CN112565904A

CN112565904A - Video clip pushing method, device, server and storage medium

Info

Publication number: CN112565904A
Application number: CN202011379353.9A
Authority: CN
Inventors: 相国强
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-11-30
Filing date: 2020-11-30
Publication date: 2021-03-26
Anticipated expiration: 2040-11-30
Also published as: CN112565904B

Abstract

The disclosure relates to a video clip pushing method, a device, a server and a storage medium, belonging to the technical field of video pushing, wherein the method comprises the following steps: the method comprises the steps of pushing at least one first video clip, determining a target interaction behavior based on the interaction behavior of the at least one first video clip after being pushed, updating a first weight parameter of the target interaction behavior to obtain an updated second weight parameter, and pushing the video clip based on the second weight parameter. In the embodiment of the disclosure, according to the real interactive behavior after pushing, the interactive behavior capable of truly measuring the wonderful degree of the video clip is determined, so that the priority of the weight parameter of the target interactive behavior is improved, and then pushing is performed based on the updated weight parameter, so that the problem of low accuracy of determining the video clip due to unreasonable weight parameter design can be avoided, the accuracy of determining the video clip is improved, and meanwhile, the accuracy of pushing the video clip is improved.

Description

Video clip pushing method, device, server and storage medium

Technical Field

The present disclosure relates to the field of video push technologies, and in particular, to a method, an apparatus, a server, and a storage medium for pushing a video clip.

Background

In the field of short video push, a highlight video segment in a video is often pushed to attract the user to watch. Currently, when a video clip is pushed, the highlight video clip is usually pushed according to the interaction condition between a user and a video. However, the highlight video clip is pushed only by the above interaction situation, so that the accuracy of the video clip pushing is low.

Disclosure of Invention

The present disclosure provides a video clip pushing method, apparatus, server, and storage medium, which improve accuracy of determining a video clip and improve accuracy of pushing the video clip. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a video clip pushing method, including:

pushing at least one first video clip, wherein the first video clip is determined based on a video to which the first video clip belongs and a first weight parameter of an interaction behavior, and the first weight parameter is used for representing the influence degree of the corresponding interaction behavior on the determination of the pushed video clip;

determining a target interaction behavior based on the interaction behavior obtained after the at least one first video segment is pushed;

updating a first weight parameter of the target interaction behavior to obtain an updated second weight parameter, wherein the priority of the second weight parameter is higher than that of the first weight parameter;

and determining a video clip to be pushed based on the second weight parameter, and pushing the determined video clip.

In some embodiments, the expected interaction effect corresponding to the target interaction behavior coincides with an actual interaction effect, and the actual interaction effect is determined based on the interaction behavior obtained after the pushing.

In some embodiments, the determining the target interaction behavior based on the interaction behavior of the at least one first video segment after the pushing comprises:

determining at least one second video segment of which the pushed interaction behavior meets a first condition based on the interaction behavior obtained after the pushing of the at least one first video segment;

and determining a target interaction behavior based on the interaction behavior of the at least one second video segment after being pushed.

In some embodiments, the determining, based on the interaction behavior of the at least one first video segment after pushing, at least one second video segment whose interaction behavior after pushing satisfies the first condition includes:

for any one of the at least one first video segment, if the number of the interaction behaviors of the any one first video segment after being pushed is greater than a first threshold, determining that the any one first video segment is a second video segment meeting a first condition.

In some embodiments, after the pushing of the at least one first video segment, the method further comprises:

acquiring a first interaction quantity sequence of the at least one first video segment after being pushed and a second interaction quantity sequence of the at least one first video segment before being pushed, wherein the first interaction quantity sequence is used for representing an actual interaction effect of the pushed interaction behavior, and the second interaction quantity sequence is used for representing an expected interaction effect of the interaction behavior before being pushed;

determining the pushing accuracy of the at least one first video segment based on the first interaction quantity ordering and the second interaction quantity ordering of the at least one first video segment, wherein the pushing accuracy is used for representing the accuracy degree of the at least one first video segment meeting the pushing condition;

determining at least one second video segment of the at least one first video segment that satisfies a first condition based on the push precision of the at least one first video segment.

if the first interaction quantity sequence is different from the second interaction quantity sequence, determining other interaction behaviors matched with the first interaction quantity sequence as the target interaction behaviors based on a third interaction quantity sequence of other interaction behaviors of the at least one first video clip before pushing except the interaction behaviors, wherein the third interaction quantity sequence is used for expressing expected interaction effects of the other interaction behaviors before pushing.

acquiring a first interaction quantity sequence of the at least one first video clip after being pushed and a sequence of a plurality of interaction behaviors of the at least one first video clip before being pushed, wherein the first interaction quantity sequence is used for representing an actual interaction effect of the pushed interaction behaviors, and the sequence of the plurality of interaction behaviors is used for representing an expected interaction effect of the plurality of interaction behaviors before being pushed;

determining the sequence matched with the first interaction quantity sequence in the sequences corresponding to the multiple interaction behaviors;

and taking the interaction behavior corresponding to the sequencing as the target interaction behavior.

In some embodiments, the pushing of the at least one first video segment comprises:

within a first pushing range, pushing at least one first video clip;

the pushing the determined video segment comprises:

and pushing the determined video clip within a second pushing range, wherein the second pushing range is larger than the first pushing range.

for any one of the at least one first video segment, determining a video sub-segment of which the pushed interactive behavior meets a second condition based on the pushed interactive behavior of the any one first video segment;

extracting the video sub-segment from any one of the first video segments;

and pushing the video sub-segment.

In some embodiments, the determining, based on the interaction behavior of any one of the first video segments after being pushed, the video sub-segment whose interaction behavior after being pushed satisfies the second condition includes:

determining the number of the interactive behaviors in a plurality of time periods in any one first video clip based on the interactive behaviors of the any one first video clip after being pushed;

determining a first time period in which the number of the interactive behaviors is continuously larger than a second threshold value based on the number of the interactive behaviors in the plurality of time periods, and taking a video sub-segment corresponding to the first time period as the video sub-segment meeting a second condition;

the extracting the video sub-segment from any one of the first video segments comprises:

the video sub-segment is extracted from the any one of the first video segments based on the start time stamp and the end time stamp of the first time segment.

and determining a second time period in which the increase amplitude of the number of the interactive behaviors is larger than a third threshold value based on the number of the interactive behaviors in the plurality of time periods, and taking the video sub-segment corresponding to the second time period as the video sub-segment meeting a second condition.

According to a second aspect of the embodiments of the present disclosure, there is provided a video clip pushing apparatus, including:

the pushing unit is configured to perform pushing on at least one first video segment, the first video segment is determined based on a video to which the first video segment belongs and a first weight parameter of an interaction behavior, and the first weight parameter is used for representing the influence degree of the corresponding interaction behavior on the determination of the pushed video segment;

the determining unit is configured to execute the step of determining a target interaction behavior based on the interaction behavior obtained after the pushing of the at least one first video segment;

the updating unit is configured to update the first weight parameter of the target interaction behavior to obtain an updated second weight parameter, and the priority of the second weight parameter is higher than that of the first weight parameter;

the pushing unit is further configured to determine a video segment to be pushed based on the second weight parameter, and push the determined video segment.

In some embodiments, the determining unit includes:

the first determining subunit is configured to execute at least one second video segment, wherein the interaction behavior obtained after the pushing of the at least one first video segment is based on, and the interaction behavior after the pushing meets a first condition;

and the second determining subunit is configured to perform target interactive behavior determination based on the interactive behavior of the at least one second video segment after being pushed.

In some embodiments, the first determining subunit is configured to, for any one of the at least one first video segment, determine that the any one first video segment is a second video segment that satisfies a first condition if the number of the interactive behaviors of the any one first video segment after being pushed is greater than a first threshold.

In some embodiments, the apparatus further comprises:

the acquisition unit is configured to perform acquisition of a first interaction quantity sequence of the at least one first video segment after being pushed and a second interaction quantity sequence of the at least one first video segment before being pushed, wherein the first interaction quantity sequence is used for representing an actual interaction effect of the interaction behavior after being pushed, and the second interaction quantity sequence is used for representing an expected interaction effect of the interaction behavior before being pushed;

an accuracy determining unit configured to perform a first interaction number ordering and a second interaction number ordering based on the at least one first video segment, and determine a push accuracy of the at least one first video segment, the push accuracy being used for representing an accuracy degree of the at least one first video segment meeting a push condition;

a second video segment determination unit configured to perform determining at least one second video segment of the at least one first video segment that satisfies a first condition based on a push precision of the at least one first video segment.

In some embodiments, the determining unit includes:

the acquiring subunit is configured to perform acquiring a first interaction quantity sequence of the at least one first video segment after being pushed and a second interaction quantity sequence of the at least one first video segment before being pushed, wherein the first interaction quantity sequence is used for representing an actual interaction effect of the interaction behavior after being pushed, and the second interaction quantity sequence is used for representing an expected interaction effect of the interaction behavior before being pushed;

and the determining subunit is configured to determine, based on a third interaction quantity ranking of other interaction behaviors of the at least one first video segment before pushing, other interaction behaviors matched with the first interaction quantity ranking as the target interaction behavior if the first interaction quantity ranking is different from the second interaction quantity ranking, and the third interaction quantity ranking is used for representing an expected interaction effect of the other interaction behaviors before pushing.

In some embodiments, the determining unit includes:

the acquiring subunit is further configured to perform acquiring a first interaction quantity sequence of the at least one first video segment after being pushed and a sequence of multiple interaction behaviors of the at least one first video segment before being pushed, wherein the first interaction quantity sequence is used for representing an actual interaction effect of the interaction behaviors after being pushed, and the sequence of the multiple interaction behaviors is used for representing an expected interaction effect of the multiple interaction behaviors before being pushed;

the determining subunit is further configured to perform determining, from the rankings corresponding to the plurality of interaction behaviors, a ranking that matches the first interaction quantity ranking;

the determining subunit is further configured to perform, as the target interaction behavior, the interaction behavior corresponding to the ranking.

In some embodiments, the pushing unit is configured to perform:

within a first pushing range, pushing at least one first video clip;

the pushing unit is further configured to perform:

In some embodiments, the apparatus further comprises:

a sub-segment determining unit configured to execute, for any one of the at least one first video segment, determining a video sub-segment of which the pushed interactive behavior meets a second condition based on the pushed interactive behavior of the any one first video segment;

an extracting unit configured to perform extracting the video sub-segment from the any one of the first video segments;

the pushing unit is further configured to perform pushing of the video sub-segment.

In some embodiments, the sub-segment determining unit is configured to perform:

the extracting unit is configured to extract the video sub-segment from any one of the first video segments based on the start time stamp and the end time stamp of the first time segment.

In some embodiments, the sub-segment determining unit is configured to perform:

According to a third aspect of embodiments of the present disclosure, there is provided a server, including:

one or more processors;

a memory for storing the processor executable program code;

wherein the processor is configured to execute the program code to implement the video clip pushing method described above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium including: the program code in the storage medium, when executed by a processor of a server, enables the server to perform the video clip pushing method described above.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer program code stored in a computer readable storage medium. The processor of the server reads the computer program code from the computer readable storage medium, and the processor executes the computer program code, so that the server executes the video clip pushing method described above.

The technical scheme provided by the embodiment of the disclosure at least has the following beneficial effects:

according to the technical scheme provided by the embodiment of the disclosure, after the video clip is pushed, the interaction behavior capable of truly measuring the wonderful degree or the popular degree of the video clip is determined according to the real interaction behavior after pushing, so that the priority of the weight parameter corresponding to the target interaction behavior is improved, the problem of low accuracy of the determined video clip caused by unreasonable weight parameter design can be avoided when the subsequent pushing is carried out based on the updated weight parameter, the accuracy of determining the video clip is improved, and the accuracy of pushing the video clip is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a schematic diagram of an implementation environment of a video segment pushing method according to an exemplary embodiment;

FIG. 2 is a flow diagram illustrating a video clip pushing method in accordance with an exemplary embodiment;

FIG. 3 is a flow diagram illustrating a video clip pushing method in accordance with an exemplary embodiment;

FIG. 4 is a flow diagram illustrating a video clip pushing method in accordance with an exemplary embodiment;

FIG. 5 is a flowchart illustrating a video clip pushing method according to an exemplary embodiment;

FIG. 6 is a flow diagram illustrating a video clip pushing method in accordance with an exemplary embodiment;

FIG. 7 is a flow diagram illustrating a video clip pushing method in accordance with an exemplary embodiment;

fig. 8 is a block diagram illustrating a video clip pushing apparatus according to an exemplary embodiment;

FIG. 9 is a block diagram illustrating a server in accordance with an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

The data to which the present disclosure relates may be data that is authorized by a user or sufficiently authorized by parties.

Fig. 1 is a schematic diagram of an implementation environment of a video segment pushing method provided by an embodiment of the present disclosure, referring to fig. 1, where the implementation environment includes: a terminal 101 and a server 102.

The terminal 101 may be at least one of a smartphone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, a laptop portable computer, and the like. The terminal 101 has a communication function and can access the internet. The terminal 101 may be generally referred to as one of a plurality of terminals, and the embodiment is only illustrated by the terminal 101. Those skilled in the art will appreciate that the number of terminals described above may be greater or fewer. The terminal 101 may run an application having a video recommendation function, such as a video application, a live application, a social application, and the like. A user operates the terminal 101 to start an application having a video recommendation function, and a recommendation page including a plurality of pushed videos, which are usually short videos (hereinafter referred to as video clips), can be displayed on an interface of the application having the video recommendation function. In the process of watching a video clip, a plurality of interaction buttons such as a praise button, a comment button, a forward button and the like can be displayed on an interface of an application program, and interaction based on the video clip can be realized by clicking the interaction buttons.

The server 102 may be an independent physical server, a server cluster or a distributed file system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. The server 102 and the terminal 101 may be directly or indirectly connected through wired or wireless communication, which is not limited in the embodiment of the present disclosure. In some embodiments, the number of the servers 102 may be more or less, and the embodiments of the disclosure do not limit this. Of course, the server 102 may also include other functional servers to provide more comprehensive and diverse services. The server 102 is associated with an interaction information database, which is used for storing the interaction behavior content and the number of the interaction behaviors of the plurality of video segments, for example, the interaction behavior content may be the content of comments, and the number of the interaction behaviors is the number of comments.

In some embodiments, the server 102 may be a push server with video recommendation functionality, for example, the server 102 may be a background server of an application with video recommendation functionality. In the embodiment of the present disclosure, after determining and extracting at least one video clip, the server 102 pushes the at least one video clip to the terminal 101, and simultaneously, monitors the interaction condition of the at least one video clip, and stores the interaction information of the at least one video clip in an interaction information database of the server. After receiving the evaluation request for the video clip, the server 102 determines, by using the video clip pushing method provided in the embodiment of the present disclosure, an interaction behavior capable of truly measuring the wonderful degree or the popular degree of the video clip based on the interaction behavior after pushing and the interaction behavior before pushing, and further updates the weight parameter of the interaction behavior, and then pushes the video clip based on the updated weight parameter when pushing the subsequent video clip. The request for evaluating the video clip may be triggered by a technician or a preset period, such as once every 1 hour.

In other embodiments, the server 102 may include a first server 1021 and a second server 1022, where the first server 1021 is used to represent a push server with a video recommendation function, and the server 1022 is used to represent a server that evaluates and feeds back a video clip after being pushed. The first server 1021 and the second server 1022 can communicate with each other. In the embodiment of the present disclosure, after determining and extracting at least one video segment, the first server 1021 pushes the at least one video segment to the terminal 101, and stores the interaction information of the at least one video segment before pushing into the interaction information database of the first server 1021. After the pushing is completed, the second server 1022 monitors the interaction condition of the at least one video clip, and stores the interaction information of the at least one video clip into the interaction information database of the server. After receiving the evaluation request for the video segment, the second server 1022 acquires the interaction information before pushing from the interaction information database associated with the first server 1021 by using the video segment pushing method provided by the embodiment of the present disclosure, determines the interaction behavior capable of truly measuring the wonderful degree or the popular degree of the video segment according to the interaction behavior before pushing and the interaction behavior after pushing, and then sends the interaction behavior to the first server 1021, so that the first server 1021 updates the weight parameter of the interaction behavior after receiving the interaction behavior, and further pushes the video segment based on the updated weight parameter when pushing the subsequent video segment. In the process, for example, the first server 1021 and the second server 1022 are respectively associated with an interaction information database, of course, the two interaction information databases may be combined into one database, that is, the first server 1021 and the second server 1022 are associated with the same interaction information database, and the interaction information database stores interaction information of a plurality of video clips before and after being pushed.

It should be noted that the video clip pushing method provided by the embodiment of the present disclosure may include a production system, an evaluation system, and a feedback system, where the production system is configured to produce a video clip, and specifically, to determine and extract at least one video clip. The evaluation system is used for evaluating the pushed video clips, and is specifically used for evaluating whether the video clips are wonderful and the wonderful degree according to the interaction behaviors obtained after pushing. The feedback system is used for feeding back to the production system, and specifically used for feeding back the correction information to the production system so as to instruct the production system to check and correct parameters, such as weight parameters, according to the correction information.

Fig. 2 is a flowchart illustrating a video clip pushing method applied to a server according to an exemplary embodiment, and as shown in fig. 2, the method includes the following steps:

in step 201, the server pushes at least one first video segment, where the first video segment is determined based on a video to which the first video segment belongs and a first weight parameter of an interaction behavior, and the first weight parameter is used to represent a degree of influence of a corresponding interaction behavior on determining the pushed video segment.

In step 202, the server determines a target interaction behavior based on the interaction behavior obtained after the pushing of the at least one first video segment.

In step 203, the server updates the first weight parameter of the target interaction behavior to obtain an updated second weight parameter, where the priority of the second weight parameter is higher than that of the first weight parameter.

In step 204, the server determines a video segment to be pushed based on the second weight parameter, and pushes the determined video segment.

Fig. 2 is a basic flow chart of the present disclosure, and the following further explains the scheme provided by the present disclosure based on a specific implementation, and fig. 3 is a flow chart of a video clip pushing method according to an exemplary embodiment, as shown in fig. 3, including the following steps:

in step 301, the server determines, in a plurality of published videos, at least one first video segment whose interactive behavior satisfies the push condition based on the interactive behavior of the videos and a corresponding first weight parameter, where the first weight parameter is used to indicate a degree of influence of the corresponding interactive behavior on the determination of the pushed video segment.

The distributed videos refer to videos distributed on the internet. For example, the published videos may be any type of videos such as a live video, a variety video, a match video, and the like, and the type of the videos is not limited by the embodiments of the present disclosure. The interactive behavior comprises at least one of a praise behavior, a comment behavior and a barrage behavior. Satisfying the push condition may be understood as satisfying the highlight condition. For example, the satisfaction of the highlight condition may be that the number of praise is greater than a certain threshold, or that the magnitude of the number of praise is greater than a certain threshold. It should be understood that the greater the number of praise, the more brilliant the video segment is represented. The first video segment is used for representing a highlight video segment in the video, namely, a video segment meeting a highlight condition in the original video. The first weight parameter is used for representing the weight parameter corresponding to the interaction behavior. It should be noted that the first video segment is represented by a unique identifier, which may be a video segment ID (identification number). In some embodiments, the uniqId function is utilized to generate the unique identifier for the first video segment. The video clips are identified through the unique identifiers, and the association of the video clips before and after pushing can be realized, so that interactive data before and after pushing can be communicated, and the evaluation and feedback of subsequent video clips are facilitated.

In some embodiments, in a plurality of published videos, the server obtains the number of the interactive behaviors of the plurality of published videos every other target time, determines at least one first video segment of which the interactive behaviors meet the pushing condition based on the number of the interactive behaviors of the plurality of videos and the corresponding first weight parameter, and then performs the pushing process of a subsequent video segment. Wherein the target duration is a preset fixed duration, such as 5 s.

In some embodiments, the process of the server determining the first video segment includes any one of:

in some embodiments, the server can determine at least one first video segment whose interactive behavior meets the push condition based on an interactive behavior of the published videos and the corresponding first weight parameter. It should be understood that in this process, the first weight parameter corresponding to the interaction behavior is 1. Taking praise behavior as an example, the corresponding process of determining the first video segment is: for any one of the plurality of published videos, acquiring the number of praise behaviors of the any one video in a plurality of time periods, determining the time period in which the number of praise behaviors is continuously larger than a certain threshold, or determining the time period in which the number of praise behaviors increases by a magnitude larger than a certain threshold, taking the time period as a first video segment, and extracting the first video segment from the any one video according to a start timestamp and an end timestamp of the time period, so that at least one first video segment meeting the push condition in the plurality of published videos can be determined. The threshold may be a fixed threshold preset by a technician. In the process, the number of certain interactive behaviors in the video and the preset threshold are utilized, so that the highlight video clip in the video can be quickly determined.

In other embodiments, the server can determine at least one first video segment whose interaction behavior satisfies the push condition based on at least two interaction behaviors of the published videos and the corresponding first weight parameters. Taking the praise behavior and the comment behavior as an example, the corresponding process of determining the first video segment is as follows: for any video in the published videos, acquiring the number of praise behaviors and the number of comment behaviors of the video in a plurality of time periods, according to the first weight parameter corresponding to the number of praise behaviors and the first weight parameter corresponding to the number of comment behaviors, weighting and summing the number of praise behaviors and the number of comment behaviors in each time period to obtain the weighted sum number of each time period, determining the time period in which the weighted sum number is continuously greater than a certain threshold value according to the weighted sum number, or, determining a time period in which the weighted sum number increase magnitude is greater than a certain threshold value, regarding the time period as a first video segment, extracting the first video segment from the any one of the videos according to the start time stamp and the end time stamp of the time period, it can be determined at least one first video segment of the published plurality of videos that meets the push condition. In the process, the amount of two or more than two interactive behaviors in the video and the corresponding weight parameters are utilized, the highlight video clip in the video can be rapidly determined, different weight parameters corresponding to different interactive behaviors are considered, the highlight video clip can be determined more accurately, the accuracy of determining the highlight video clip is improved, and the accuracy of pushing the video clip is further improved.

In step 302, the server pushes the at least one first video segment.

In some embodiments, after the server extracts the at least one first video clip, the server pushes the at least one first video clip to the user side in various forms, and the user side displays the any one first video clip in a recommendation interface of the application program after receiving the any one first video clip. In the process that a user watches any one of the first video clips, a user side interface can display a plurality of interaction buttons, such as a praise button, a comment button, a forwarding button and the like, and the user can realize interaction based on the video clip by clicking the interaction buttons.

It should be noted that the processes from step 301 to step 302 can be executed by a production system, and after at least one first video clip is produced by the production system, the produced at least one first video clip is pushed, that is, distributed online. At this point, the at least one first video segment is further viewed and consumed as a new work by the user, and the at least one first video segment is associated with the original unique identifier.

In step 303, the server determines a target interaction behavior based on the interaction behavior obtained after the pushing of the at least one first video segment.

The interaction behavior obtained after the pushing comprises at least one of clicking behavior, playing behavior, praise behavior, comment behavior, barrage behavior, forwarding behavior, collection behavior and the like. The expected interaction effect corresponding to the target interaction behavior is in accordance with the actual interaction effect, and the actual interaction effect is determined based on the interaction behavior obtained after pushing. The target interaction behavior is used for expressing the interaction behavior capable of truly measuring the wonderful degree or the popular degree of the video clip. The expected interactive effect is determined based on the interactive behavior before pushing, that is, based on the interactive behavior of the first video segment in the original video. In the embodiment of the present disclosure, the expected interactive effect is represented by an interaction number sequence of the at least one first video segment before being pushed, and the actual interactive effect is represented by an interaction number sequence of the at least one first video segment after being pushed. The interaction quantity ranking may be understood as a highlight ranking of the at least one first video segment. It should be understood that after the at least one first video segment is pushed, the at least one first video segment is regarded as a new work in a new scene to be further watched and consumed by the user, the user can perform a series of operations such as comment, approval, sharing, downloading and the like on the new work, the server responds to an interaction request triggered by the user operation, can acquire relevant information of an interaction behavior, and at the moment, the server restarts to record the interaction behavior, the interaction behavior obtained after the pushing is also real interaction behavior data, and can evaluate and measure whether the video segment is really wonderful or not.

In some embodiments, the process of the server determining the target interaction behavior comprises any one of:

in some embodiments, the server obtains a first interaction quantity ranking of the at least one first video segment after being pushed and a second interaction quantity ranking of the at least one first video segment before being pushed, wherein the first interaction quantity ranking is used for representing an actual interaction effect of the interaction behavior after being pushed, and the second interaction quantity ranking is used for representing an expected interaction effect of the interaction behavior before being pushed. If the first interaction quantity sequence is different from the second interaction quantity sequence, determining other interaction behaviors matched with the first interaction quantity sequence as the target interaction behaviors based on a third interaction quantity sequence of other interaction behaviors of the at least one first video clip before pushing except the interaction behaviors, wherein the third interaction quantity sequence is used for expressing expected interaction effects of the other interaction behaviors before pushing.

Taking the first video segment determined according to the favorable behavior before pushing and the first video segment evaluated according to the favorable behavior after pushing as an example, before pushing, sequencing the favorable behavior from high to low according to the favorable behavior quantity of at least one first video segment from numerical values to obtain favorable quantity sequencing before pushing, and after pushing, sequencing the favorable behavior quantity from high to low according to the favorable behavior quantity of at least one first video segment from numerical values to obtain favorable quantity sequencing after pushing. Judging whether the ranking of the praise number before pushing and the ranking of the reward number after pushing are the same, if so, indicating that the praise behavior before pushing can measure the actual interaction effect after pushing, and then not needing to execute subsequent steps, and if not, obtaining the number of other interaction behaviors before pushing, such as obtaining the number of comment behaviors and the number of bullet screen behaviors. And sequencing according to the number of the comment behaviors and the number of the bullet screen behaviors to obtain a comment number sequence and a bullet screen number sequence, comparing the pushed reward number sequence with the comment number sequence and the bullet screen number sequence respectively, determining a sequence matched with the pushed reward number sequence, if the comment number sequence is matched with the pushed reward number sequence, indicating that the comment behaviors can measure the interactive effect after actual pushing, comparing the favorable behaviors, and taking the comment behaviors as target interactive behaviors if the comment behaviors are the interactive behaviors which can really measure whether the video clips are wonderful. It should be noted that the type of the selected interactive behavior before pushing and the type of the selected interactive behavior after pushing may be the same or different. For example, the video clips are sorted in a praise behavior before and after being pushed. It should be noted that the above process only takes a single kind of interaction behavior as an example for sorting, and the server can also sort the video segments based on two or more kinds of interaction behaviors. Specifically, which interactive behavior is selected, several interactive behaviors are selected, different metrics can be set according to different video products, and then the interactive behavior corresponding to the metrics is selected. The embodiment of the present disclosure does not limit the process of selecting which kind or several kinds of interactive behaviors are selected.

For example, if the video segment ID1, the video segment ID2, and the video segment ID3 represent 3 first video segments, and if the ranking of the number of praises before pushing is ID1(50) > ID2(30) > ID3(10), and the ranking of the number of rewards after pushing is ID2(50) > ID1(40) > ID3(10), it can be found that the ranking of the number of praises before pushing is different from the ranking of the number of rewards after pushing, the number of comment behaviors before pushing and the number of barrage behaviors after pushing are obtained, and if the ranking of the number of comments before pushing is ID2(30) > ID1(20) > ID3(15), and the ranking of the number of barrage before pushing is ID3(50) > ID2(35) > ID1(15), it can be found that the ranking of comment behaviors before pushing is the same as the ranking of the number of reward behaviors after pushing as the target interaction behaviors.

In the process, the target interaction behavior is determined by judging whether the first interaction quantity sequence after pushing is the same as the second interaction quantity sequence before pushing or not and then performing a comparison process of the subsequent third interaction quantity sequence and the first interaction quantity sequence.

In other embodiments, the server obtains a first interaction quantity ranking of the at least one first video segment after being pushed and a ranking of a plurality of interaction behaviors of the at least one first video segment before being pushed, where the ranking of the plurality of interaction behaviors is used to represent an expected interaction effect of the plurality of interaction behaviors before being pushed. And determining the sequence matched with the first interaction quantity sequence in the sequences corresponding to the multiple interaction behaviors, and taking the interaction behavior corresponding to the sequence as the target interaction behavior. In the process, the target interaction behaviors are determined by comparing the sequences of the multiple interaction behaviors before pushing and the sequences of the first interaction quantity after pushing one by one, and the target interaction behaviors can be determined quickly.

It should be noted that, the process of obtaining the second interaction quantity ranking, the third interaction quantity ranking and the quantity ranking of the multiple types of interaction behaviors before pushing in step 303 can be executed before pushing the video segment, for example, in step 301, that is, when the first video segment is extracted, the server records the quantity of the interaction behaviors and the interaction quantity ranking of the at least one first video segment, and then obtains the ranking before pushing by querying in subsequent ranking comparison. Or, the server can acquire the number of the interaction behaviors before pushing in the sorting comparison, and then sort to obtain the sorting before pushing. The embodiment of the present disclosure does not limit the process of obtaining the pre-push ranking.

It should be further noted that the process of step 303 can be executed by a feedback system, and through statistical analysis of a plurality of video segments, an interactive behavior that can truly measure whether the video segments are wonderful or not is determined. For example, it may be found that the number of review behaviors is more excellent than the number of praise behaviors in measuring the wonderful degree, and the feedback system further controls the initial production system according to the correction information obtained by analysis, so as to achieve the purpose of feedback, and make the production system more accurate.

In step 304, the server updates the first weight parameter of the target interaction behavior to obtain an updated second weight parameter, wherein the priority of the second weight parameter is higher than that of the first weight parameter.

In some embodiments, after determining the target interaction behavior, the server updates the first weight parameter of the target interaction behavior according to the target adjustment value to obtain an updated second weight parameter. Wherein, the target adjustment value is a preset adjustment value. For example, if the first weight parameter of the target interaction behavior is 30% and the target adjustment value is 5%, the first weight parameter of the target interaction behavior is increased by 5% to obtain a second weight parameter of 35%.

In step 305, the server determines a video segment to be pushed based on the second weight parameter, and pushes the determined video segment.

In some embodiments, after obtaining the second weight parameter, the server determines, in the published video, a video segment to be pushed according to the interaction behavior of the published video and the second weight parameter corresponding to the interaction behavior, and then pushes the determined video segment.

It should be noted that the process from step 304 to step 305 is executed by the production system, and the production system updates and corrects the parameters of the production system according to the correction information output by the feedback system.

In some embodiments, after determining the at least one first video segment to be pushed based on the first weight parameter, the server pushes the at least one first video segment within a first pushing range. And when the server determines the video clip to be pushed based on the second weight parameter, pushing the determined video clip within a second pushing range, wherein the second pushing range is larger than the first pushing range. Alternatively, the push scope may be the number of clients to be pushed. For example, the first push scope may be to push to a first number of ues, and the second push scope may be to push to a second number of ues. The first number is smaller than the second number, for example, the first number may be 1000, and the second number may be 100000. In this embodiment, when pushing for the first time, pushing is performed for a small range of user terminals, and when pushing for the second time, pushing is performed for a large range of user terminals, so that the pushing cost is reduced, the accuracy of the pushed video clips is also improved, and it can be ensured that the pushed video clips are really wonderful video clips when pushing for the large range.

According to the technical scheme provided by the embodiment of the disclosure, the highlight video clip meeting the conditions is determined and pushed according to the interaction condition of the video, after the highlight video clip is pushed, the target interaction behavior with the expected interaction effect consistent with the actual interaction effect is determined according to the real interaction behavior after pushing, namely, the interaction behavior capable of truly measuring the highlight degree or the popularity degree of the video clip is determined, and further the weight parameter corresponding to the target interaction behavior is improved, so that when the follow-up pushing is carried out based on the updated weight parameter, the problem that the accuracy of determining the video clip is low due to unreasonable weight parameter design can be avoided, the accuracy of determining the video clip is improved, and the accuracy of pushing the video clip is improved. Due to the fact that the online evaluation system and the feedback system are introduced, parameters of the production system are updated by means of the real interaction behavior obtained after pushing, the wonderful video identification of the production system is sensitive, and accuracy is remarkably improved.

Fig. 3 is a process of determining a target interaction behavior based on at least one first video segment, and updating a weight parameter of the target interaction behavior. In other embodiments, a truly highlighted video segment may be determined from the at least one first video segment, and then the target interaction behavior may be determined based on the truly highlighted video segment. Fig. 4 is a flowchart illustrating a video clip pushing method according to an exemplary embodiment, as shown in fig. 4, including the following steps:

in step 401, the server determines, in a plurality of published videos, at least one first video segment whose interactive behavior satisfies the push condition based on the interactive behavior of the videos and a corresponding first weight parameter, where the first weight parameter is used to indicate a degree of influence of the corresponding interactive behavior on determining the pushed video segment.

In step 402, the server pushes the at least one first video segment.

The contents of step 401 to step 402 refer to the contents of step 301 to step 302, and are not described again.

In step 403, the server determines at least one second video segment whose pushed interactive behavior satisfies the first condition based on the interactive behavior obtained after the pushing of the at least one first video segment.

Wherein the first condition is used to weigh whether the first video segment is really highlights. The second video segment is used to represent a truly highlight video segment.

In some embodiments, for any one of the at least one first video segment, if the number of the interactive behaviors of the any one first video segment after being pushed is greater than a first threshold, the any one first video segment is determined to be a second video segment satisfying a first condition, and if the number of the interactive behaviors of the any one first video segment after being pushed is less than or equal to the first threshold, the any one first video segment is determined not to be the second video segment satisfying the first condition. The first threshold is a fixed threshold preset by a technician, such as 1000.

In some embodiments, the number of interactive behaviors may be one number of interactive behaviors, or may be a weighted sum of two or more numbers of interactive behaviors. For example, taking praise behavior as an example, if the number of praise behaviors of the first video segment after being pushed is greater than 1000, it is determined that the first video segment is a highlight video segment, and the first video segment is taken as a second video segment. For another example, taking the praise behavior and the comment behavior as an example, according to the praise behavior number, the comment behavior number, the weight corresponding to the praise behavior, and the weight corresponding to the comment behavior, the weighted sum is performed on the praise behavior number and the comment behavior number, if the weighted sum is greater than a first threshold, it is determined that the first video segment satisfies the first condition, and if the weighted sum is less than or equal to the first threshold, it is determined that the first video segment does not satisfy the first condition.

It should be noted that, according to the difference of the selected interactive behavior type or the number of types, the corresponding first threshold value is also different. For example, the first threshold corresponding to the praise behavior may be 1000, and the first threshold corresponding to the comment behavior may be 500. For another example, if a single kind of interaction behavior is selected, for example, the first threshold corresponding to the like behavior may be 1000, and two kinds of interaction behaviors are selected, for example, the first threshold corresponding to the weighted sum of the like behavior and the comment behavior may be 700. The embodiment of the disclosure does not limit how to set the first threshold

It should be further noted that the process of step 403 can be performed by an evaluation system, and the evaluation system can evaluate and measure the really wonderful video segment based on the interaction behavior obtained after pushing.

In step 404, the server determines a target interaction behavior based on the interaction behavior of the at least one second video segment after being pushed.

And the expected interaction effect corresponding to the target interaction behavior is consistent with the actual interaction effect, and the actual interaction effect is determined based on the interaction behavior obtained after pushing.

In step 404, the content of the target interaction behavior is determined based on the second video segment, which is referred to in step 303 for the content of the target interaction behavior determined based on the first video segment, and is not described again.

In the process, the real wonderful video clips are determined, and then whether wonderful interactive behaviors of the video clips can be measured really is determined according to the real wonderful video clips, so that the accuracy of determining the target interactive behaviors can be improved, the accuracy of updating the weight parameters is also improved, and the accuracy of pushing the subsequent video clips is further improved.

It should be noted that the process of step 404 can be executed by a feedback system, and further analysis is performed on at least one second video segment according to the output of the evaluation system to extract new features of the real highlight videos, that is, to determine an interaction behavior capable of truly measuring whether the video segment is highlight, so as to perform a subsequent feedback process.

In step 405, the server updates the first weight parameter of the target interaction behavior to obtain an updated second weight parameter, wherein the priority of the second weight parameter is higher than that of the first weight parameter.

In step 406, the server determines a video segment to be pushed based on the second weight parameter, and pushes the determined video segment.

The contents of step 405 to step 406 refer to the contents of step 304 to step 305, and are not described again.

For example, fig. 5 is a flow diagram illustrating a video clip pushing method according to an exemplary embodiment, as shown in fig. 5, and fig. 5 illustrates a production system, an evaluation system, and a feedback system. The production system is specifically used for acquiring video or live broadcast interaction information such as user praise number, comment number and barrage number, taking the number of interaction behaviors as input, and extracting video clips meeting conditions from the video or live broadcast. The evaluation system is specifically configured to examine the generated highlight video segments according to the real feedback of the user, thereby finding out a truly highlight video segment. The feedback system is specifically configured to analyze the truly brilliant video segment, determine an interaction behavior of the truly brilliant video segment, generate correction information based on the interaction behavior, and feed the correction information back to the production system to instruct the production system to perform verification and correction.

According to the technical scheme provided by the embodiment of the disclosure, after the video clips are pushed, according to the real interactive behaviors after being pushed, the real wonderful video clips are determined firstly, then according to the real wonderful video clips, the target interactive behaviors with the expected interactive effects consistent with the actual interactive effects are determined, namely, the interactive behaviors capable of truly measuring the wonderful degree or the popular degree of the video clips are determined, and further the weight parameters corresponding to the target interactive behaviors are improved, so that when the video clips are pushed subsequently based on the updated weight parameters, the problem that the accuracy of the determined video clips is low due to unreasonable weight parameter design can be avoided, the accuracy of determining the video clips is improved, and meanwhile, the accuracy of pushing the video clips is improved.

In some embodiments, with the video segment pushing method provided by the embodiments of the present disclosure, it is also possible to evaluate the pushing accuracy of the video segment, and use the pushing accuracy to perform subsequent evaluation and feedback processes. Fig. 6 is a flowchart illustrating a video clip pushing method according to an exemplary embodiment, as shown in fig. 6, including the following steps:

in step 601, the server determines, in a plurality of published videos, at least one first video segment whose interactive behavior meets the push condition based on the interactive behavior of the videos and a corresponding first weight parameter, where the first weight parameter is used to represent a degree of influence of the corresponding interactive behavior on determining the pushed video segment.

In step 602, the server pushes at least one first video clip.

The contents of step 601 to step 602 refer to the contents of step 301 to step 302, and are not described again.

In step 603, the server obtains a first interaction quantity ranking of the at least one first video segment after being pushed and a second interaction quantity ranking of the at least one first video segment before being pushed, where the first interaction quantity ranking is used for representing an actual interaction effect of the interaction behavior after being pushed, and the second interaction quantity ranking is used for representing an expected interaction effect of the interaction behavior before being pushed.

In step 604, the server determines a push accuracy of the at least one first video segment based on the first interaction quantity ranking and the second interaction quantity ranking of the at least one first video segment, wherein the push accuracy is used for representing a degree of accuracy that the at least one first video segment meets the push condition.

Wherein, the push accuracy is used to measure the accuracy of the true wonderful of the pushed video clip, and it can also be understood that the pushed video clip is the true wonderful degree.

In some embodiments, the server determines a variance value between the first interaction number ordering and the second interaction number ordering based on the first interaction number ordering and the second interaction number ordering of the at least one first video segment, and determines a push accuracy of the second interaction number ordering of the at least one first video segment based on the variance value. In the process, a real online evaluation system is introduced, so that the effect of the production of the wonderful video becomes evaluable, and the effect is more real and credible.

In step 605, the server determines at least one second video segment of the at least one first video segment that satisfies a first condition based on the push precision of the at least one first video segment.

In some embodiments, the server determines, as the second video segment, at least one video segment having a push precision greater than a precision threshold, based on a push precision of the at least one first video segment, among the at least one first video segment. By pushing the accuracy, the truly brilliant video clip can be quickly determined, and the process of determining the truly brilliant video clip is improved.

In step 606, the server determines a target interaction behavior based on the interaction behavior of the at least one second video segment after being pushed.

In step 607, the server updates the first weight parameter of the target interaction behavior to obtain an updated second weight parameter, and the priority of the second weight parameter is higher than that of the first weight parameter.

In step 608, the server determines a video segment to be pushed based on the second weight parameter, and pushes the determined video segment.

The contents of step 606 to step 608 refer to the contents of step 404 to step 406, which are not described again.

According to the technical scheme provided by the embodiment of the disclosure, after the video clip is pushed, the target interaction behavior with the expected interaction effect in accordance with the actual interaction effect is determined according to the real interaction behavior after pushing, that is, the interaction behavior capable of truly measuring the wonderful degree or the popular degree of the video clip is determined, so that the weight parameter corresponding to the target interaction behavior is improved, and when the video clip is pushed subsequently based on the updated weight parameter, the problem of low accuracy of the determined video clip caused by unreasonable weight parameter design can be avoided, the accuracy of determining the video clip is improved, and the accuracy of pushing the video clip is improved.

In some embodiments, the pushed real interactive data can be used for extracting a real wonderful video sub-segment from the first video segment, and then pushing the real wonderful video sub-segment. Fig. 7 is a flowchart illustrating a video clip pushing method according to an exemplary embodiment, as shown in fig. 7, including the following steps:

in step 701, the server determines, in a plurality of published videos, at least one first video segment whose interactive behavior meets the push condition based on the interactive behavior of the videos and a corresponding first weight parameter, where the first weight parameter is used to represent a degree of influence of the corresponding interactive behavior on determining the pushed video segment.

In step 702, the server pushes at least one first video segment.

The contents of step 701 to step 702 refer to the contents of step 301 to step 302, and are not described again.

In step 703, for any one of the at least one first video segment, the server determines a video sub-segment whose pushed interactive behavior satisfies a second condition based on the pushed interactive behavior of the any one first video segment.

Wherein the second condition is used to measure whether the video sub-segment is highlights.

In some embodiments, the process of the server determining the highlight video sub-segment comprises any one of:

in some embodiments, the number of the interactive behaviors in the any one of the first video segments in a plurality of time periods is determined based on the interactive behaviors of the any one of the first video segments after being pushed, a first time period in which the number of the interactive behaviors is continuously greater than a second threshold value is determined based on the number of the interactive behaviors in the plurality of time periods, and a video sub-segment corresponding to the first time period is taken as the video sub-segment meeting the second condition.

In other embodiments, based on the interaction behavior of any one of the first video segments after being pushed, the number of the interaction behaviors in the any one of the first video segments in a plurality of time periods is determined, based on the number of the interaction behaviors in the plurality of time periods, a second time period in which the increase amplitude of the number of the interaction behaviors is greater than a third threshold value is determined, and a video sub-segment corresponding to the second time period is taken as the video sub-segment meeting the second condition.

In step 704, the server extracts the video sub-segment from the any one of the first video segments.

In some embodiments, the video sub-segment is extracted from the any one of the first video segments based on a start time stamp and an end time stamp of the first time period.

In step 705, the server pushes the video sub-segment.

According to the technical scheme provided by the embodiment of the disclosure, after the video clip is pushed, the really wonderful video sub clip can be determined according to the real interactive behavior after the video clip is pushed, and then the video sub clip is pushed, so that the really wonderful video sub clip can be pushed.

Fig. 8 is a block diagram illustrating a video clip pushing apparatus according to an exemplary embodiment. Referring to fig. 8, the apparatus includes a pushing unit 801, a determining unit 802, and an updating unit 803.

A pushing unit 801 configured to perform pushing on at least one first video segment, where the first video segment is determined based on a video to which the first video segment belongs and a first weight parameter of an interaction behavior, and the first weight parameter is used to represent a degree of influence of a corresponding interaction behavior on determining the pushed video segment;

a determining unit 802 configured to perform determining a target interaction behavior based on an interaction behavior obtained after the pushing of the at least one first video segment;

an updating unit 803, configured to perform an update on a first weight parameter of the target interaction behavior, resulting in an updated second weight parameter, where a priority of the second weight parameter is higher than that of the first weight parameter;

the pushing unit 801 is further configured to determine a video segment to be pushed based on the second weight parameter, and push the determined video segment.

In some embodiments, the determining unit 802 includes:

In some embodiments, the apparatus further comprises:

a second video segment determination unit configured to determine, by the execution server, at least one second video segment of the at least one first video segment that satisfies the first condition based on the push precision of the at least one first video segment.

In some embodiments, the determining unit 802 includes:

In some embodiments, the pushing unit 801 is configured to perform:

within a first pushing range, pushing at least one first video clip;

the pushing unit 801 is further configured to perform:

In some embodiments, the apparatus further comprises:

the pushing unit 801 is further configured to perform pushing the video sub-segment.

In some embodiments, the sub-segment determining unit is configured to perform:

It should be noted that: in the above embodiment, when pushing a video clip, the video clip pushing apparatus is exemplified by only the division of the functional modules, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the video segment pushing apparatus and the video segment pushing method provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments and are not described herein again.

Fig. 9 is a block diagram of a server according to an exemplary embodiment, where the server 900 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 901 and one or more memories 902, where the one or more memories 902 store at least one program code, and the at least one program code is loaded and executed by the one or more processors 901 to implement the video segment pushing method provided by the above-mentioned method embodiments. Certainly, the server 900 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 900 may also include other components for implementing device functions, which are not described herein again.

In an exemplary embodiment, there is also provided a storage medium, such as a memory 902, comprising program code, which is executable by a processor 901 of the server 900 to perform the video clip pushing method described above. In some embodiments, the storage medium may be a non-transitory computer-readable storage medium, which may be, for example, a read-only memory (ROM), a random access memory (random access memory), a RAM), a compact-disc-read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and so forth.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for pushing video clips, the method comprising:

pushing at least one first video segment, wherein the first video segment is determined based on a video to which the first video segment belongs and a first weight parameter of an interaction behavior, and the first weight parameter is used for representing the influence degree of the corresponding interaction behavior on the determination of the pushed video segment;

2. The method according to claim 1, wherein an expected interaction effect corresponding to the target interaction behavior coincides with an actual interaction effect, and the actual interaction effect is determined based on the interaction behavior obtained after the pushing.

3. The method according to claim 1, wherein the determining the target interaction behavior based on the interaction behavior of the at least one first video segment after being pushed comprises:

4. The method according to claim 3, wherein the determining, based on the interaction behavior of the at least one first video segment after being pushed, at least one second video segment whose interaction behavior after being pushed satisfies a first condition comprises:

5. The method of claim 3, wherein after the pushing the at least one first video segment, the method further comprises:

determining a pushing precision of the at least one first video segment based on a first interaction quantity ordering and a second interaction quantity ordering of the at least one first video segment, wherein the pushing precision is used for representing the precision degree of the at least one first video segment meeting the pushing condition;

determining at least one second video segment of the at least one first video segment that satisfies a first condition based on a push precision of the at least one first video segment.

6. The method according to claim 1, wherein the determining the target interaction behavior based on the interaction behavior of the at least one first video segment after being pushed comprises:

7. The method according to claim 1, wherein the determining the target interaction behavior based on the interaction behavior of the at least one first video segment after being pushed comprises:

determining a sequence matched with the first interaction quantity sequence in the sequences corresponding to the multiple interaction behaviors;

8. A video clip pushing apparatus, the apparatus comprising:

the pushing unit is configured to push at least one first video segment, the first video segment is determined based on a video to which the first video segment belongs and a first weight parameter of an interaction behavior, and the first weight parameter is used for representing the influence degree of the corresponding interaction behavior on the determination of the pushed video segment;

the determining unit is configured to execute target interaction behavior determination based on the interaction behavior obtained after the pushing of the at least one first video segment;

the updating unit is configured to update a first weight parameter of the target interaction behavior to obtain an updated second weight parameter, and the priority of the second weight parameter is higher than that of the first weight parameter;

9. A server, characterized in that the server comprises:

one or more processors;

a memory for storing the processor executable program code;

wherein the processor is configured to execute the program code to implement the video segment pushing method of any of claims 1 to 7.

10. A storage medium, characterized in that program code in the storage medium, when executed by a processor of a server, enables the server to perform the video clip pushing method according to any one of claims 1 to 7.