie and an appearing actor, etc. By placing such videos as preset videos in the second database, the user can be allowed to recommend videos related to elements (such as stars, singers, songs, and the like) of interest to the user when the video views the elements, so that the video viewing experience of the user is improved.
It should be understood that the above is only an example of how to determine the preset video according to the category and the playing information of the video, and the preset video may also be obtained from the video database by using other video categories, playing information, or a combination of the two.
According to some embodiments, the step S1021 of establishing the first database may include: determining at least one candidate video clip in each preset video in the second database based on the corresponding playing information; the first database is established based on a plurality of candidate video segments of a plurality of preset videos. Therefore, the first database can include each candidate video clip of each preset video in the second database, and the richness of the first database is guaranteed. In addition, the candidate video clips may be determined based on the playing information, so that the candidate video clips have a high probability of being clips watched by more users and watched repeatedly, and the quality of the first database is guaranteed, that is, the recommendation performance is high. Meanwhile, the time for building the first database based on the second database can be shortened compared to building the second database based on all videos in the video database.
According to some embodiments, determining at least one candidate video segment for each preset video in the second database may include: the method comprises the steps of inputting a preset video into a video understanding model, and obtaining at least one candidate video segment of the preset video output by the video understanding model and video information of each candidate video segment. Therefore, the candidate video segments included in the preset video and the video information of each candidate video segment can be rapidly acquired through the neural network model, so that the speed of video segmentation and video segment content understanding is increased, and the efficiency of generating at least one related video list corresponding to the candidate video segments for the preset video is improved. It should be noted that, it is not limited herein that at least one candidate video segment of the preset video can be obtained by using the video understanding model only to obtain the video information thereof.
The video understanding model may be, for example, a propeller ERNIE model or a convolutional neural network.
According to some embodiments, the training process of the video understanding model may include: acquiring a sample video, and marking at least one real candidate video clip and video information of each real candidate video clip in the sample video based on corresponding playing information; inputting the sample video into a video understanding model, and outputting at least one prediction candidate video segment of the sample video and video information of each prediction candidate video segment; calculating a loss value between at least one predicted candidate video segment and video information thereof and at least one real candidate video segment and video information thereof by using a loss function; and adjusting parameters of the video understanding model based on the loss value. Iteration can be carried out until the calculated loss value meets the requirement, and the training of the video understanding model is completed.
According to some embodiments, for example, one or more candidate video segments with a correlation degree higher than a preset value with each target video segment may be obtained from the first database as the relevant video of the target video segment, and one or more candidate video segments with the highest correlation degree may also be obtained as the relevant video of the target video segment. The relevancy can be determined through video information, for example, the relevancy of two video segments with the same video category and the same video tag semantics can be defined to be the highest, and the relevancy of two video segments with the same video category and the same video tag semantics can be defined to be the high; for two video segments with the same video category, the semantic similarity of the video labels can be quantified, and the correlation degree between the two video segments can be obtained based on the semantic similarity. It is to be understood that the above description is only an example of how to obtain one or more relevant video segments of each target video segment from the first database based on the relevance of the corresponding video information, and the relevance may be defined in other ways and/or obtained based on the relevance in other ways, which is not limited herein.
According to some embodiments, building the second database based on the plurality of preset videos may further include: obtaining one or more related candidate video clips of each candidate video clip from a first database; and storing the mapping relation between each preset video and at least one candidate video segment and the mapping relation between each candidate video segment and one or more related candidate video segments. Therefore, by storing the mapping relationship between the preset video and the candidate video segments and the mapping relationship between the candidate segment video and the related candidate video segments in the second database, when the target video to be played is a video in the second database, the target video segments (i.e. the candidate video segments) of the target video and one or more related video segments (i.e. related candidate video segments) of each target video segment can be directly acquired from the second data based on the mapping relationship, and then the related video list of each target video segment in the target video can be quickly generated.
In the above technical solution, a first database and a second database are established, the first database is established based on a preset video in the second database, then a relevant video segment of each candidate video segment in the first database is determined, and a mapping relationship between a previous video and the candidate video segment and a mapping relationship between each candidate video segment and the relevant video segment are added in the first database. Therefore, when the target video in the second database is played, the plurality of target video segments in the target video and one or more related videos of each of the plurality of target video segments can be directly obtained. And then when the target video is played, quickly displaying the target video clip and the corresponding related video list. In addition, a new preset video can be added into the second database, and the video clip in the first database can be updated based on the updated new video in the second database.
After determining one or more related videos of each of a plurality of target video clips of the target video, when the target video is played in the playing area in response to receiving a playing operation of the target video, the target video clip and the corresponding related video list can be displayed in response to a user operation.
According to some embodiments, as shown in fig. 5, the play area 1001 may include a progress bar 1002 indicating a progress of playing of the target video, which may include a sub-progress bar 1003 playing each of the target video clips. In addition, the sub-progress bar corresponding to each of the plurality of target video clips may be highlighted. Thus, a target video segment with an associated video list 1004 in the target video may be indicated by the sub-progress bar.
According to some embodiments, the first operation may be clicking on the corresponding sub-progress bar 1003 of the target video clip. That is, when a click operation on the corresponding sub-progress bar is received, the related video list 1004 of the target video clip is displayed. The first operation may be a single click operation, a double click operation, a long press operation, or the like, and is not limited herein. The user may perform a first operation on a corresponding sub-progress bar of any one of the target video clips, and in response to receiving the first operation, display an associated video list 1004 of the target video clip.
According to some embodiments, as shown in fig. 5, displaying the relevant video list 1004 of the target video clip may include, for example: inserting a blank frame with a cropping head pointing to the sub progress bar above the corresponding sub progress bar tightly attached to the target video clip; one or more related videos 1005 of the target video segment are displayed within the blank frame. Accordingly, through the display manner of the related video list, when the user views the target video segment, the corresponding one or more related videos 1005 can be clearly displayed.
According to some embodiments, the second operation may be clicking on one of the related videos 1005 in the related video list 1004. That is, in response to receiving a click operation on one of the related videos 1005 in the related video list 1004, the related video is played. The second operation may be a single-click operation, a double-click operation, a long-press operation, or the like, and is not limited herein. The user may perform a second operation on any one of the related videos in the related video list 1004 and, in response to receiving the second operation, play the related video.
According to some embodiments, step S105 may be that in response to receiving the second operation on one of the related videos in the displayed related video list, the playing of the target video may be paused, and the one of the related videos may be played through a popup. Therefore, by using the popup window playing mode, the watching interface of the target video, including the watching information of the target video, can be kept, after returning, watching can be continued from the pause, the continuity of video watching is ensured, and the watching experience of the video is improved. As shown in fig. 6, playing the related video through the pop-up window may include, for example: a popup 1011 is generated in the play area 1001 as a pop-up animation; after the pop-up animation is finished, the related video is played in the pop-up window 1011.
According to some embodiments, as shown in fig. 2, the video recommendation method may further include: and step S106, responding to the received closing operation of the played related video, and continuing to play the target video. Therefore, the regression target video is closed and operated, and the target video is continuously played from the pause position, so that the recommended video is smoothly linked with the target video which is continuously watched, and the watching experience of the video is improved.
As shown in fig. 6, the closing operation for the played related video may be, for example, clicking a closing button 1012 at the upper right corner of the pop-up window, or clicking a playing area 1001 of the target video outside the pop-up window, which is not limited herein. Resuming playing the target video may be, for example, resuming playing the target video from a pause in the target video.
It is to be understood that the above description is provided by way of an exemplary embodiment to illustrate, without limitation, how to display a list of related videos, play the related videos, and close the related videos and continue to play the target video in response to receiving a multi-step operation by a user.
According to another aspect of the present disclosure, a video recommendation device is also provided. As shown in fig. 7, the video recommendation apparatus 100 may include: a first determining unit 101 configured to determine a plurality of target video segments in a target video; a second determining unit 102 configured to determine one or more relevant videos for each of the plurality of target video segments; a first playing unit 103 configured to play a target video in a playing area in response to receiving a playing operation for the target video; a list display unit 104 configured to display a related video list of at least one of the target video clips in response to receiving a first operation on a play area; and a second playing unit 105 configured to play one of the displayed related videos in response to receiving a second operation on the one of the related videos.
According to some embodiments, the first playing unit 103 may be further configured to continue playing the target video in response to receiving a closing operation for the played one of the related videos.
Here, the operations of the above-mentioned units 101-105 of the video recommendation device 100 are similar to the operations of the steps S101-S106 described above, and are not described herein again.
According to another aspect of the present disclosure, there is also provided an electronic device, which may include: a processor; and a memory storing a program comprising instructions which, when executed by the processor, cause the processor to perform a video recommendation method according to the above.
According to another aspect of the present disclosure, there is also provided a computer-readable storage medium storing a program, the program comprising instructions that, when executed by a processor of an electronic device, cause the electronic device to perform the video recommendation method according to the above.
Referring to fig. 8, a computing device 2000, which is an example of a hardware device (electronic device) that may be applied to aspects of the present disclosure, will now be described. Computing device 2000 may be any machine configured to perform processing and/or computing, and may be, but is not limited to, a workstation, a server, a desktop computer, a laptop computer, a tablet computer, a personal digital assistant, a robot, a smartphone, an in-vehicle computer, or any combination thereof. The video recommendation methods described above may be implemented in whole or at least in part by computing device 2000 or a similar device or system.
The computing device 2000 may also include a working memory 2014, which may be any type of working memory that can store programs (including instructions) and/or data useful for the operation of the processor 2004, and may include, but is not limited to, random access memory and/or read only memory devices.
Software elements (programs) may be located in the working memory 2014 including, but not limited to, an operating system 2016, one or more application programs 2018, drivers, and/or other data and code. Instructions for performing the above-described methods and steps may be included in the one or more applications 2018, and the above-described video recommendation methods may be implemented by the instructions of the one or more applications 2018 being read and executed by the processor 2004. More specifically, in the above-described video recommendation method, steps S101 to S106 may be implemented, for example, by the processor 2004 executing the application 2018 having the instructions of steps S101 to S106. Further, other steps in the video recommendation method described above may be implemented, for example, by the processor 2004 executing an application 2018 having instructions to perform the respective steps. Executable code or source code of instructions of the software elements (programs) may be stored in a non-transitory computer-readable storage medium (such as the storage device 2010 described above) and, upon execution, may be stored in the working memory 2014 (possibly compiled and/or installed). Executable code or source code for the instructions of the software elements (programs) may also be downloaded from a remote location.
It will also be appreciated that various modifications may be made in accordance with specific requirements. For example, customized hardware might also be used and/or particular elements might be implemented in hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. For example, some or all of the disclosed methods and apparatus may be implemented by programming hardware (e.g., programmable logic circuitry including Field Programmable Gate Arrays (FPGAs) and/or Programmable Logic Arrays (PLAs)) in an assembly language or hardware programming language such as VERILOG, VHDL, C + +, using logic and algorithms according to the present disclosure.
It should also be understood that the foregoing method may be implemented in a server-client mode. For example, a client may receive data input by a user and send the data to a server. The client may also receive data input by the user, perform part of the processing in the foregoing method, and transmit the data obtained by the processing to the server. The server may receive data from the client and perform the aforementioned method or another part of the aforementioned method and return the results of the execution to the client. The client may receive the results of the execution of the method from the server and may present them to the user, for example, through an output device.
It should also be understood that the components of computing device 2000 may be distributed across a network. For example, some processes may be performed using one processor while other processes may be performed by another processor that is remote from the one processor. Other components of the computing system 2000 may also be similarly distributed. As such, the computing device 2000 may be interpreted as a distributed computing system that performs processing at multiple locations.
Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the above-described methods, systems and apparatus are merely exemplary embodiments or examples and that the scope of the present invention is not limited by these embodiments or examples, but only by the claims as issued and their equivalents. Various elements in the embodiments or examples may be omitted or may be replaced with equivalents thereof. Further, the steps may be performed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced with equivalent elements that appear after the present disclosure.
Claims (18)
1. A video recommendation method, comprising:
determining a plurality of target video segments in a target video;
determining one or more relevant videos for each of the plurality of target video segments;
in response to receiving a play operation of the target video, playing the target video in a play area, wherein the play area comprises a progress bar indicating a play progress of the target video, and the progress bar comprises a highlighted sub-progress bar corresponding to each of the plurality of target video segments;
in response to receiving a first operation on the playing area, displaying a related video list of one target video clip of the plurality of target video clips, wherein the first operation is clicking a sub progress bar corresponding to the one target video clip; and
and in response to receiving a second operation on one of the displayed related videos in the related video list, playing the one of the related videos.
2. The video recommendation method of claim 1, wherein in response to receiving a second operation on one of the displayed related videos in the related video list, pausing the playing of the target video and playing the one of the related videos through a popup window.
3. The video recommendation method of claim 1, further comprising:
and in response to receiving the closing operation of the played related video, continuing to play the target video.
4. The video recommendation method of any of claims 1-3, wherein determining a plurality of target video segments in a target video comprises:
acquiring the playing information of the target video;
determining the plurality of target video clips from a target video based on the playing information.
5. The video recommendation method of claim 4, wherein determining a plurality of target video segments in a target video further comprises:
segmenting the target video to obtain a plurality of sub-video segments,
wherein the playing information includes the playing times of the target video and the repeated playing times of each of the plurality of sub-video segments.
6. The video recommendation method of any of claims 1-3, further comprising:
determining video information for each of the target video segments,
wherein determining one or more relevant videos for each of the plurality of target video segments comprises:
establishing a first database, wherein the first database comprises a plurality of candidate video clips and video information of each candidate video clip;
and acquiring one or more related video clips of each target video clip from the first database based on the correlation degree of the corresponding video information.
7. The video recommendation method of claim 6, wherein the video information comprises a video category and a video tag.
8. The video recommendation method of claim 6, further comprising:
acquiring a plurality of preset videos and playing information of each preset video from a video database according to preset rules;
and establishing a second database based on the plurality of preset videos, wherein the target video is a video in the second database.
9. The video recommendation method of claim 8, wherein the plurality of preset videos are obtained from a video database based on the category and playing information of the videos.
10. The video recommendation method of claim 8, wherein establishing a first database comprises:
determining at least one candidate video clip in each preset video in the second database based on corresponding playing information;
establishing the first database based on a plurality of candidate video clips of the plurality of preset videos.
11. The video recommendation method of claim 10, wherein building a second database further comprises:
obtaining one or more relevant candidate video segments for each of the candidate video segments from the first database;
and storing the mapping relation between each preset video and at least one candidate video segment and the mapping relation between each candidate video segment and one or more related candidate video segments.
12. The video recommendation method of claim 10, wherein determining at least one candidate video segment for each of the predetermined videos in the second database comprises:
inputting the preset video into a video understanding model, and acquiring at least one candidate video segment in the preset video output by the video understanding model and video information of each candidate video segment.
13. The video recommendation method of claim 12, wherein the training process of the video understanding model comprises:
acquiring a sample video, and marking at least one real candidate video clip and video information of each real candidate video clip in the sample video based on corresponding playing information;
inputting the sample video into a video understanding model, and outputting at least one prediction candidate video segment of the sample video and video information of each prediction candidate video segment;
calculating a loss value between the at least one predicted candidate video segment and its video information and the at least one true candidate video segment and its video information using a loss function; and
adjusting parameters of the video understanding model based on the loss value.
14. The video recommendation method of any of claims 1-3, wherein the second operation is clicking on one of the related videos in the related video list.
15. A video recommendation apparatus comprising:
a first determining unit configured to determine a plurality of target video segments in a target video;
a second determining unit configured to determine one or more related videos of each of the plurality of target video segments;
a first playing unit configured to play the target video in a playing area in response to receiving a playing operation on the target video, wherein the playing area includes a progress bar indicating a playing progress of the target video, and the progress bar includes a highlighted sub-progress bar corresponding to each of the plurality of target video clips;
a list display unit configured to display a video list related to one of the target video clips in response to receiving a first operation on the play area, wherein the first operation is clicking a sub progress bar corresponding to the one of the target video clips; and
a second playing unit configured to play one of the related videos in the displayed related video list in response to receiving a second operation on the one of the related videos.
16. The video recommendation device of claim 15, wherein the first playing unit is further configured to continue playing the target video in response to receiving a closing operation of the played one of the related videos.
17. An electronic device, comprising:
a processor; and
a memory storing a program comprising instructions that, when executed by the processor, cause the processor to perform the video recommendation method of any of claims 1-14.
18. A computer readable storage medium storing a program, the program comprising instructions that when executed by a processor of an electronic device cause the electronic device to perform the video recommendation method of any of claims 1-14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011099404.2A CN112235641B (en) | 2020-10-14 | 2020-10-14 | Video recommendation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011099404.2A CN112235641B (en) | 2020-10-14 | 2020-10-14 | Video recommendation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112235641A CN112235641A (en) | 2021-01-15 |
| CN112235641B true CN112235641B (en) | 2022-09-16 |
Family
ID=74112839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011099404.2A Active CN112235641B (en) | 2020-10-14 | 2020-10-14 | Video recommendation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112235641B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113127683A (en) * | 2021-04-22 | 2021-07-16 | 北京百度网讯科技有限公司 | Content recommendation method and device, electronic equipment and medium |
| CN113536033A (en) * | 2021-07-12 | 2021-10-22 | 深圳康佳电子科技有限公司 | Multimedia resource recommendation method and related equipment |
| CN114443897A (en) * | 2022-02-10 | 2022-05-06 | 北京字跳网络技术有限公司 | Video recommendation method and device, electronic equipment and storage medium |
| CN114449331B (en) * | 2022-02-16 | 2023-11-21 | 北京字跳网络技术有限公司 | Video display method and device, electronic equipment and storage medium |
| CN114640868A (en) * | 2022-03-11 | 2022-06-17 | 湖南快乐阳光互动娱乐传媒有限公司 | Video drainage method and related equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823870A (en) * | 2014-02-26 | 2014-05-28 | 联想(北京)有限公司 | Information processing method and electronic device |
| KR20150048961A (en) * | 2013-10-28 | 2015-05-08 | 에스케이플래닛 주식회사 | System for servicing hot scene, method of servicing hot scene and apparatus for the same |
| CN105872713A (en) * | 2016-04-22 | 2016-08-17 | 腾讯科技（北京）有限公司 | Method and device for presenting additional media information |
| US10257547B1 (en) * | 2018-06-29 | 2019-04-09 | Rovi Guides, Inc. | Systems and methods for altering a progress bar to prevent spoilers in a media asset |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107666623A (en) * | 2017-03-07 | 2018-02-06 | 腾讯科技（深圳）有限公司 | The methods of exhibiting and device of broadcast information |
| CN110248236B (en) * | 2019-07-02 | 2022-02-18 | 广州酷狗计算机科技有限公司 | Video playing method, device, terminal and storage medium |
| CN111143610B (en) * | 2019-12-30 | 2021-03-02 | 腾讯科技（深圳）有限公司 | Content recommendation method and device, electronic equipment and storage medium |
-
2020
- 2020-10-14 CN CN202011099404.2A patent/CN112235641B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150048961A (en) * | 2013-10-28 | 2015-05-08 | 에스케이플래닛 주식회사 | System for servicing hot scene, method of servicing hot scene and apparatus for the same |
| CN103823870A (en) * | 2014-02-26 | 2014-05-28 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN105872713A (en) * | 2016-04-22 | 2016-08-17 | 腾讯科技（北京）有限公司 | Method and device for presenting additional media information |
| US10257547B1 (en) * | 2018-06-29 | 2019-04-09 | Rovi Guides, Inc. | Systems and methods for altering a progress bar to prevent spoilers in a media asset |
Non-Patent Citations (1)
| Title |
|---|
| 视频节目层次化搜索和推荐方法的研究;张等;《计算机技术与发展》;20180307(第07期);第171-174页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112235641A (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112235641B (en) | Video recommendation method, device, equipment and medium | |
| US10223466B2 (en) | Method for searching and device thereof | |
| US10115433B2 (en) | Section identification in video content | |
| CN106649780B (en) | Information providing method and device based on artificial intelligence | |
| JP2021516398A (en) | Music recommendation methods, equipment, computing equipment and media | |
| US11741072B2 (en) | Method and apparatus for real-time interactive recommendation | |
| JP2018085754A (en) | Method and system for extracting and providing highlight video of moving picture content | |
| JP2019003604A (en) | Methods, systems and programs for content curation in video-based communications | |
| CN104782138A (en) | Identifying a thumbnail image to represent a video | |
| US20160062625A1 (en) | Computing device and method for classifying and displaying icons | |
| JP7056359B2 (en) | Methods, systems and programs for topic guidance in video content using sequence pattern mining | |
| JP2021168117A (en) | Video clip search method and device | |
| JP2015162244A (en) | Methods, programs and computation processing systems for ranking spoken words | |
| US20160170584A1 (en) | Device and method for arranging contents displayed on screen | |
| US20220237249A1 (en) | Method for searching and device thereof | |
| KR102087807B1 (en) | Character inputting method and apparatus | |
| CN113392237A (en) | Classified label display method, server and display equipment | |
| US10275341B2 (en) | Mobile application usability testing | |
| EP3414680A1 (en) | Text digest generation for searching multiple video streams | |
| Wang et al. | Similarity-based visualization of large image collections | |
| US20180151178A1 (en) | Interactive question-answering apparatus and method thereof | |
| CN109255070B (en) | Recommendation information processing method and device, computer equipment and storage medium | |
| KR102551343B1 (en) | Electric apparatus and method for control thereof | |
| CN104661093A (en) | Method and system for determining updates for a video tutorial | |
| WO2017011084A1 (en) | System and method for interaction between touch points on a graphical display |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |