CN114513686B - Video information determining method, device and storage medium - Google Patents
Video information determining method, device and storage medium Download PDFInfo
- Publication number
- CN114513686B CN114513686B CN202011287923.1A CN202011287923A CN114513686B CN 114513686 B CN114513686 B CN 114513686B CN 202011287923 A CN202011287923 A CN 202011287923A CN 114513686 B CN114513686 B CN 114513686B
- Authority
- CN
- China
- Prior art keywords
- video
- recommended
- current
- determining
- association
- 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
- 238000000034 method Methods 0.000 title claims abstract description 92
- 230000003993 interaction Effects 0.000 claims abstract description 34
- 230000002452 interceptive effect Effects 0.000 claims abstract description 25
- 230000006399 behavior Effects 0.000 claims description 76
- 230000008569 process Effects 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 17
- 230000002596 correlated effect Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 abstract description 12
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending 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]
- H04N21/40—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
-
- 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
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to a method, a device and a storage medium for determining video information, relates to the field of software application, and aims to solve the problem that a video recommendation scheme in the prior art is poor in recommendation effect. The method comprises the following steps: acquiring a recommended video record of a current account of the current video, wherein the recommended video record is at least used for recording the interactive operation of the current account on the recommended video; and determining the association relation between each recommended video and the current video at least according to the interaction operation of each current account on the recommended video and the current video.
Description
Technical Field
The present disclosure relates to the field of software applications, and in particular, to a method and apparatus for determining video information, and a storage medium.
Background
Personalized recommendation refers to mining content potentially of interest to a user by analyzing the user's historical behavior and recommending to the user in a specific scenario. For example, while the user is watching the video, the user's viewing records are analyzed to determine videos of potential interest to the user and make recommendations.
In the prior art, it is common to aggregate videos with their labels, and then recommend the closest set of videos to the user. However, this method is excessively dependent on the tag, and when the tag of the video is inaccurate, the user may be uninteresting about the recommended video, i.e., the recommendation effect is poor.
Disclosure of Invention
The disclosure provides a method, a device and a storage medium for determining video information, so as to at least solve the problem of poor recommendation effect of a video recommendation scheme in the prior art. The technical scheme of the present disclosure is as follows:
according to a first aspect of the present disclosure, there is provided a method of determining video information, the method comprising: after the recommended video records of the current accounts of the current videos are obtained, according to the interaction operation of the current accounts on the recommended videos and the current videos, the association relation between the recommended videos and the current videos is determined.
The current video is a video of which the play operation is executed by the current account; the recommended video record is at least used for recording the interaction operation of the current account on the recommended video; the recommended video is the video displayed on the associated interface for playing the video in the process of playing the video in the current account.
Optionally, the method for determining the association relationship between each recommended video and the current video according to the interaction operation of each current account on the recommended video and the current video includes: and determining positive correlation videos and negative correlation videos according to the interaction operation of each current account on the recommended video and the current video, and recording the positive correlation videos and the negative correlation videos of the current video. The positive association video and the current video have positive association relationship, the negative association video and the current video have negative association relationship, and the association relationship comprises positive association relationship and negative association relationship.
Optionally, the method for determining the positive associated video and the negative associated video according to the interaction operation of each current account on the recommended video and the current video includes: based on the interaction operation of each current account on the recommended video and the playing operation of the current video, determining the association parameters of the recommended video, and based on the association parameters of the recommended video, determining the positive association video and the negative association video. The association parameter is used for representing the probability of playing the recommended video under the condition that the current account plays the current video.
Optionally, the method for determining the positive associated video and the negative associated video based on the associated parameters of the recommended video includes: and sequencing the recommended videos according to the size sequence of the association parameters, and determining positive association videos and negative association videos according to the sequenced recommended videos. Or determining the recommended video with the association parameter meeting the first preset condition as a forward associated video; and determining the recommended video with the association parameter meeting the second preset condition as the negative association video.
Optionally, the method for determining the associated parameters of the recommended video based on the interaction operation of each current account on the recommended video and the playing operation of the current video includes: based on the interaction operation of each current account on the recommended video and the playing operation of the current video, determining a first behavior and a second behavior, and determining the ratio of the first behavior to the second behavior as the association parameter of the current video to one recommended video. Wherein the first behavior is the sum of the number of the same interactive operations performed by each current account on one recommended video; the second behavior is that the number of recommended videos is displayed on the associated interface of the played video in the process of playing the current video.
Optionally, the determining method provided in the present disclosure further includes: a first identification is added for positively correlated video and a second identification is added for negatively correlated video. The first identifier is used for indicating that the positive association video has a positive association relationship with the current video, and the second identifier is used for indicating that the negative association video has a negative association relationship with the current video.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
in the scheme, the association relation between the current video and the recommended video is determined by utilizing the interaction operation of the current account on the recommended video of the current video and the current video, so that the recommended video is determined for the account based on the association relation. Therefore, the mode of determining the current video and the recommended video with the association relation according to the interactive operation of each current account on the recommended video avoids the excessive dependence on the labels, and the behavior of the user is used as the basis for determining the association relation, so that the user can be more close to the idea when recommending the video for the user later, and the recommendation effect is improved.
According to a second aspect of the present disclosure, there is provided a method of determining video information, the method comprising: and responding to the video recommendation request sent by the platform account, and reading the historical operation video of the platform account. Thereafter, a recommended video for the platform account is determined based at least on the associated video of the historical operating video. The historical operation video is a video of platform account history executing interactive operation; the associated video is a video with an association relationship with the historical operation video; the association relationship is obtained based on the optional method for determining video information in any one of the first aspect.
Optionally, in the association relationship, the recommended video and the historical operation video have a forward association relationship, and the association degree between the recommended video and the historical operation video is greater than a first threshold.
Optionally, the method for determining video information further includes: a mask video for the platform account is determined based at least on the associated video of the historical operating video. The shielding video is a video with a negative incidence relation with the historical operation video.
Optionally, the degree of association between the mask video and the historical operation video is smaller than a second threshold.
In the scheme, according to the historical operation video and the association relation of the platform account, the association video of the historical operation video is determined, and the recommended video of the platform account is determined according to the association video. In this way, the recommended video of the platform account is obtained according to the video and the association relation of the platform account history after the interactive operation is executed, so that the recommended effect can be improved more closely to the idea of the user.
According to a third aspect of the present disclosure, there is provided a determination apparatus of video information, the determination apparatus including an acquisition module and a determination module. And the acquisition module is configured to execute recommended video recording of the current account for acquiring the current video. And the determining module is configured to execute interaction operation of each current account on the recommended video and the current video and determine the association relation between each recommended video and the current video.
The current video is a video of which the play operation is executed by the current account; the recommended video record is at least used for recording the interaction operation of the current account on the recommended video; the recommended video is the video displayed on the associated interface for playing the video in the process of playing the video in the current account.
Optionally, the determining module is specifically configured to perform: and determining positive correlation videos and negative correlation videos according to the interaction operation of each current account on the recommended video and the current video, and recording the positive correlation videos and the negative correlation videos of the current video. The positive association video and the current video have positive association relationship, the negative association video and the current video have negative association relationship, and the association relationship comprises positive association relationship and negative association relationship.
Optionally, the determining module is specifically configured to perform: based on the interaction operation of each current account on the recommended video and the playing operation of the current video, determining the association parameters of the recommended video, and based on the association parameters of the recommended video, determining the positive association video and the negative association video. The association parameter is used for representing the probability of playing the recommended video under the condition that the current account plays the current video.
Optionally, the determining module is specifically configured to perform: and sequencing the recommended videos according to the size sequence of the association parameters, and determining positive association videos and negative association videos according to the sequenced recommended videos. Or determining the recommended video with the association parameter meeting the first preset condition as a forward associated video; and determining the recommended video with the association parameter meeting the second preset condition as the negative association video.
Optionally, the determining module is specifically configured to perform: based on the interaction operation of each current account on the recommended video and the playing operation of the current video, determining a first behavior and a second behavior, and determining the ratio of the first behavior to the second behavior as the association parameter of the current video to one recommended video. Wherein the first behavior is the sum of the number of the same interactive operations performed by each current account on one recommended video; the second behavior is that the number of recommended videos is displayed on the associated interface of the played video in the process of playing the current video.
Optionally, the determining device provided by the present disclosure further includes a processing module. The processing module is configured to perform adding a first identification for positively correlated video and adding a second identification for negatively correlated video. The first identifier is used for indicating that the positive association video has a positive association relationship with the current video, and the second identifier is used for indicating that the negative association video has a negative association relationship with the current video.
According to a fourth aspect of the present disclosure, there is provided a determination apparatus of video information, the determination apparatus including an acquisition module and a determination module. And the acquisition module is configured to execute the historical operation video of the platform account in response to the video recommendation request sent by the platform account. A determination module configured to perform a determination of recommended videos for the platform account based at least on the associated videos of the historical operating videos. The historical operation video is a video of platform account history executing interactive operation; the associated video is a video with an association relationship with the historical operation video; the association relationship is obtained based on the optional determination device of the video information in any one of the above third aspects.
Optionally, in the association relationship, the recommended video and the historical operation video have a forward association relationship, and the association degree between the recommended video and the historical operation video is greater than a first threshold.
Optionally, the determining module is further configured to perform determining the mask video for the platform account based at least on the associated video of the historical operating video. The shielding video is a video with a negative incidence relation with the historical operation video.
Optionally, the degree of association between the mask video and the historical operating video is less than a second threshold.
According to a fifth aspect of the present disclosure, there is provided a video information determination apparatus including: a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement the method of determining video information as optional in any of the first aspects.
According to a sixth aspect of the present disclosure, there is provided a video information determination apparatus including: a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement the method of determining video information as optional in any of the second aspects.
According to a seventh aspect of the present disclosure, there is provided a computer-readable storage medium having instructions stored thereon, which when executed by a processor of a video information determining apparatus, enable the video information determining apparatus to perform the video information determining method selectable as any one of the above first aspects.
According to an eighth aspect of the present disclosure, there is provided a computer-readable storage medium having instructions stored thereon, which when executed by a processor of a video information determining apparatus, enable the video information determining apparatus to perform the video information determining method selectable as any one of the above second aspects.
According to a ninth aspect of the present disclosure there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of determining video information as optional in any of the first aspects.
According to a tenth aspect of the present disclosure there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of determining video information as optional in any of the second aspects.
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 disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.
Fig. 1 is an implementation environment diagram illustrating a method of determining video information according to an exemplary embodiment.
Fig. 2 is one of flowcharts illustrating a method of determining video information according to an exemplary embodiment.
Fig. 3 is one of the schematic diagrams of a video display interface according to an exemplary embodiment.
FIG. 4 is a second schematic diagram of a video display interface, according to an example embodiment.
Fig. 5 is a second flowchart illustrating a method of determining video information according to an exemplary embodiment.
Fig. 6 is a third flowchart illustrating a method of determining video information according to an exemplary embodiment.
Fig. 7 is one of schematic structural diagrams of a video information determining apparatus according to an exemplary embodiment.
Fig. 8 is a second schematic diagram of a configuration of a video information determination apparatus according to an exemplary embodiment.
Fig. 9 is one of the hardware configuration diagrams of a video information determination apparatus according to an exemplary embodiment.
Fig. 10 is a second schematic diagram of a hardware configuration of a video information determination apparatus according to an exemplary embodiment.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of 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 this disclosure are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with aspects of the present disclosure.
First, an application scenario of the embodiment of the present disclosure will be described.
The method for determining the video information is applied to a scene where a user watches video. In the related art, after videos are aggregated by using tags, videos of interest to a user are determined and recommended to the user. However, when the label of the video is inaccurate, the user may not be interested in the video determined according to the label, resulting in poor recommendation effect.
In addition, some video recommendation schemes use i2i mode to calculate the similarity between the played video and the recommended video according to the forward sequence consumed by the user, so as to determine the video recommended preferentially. The forward sequence consumed by the user refers to a video sequence in which the user has interactive behaviors, for example, a video sequence which is exposed to the user and is praised by the user; or a video sequence that is exposed to the user and clicked on by the user.
This way of determining the priority recommended video based on similarity cannot solve the problem of video similarity in chronological order. For example, if an event is described in detail in video a and briefly in video B, then the video recommendation method for calculating similarity will calculate video a and video B as similar videos. Thus, the probability of watching B video and then watching a video is high, but the probability of watching a video and then watching B video is low. Therefore, when recommending B video for a user who has watched a video, the recommendation effect is also poor.
In addition, the method of determining the priority recommended video according to the similarity cannot solve the problem that the played video and the recommended video are repeated. For example, if the a video is watermarked, or if the a video is converted into the B video, the video recommendation method for calculating the similarity will also calculate the a video and the B video as similar videos. Thus, when recommending B video for a user who has watched a video, the recommendation effect is also poor.
In order to solve the above-mentioned problems, an embodiment of the present disclosure provides a method for determining video information, after a recommended video record of a current account of a current video is obtained, according to an interaction operation of each current account on the recommended video and the current video, determining an association relationship between each recommended video and the current video. And then, responding to the video recommendation request sent by the platform account, reading the historical operation video of the platform account, and determining the recommendation video of the platform account at least based on the associated video of the historical operation video. In this way, the behavior of the user is used as a standard for measuring the recommended video of the user, the dependence on the label in the method for determining the video information can be reduced, the video potentially interested by the user is found to be recommended, and the recommendation effect is improved.
Next, an implementation environment of the embodiments of the present disclosure will be described.
Fig. 1 is a schematic view of an implementation environment of a method of determining video information according to an exemplary embodiment. As shown in fig. 1, the method for determining video information in the present disclosure may be applied to this implementation environment. The implementation environment includes a terminal 01 and a server 02. Wherein the terminal 01 and the server 02 may be interconnected and communicate through a network.
The terminal 01 may be a mobile phone, a tablet computer, a desktop, a laptop, a handheld computer, a notebook, a vehicle-mounted device, an ultra-mobile personal computer (UMPC), a netbook, etc., and the specific form of the terminal 01 is not particularly limited in the embodiments of the present disclosure.
The server 02 may be a server, a server cluster formed by a plurality of servers, or a cloud computing service center. The server 02 may include a processor, memory, network interfaces, and the like.
It should be noted that, the method for determining video information provided in the embodiment of the present disclosure may be applied to the server 02 and may also be applied to the terminal 01. The server 02 and the terminal 01 may be collectively referred to as an electronic device. That is, the execution subject of the video information determining method provided in the embodiment of the present disclosure may be a video information determining apparatus, and the video information determining apparatus may be the above-mentioned electronic device (such as the server 02 or the terminal 01).
Those skilled in the art will appreciate that the above terminals and servers are only examples, and that other terminals or servers that may be present in the present disclosure or in the future are intended to be included within the scope of the present disclosure and are incorporated herein by reference.
Fig. 2 is a flowchart illustrating a method of determining video information according to an exemplary embodiment. As shown in fig. 2, the method may include the following steps.
201. A determining means of the video information obtains a recommended video record of a current account of the current video.
The method comprises the steps that a current video is a video which is played by a current account, a recommended video record is at least used for recording the interaction operation of the current account on the recommended video, and the recommended video is a video which is displayed on an associated interface of the played video in the process of playing the video by the current account.
Typically, the account will display some recommended video on the associated interface of the video during the video playing process. At this time, the video is the current video in the present disclosure, and the recommended videos are recommended videos in the present disclosure. By way of example, fig. 3 provides a schematic diagram of a video display interface. As shown in fig. 3, the display interface of the video includes a current video 31 and 3 recommended videos 32. Of course, the recommended video may be displayed around the current video, or alternatively, may be displayed alternately during the playing of the current video, which is not limited in this disclosure.
If the account is interested in a certain recommended video in the recommended videos, the recommended video is triggered to be played. Further, if the account likes the recommended video, operations such as praise, comment and the like may be performed on the recommended video. At this time, the operations of playing the recommended video, praying, commenting, and the like are triggered as the interactive operations in the present disclosure. Then, the determining device of the video information obtains the interaction operation of the current account on the recommended video.
202. The video information determining device determines the association relation between each recommended video and the current video at least according to the interaction operation of each current account on the recommended video and the current video.
Firstly, the determining device of the video information determines a positive associated video and a negative associated video of the current video according to the interaction operation of each current account on the recommended video and the current video.
Specifically, the method for determining positive-direction associated video and negative-direction associated video by the determining device of video information comprises the following steps:
202a, the determining device of the video information determines the associated parameters of the recommended video based on the interaction operation of each current account on the recommended video and the playing operation of the current video.
The association parameter is used for representing the probability of playing the recommended video under the condition that the current account plays the current video.
Specifically, the determining device of the video information determines the first behavior and the second behavior based on the interactive operation of each current account on the recommended video and the playing operation of the current video.
Wherein, the first behavior is: each current account performs the sum of the number of identical interactions for one recommended video. The second behavior is that the number of recommended videos is displayed on the associated interface of the played video in the process of playing the current video.
Specifically, if the account is interested in the recommended video, the account triggers the recommended video to be played. At this time, the determination means of video information determines that the account has performed an interactive operation of switching playback of the recommended video. Further, in the process of playing the recommended video, if the account finds that the content of the recommended video is the favorite content, the account can see the recommended video. At this time, the determining means of video information determines that the account performs the long-cast interactive operation on the recommended video. Still further, the account is interested in the recommended video in the process of playing the recommended video, and may also perform operations such as praise, comment and the like on the recommended video. At this time, the determining means of the video information determines that the account performs the interactive operation of the specific operation on the recommended video. Of course, this particular operation includes, but is not limited to, praise and comment.
Thus, the first behavior is: the sum of the number of actions of each current account successfully switching from the current video to one recommended video within a preset time period, or the sum of the number of actions of each current account successfully switching from the current video to one recommended video and the playing time of one recommended video being longer than a third threshold value within a preset time period, or the sum of the number of actions of each current account successfully switching from the current video to one recommended video and detecting a specific operation on one recommended video within a preset time period. Wherein the third threshold is preset. For example, the value may be a default value or a value written by a person according to actual situations.
The video information determining device then determines the ratio of the first behavior to the second behavior as the associated parameter from the current video to a recommended video.
From the above, the first behavior is determined according to the operation behavior of the plurality of recommended videos by different accounts, and the second behavior is determined according to the number of the current videos and the recommended videos. The association parameter is determined from a ratio of the first behavior to the second behavior.
For example, FIG. 4 provides a schematic diagram of a display interface for video of different accounts. Referring to fig. 4, in a display interface a of the first account, recommended videos of the current video include: the first recommended video, the second recommended video, and the third recommended video. In the display interface B of the second account, the recommended videos of the front video include: the second recommended video, the third recommended video, the fourth recommended video. In the display interface C of the third account, the recommended video of the current video includes: the second recommended video, the fourth recommended video, the fifth recommended video. In the display interface D of the fourth account, the recommended video of the current video includes: the first recommended video, the fourth recommended video, and the sixth recommended video. In the display interface E of the fifth account, the recommended video of the current video includes: the first recommended video, the third recommended video, the fifth recommended video.
The third threshold is set to 10s, for example. At 9:00:00 (9 hours 0 minutes 0 seconds), the first account, the second account, the third account, the fourth account, and the fifth account all begin to view the current video.
At 9:00:05, the first account switches from the current video to the first recommended video. At 9:00:10, the first account again switches from the first recommended video to another video (which may be the current video or another recommended video). I.e. the first account plays the first recommended video for a period of 5s.
At 9:00:03, the second account switches from the current video to the second recommended video. At 9:00:15, the second account switches from the second recommended video to another video (which may be the current video or another recommended video). I.e. the second account plays the second recommended video for 12s.
At 9:00:04, the third account switches from the current video to the second recommended video. At 9:00:11, the third account switches from the second recommended video to another video (which may be the current video or another recommended video). I.e. the third account plays the second recommended video for a period of 7s.
At 9:00:07, the fourth account switches from the current video to the first recommended video. At 9:00:15, the fourth account is praise for the first recommended video. At 9:00:20, the fourth account switches from the first recommended video to another video (which may be the current video or another recommended video). That is, the length of time for which the fourth account plays the first recommended video is 13s, and praise for the first recommended video.
At 9:00:01, the fifth account switches from the current video to the first recommended video. The fourth account reviews the first recommended video at 9:00:09. At 9:00:16, the fifth account switches from the first recommended video to another video (which may be the current video or another recommended video). I.e. the duration of playing the first recommended video by the fifth account is 15s and the first recommended video is commented on.
Then for the first recommended video: when the first behavior is used for representing the number of behaviors of successfully switching from the current video to one recommended video in a preset time period, the first behavior is 3, and the second behavior is 3, and then the association parameter of the first recommended video is 1.
When the first behavior is used for representing the number of behaviors that the current video is successfully switched to a recommended video and the playing time of the recommended video is longer than a third threshold value in a preset time period, the first behavior is 2, the second behavior is 3, and the association parameter of the first recommended video is 2/3.
When the first behavior is used for representing the number of behaviors of successfully switching from the current video to one recommended video and detecting the operation on one recommended video in a preset time period, the first behavior is 2, the second behavior is 3, and the association parameter of the first recommended video is 2/3.
For a second recommended video: when the first behavior is used for representing the number of behaviors of successfully switching from the current video to one recommended video in a preset time period, the first behavior is 2, the second behavior is 3, and the association parameter of the second recommended video is 2/3.
When the first behavior is used for representing the number of behaviors that the current video is successfully switched to one recommended video and the playing time of one recommended video is longer than a third threshold value in a preset time period, the first behavior is 1, the second behavior is 3, and the association parameter of the second recommended video is 1/3.
When the first behavior is used for representing the number of behaviors of successfully switching from the current video to one recommended video and detecting the operation on one recommended video in a preset time period, the first behavior is 0, the second behavior is 3, and the association parameter of the second recommended video is 0.
For the third recommended video, the fourth recommended video, the fifth recommended video, the sixth recommended video: since no account is successfully switched from the current video to the third recommended video, the fourth recommended video, the fifth recommended video and the sixth recommended video, the association parameters of the third recommended video, the fourth recommended video, the fifth recommended video and the sixth recommended video are all 0.
202b, the determining device of the video information determines the positively-associated video and the negatively-associated video based on the associated parameters of the recommended video.
The forward association video has a forward association relationship with the current video. The negative association video has a negative association relationship with the current video, and the association relationship comprises a positive association relationship and a negative association relationship. Specifically, when the account performs the interaction operation in the step 202a on the recommended video in the process of playing the current video, it is determined that the recommended video has a forward association relationship with the current video; when the account does not perform the interactive operation in the step 202a on the recommended video in the process of playing the current video, it is determined that the recommended video has a negative association relationship with the current video. Wherein the interaction operation in the step 202a is not performed on the recommended video, including: the interactive operation is not performed on the recommended video and the operation of closing the recommendation is performed on the recommended video. That is, positively associated video refers to video that is of relative interest to an account, and negatively associated video refers to video that is of relative dislike to an account.
Specifically, the manner in which the determining means of the video information determines the positively correlated video and the negatively correlated video may include any one of the following implementations.
Implementation 1: the video information determining device sorts the recommended videos according to the size sequence of the association parameters, and determines positive association videos and negative association videos according to the sorted recommended videos.
For example, in the video display interface shown in fig. 4, the association parameter of the first recommended video is 2/3, the association parameter of the second recommended video is 1/3, and the association parameters of the third recommended video, the fourth recommended video, the fifth recommended video, and the sixth recommended video are all 0.
And sorting the plurality of recommended videos according to the determined association parameters from the big to the small order of the association parameters. The ordered video sequence is: { first recommended video, second recommended video, third recommended video, fourth recommended video, fifth recommended video, sixth recommended video }. The third recommended video, the fourth recommended video, the fifth recommended video and the sixth recommended video have the same association parameters and can be randomly ordered.
And then determining positive associated videos and negative associated videos according to the ordered recommended videos. For example, the recommended videos ranked in the first three are determined to be positive-direction associated videos of the current video, and other videos are determined to be negative-direction associated videos of the current video, so that the positive-direction associated videos of the current video comprise a first recommended video, a second recommended video and a third recommended video; the negative associated video of the current video comprises a fourth recommended video, a fifth recommended video and a sixth recommended video. Optionally, in the ranking, the plurality of recommended videos may also be ranked in order of the associated parameters from small to large. In this way, the recommended videos ranked in the last three are determined to be the positive associated videos of the current video, and the other videos are determined to be the negative associated videos of the current video.
Implementation 2: the video information determining device determines the recommended video with the association parameter meeting the first preset condition as the forward associated video. And determining the recommended video with the association parameter meeting the second preset condition as the negative association video.
The first preset condition is a numerical value of an association parameter, when the association parameter is greater than or equal to the numerical value, the recommended video corresponding to the association parameter is determined to be a positive association video of the current video, and when the association parameter is less than the numerical value, the recommended video corresponding to the association parameter is determined to be a negative association video of the current video. The value is preset, for example, may be a default value, or a value written by a relevant person according to actual situations.
For example, in the video display interface shown in fig. 4, the association parameter of the first recommended video is 2/3, the association parameter of the second recommended video is 1/2, and the association parameters of the third recommended video, the fourth recommended video, the fifth recommended video, and the sixth recommended video are all 0. The first preset condition is 1/5. The positive-going associated video of the current video includes the first recommended video and the second recommended video and the negative-going associated video of the current video includes the third recommended video, the fourth recommended video, the fifth recommended video, the sixth recommended video.
It should be noted that, when determining the positively correlated video and the negatively correlated video of the current video according to the determined correlation parameters, the counting rule of the first behavior should be based on the same counting criteria. For example, the first behavior of the first recommended video is characterized by: and in a preset time period, the number of the behaviors of successfully switching from the current video to the first recommended video. Then in calculating the associated parameters of the second recommended video, the first behavior of the second recommended video should also be characterized as: and the number of actions of successfully switching from the current video to the second recommended video in the preset time period.
Finally, the determining device of the video information records the positive associated video and the negative associated video of the current video, and the association relation between each recommended video and the current video is obtained.
Optionally, after determining the association relationship between each recommended video and the current video, the determining device of the video information adds a first identifier to the forward association video, to indicate that the forward association video has a forward association relationship with the current video. The video information determining device adds a second identifier for the negative association video to indicate that the negative association video has a negative association relationship with the current video. In this way, the video information determining device adds the first identifier for the positive association video and adds the second identifier for the negative association video in the association relationship, so that the positive association video and the negative association video can be distinguished more easily when the association relationship is used later.
In the above scheme, the video information determining device determines the association relationship between the current video and the recommended video by using the interaction operation of the current account on the recommended video of the current video and the current video, so as to determine the recommended video for the account based on the association relationship. Therefore, the mode of determining the current video and the recommended video with the association relation according to the interactive operation of each current account on the recommended video avoids the excessive dependence on the labels, and the behavior of the user is used as the basis for determining the association relation, so that the user can be more close to the idea when recommending the video for the user later, and the recommendation effect is improved.
Fig. 5 is a flowchart illustrating another method of determining video information according to an exemplary embodiment. As shown in fig. 5, the method may include the following steps.
301. The determining device of the video information responds to the video recommendation request sent by the platform account, and reads the historical operation video of the platform account.
The historical operation video is a video of platform account history executing interactive operation.
Specifically, when the video information determining device determines that the platform account has video recommendation requirements, the historical video played by the platform account is read according to the identification of the platform account. And then selecting the historical operation video of the platform account, which is subjected to interactive operation, from the historical video.
302. The determining means of the video information determines a recommended video of the platform account based at least on the associated video of the historical operating video.
The associated video is a video having an association relationship with the historical operation video, and the association relationship is obtained based on the steps 201-202.
Specifically, the determining device of the video information determines an associated video having an associated relation with the historical operation video in the associated relation, wherein the associated video comprises a positive associated video and a negative associated video. And then, the determining device of the video information determines the forward association video which has a forward association relationship with the historical operation video of the platform account and has the association degree larger than a first threshold value as the recommended video of the platform account. The association degree is the association parameter in the step 202. Wherein the first threshold is preset. For example, the value may be a default value or a value written by a person according to actual situations.
For example, in the video display interface shown in fig. 4, the association parameter of the first recommended video is 2/3, the association parameter of the second recommended video is 1/3, and the association parameters of the third recommended video, the fourth recommended video, the fifth recommended video, and the sixth recommended video are all 0. The first threshold is 1/4. The first recommended video, the second recommended video and the third recommended video are forward associated videos of the current video. The recommended videos for the platform account include a first recommended video and a second recommended video.
In the above scheme, the video information determining device determines the associated video of the historical operation video according to the historical operation video and the association relationship of the platform account, and determines the recommended video of the platform account according to the associated video. In this way, the recommended video of the platform account is obtained according to the video and the association relation of the platform account history after the interactive operation is executed, so that the recommended effect can be improved more closely to the idea of the user.
Optionally, after the above step 302, as shown in fig. 6, the method for determining video information may further include the following step 303.
303. The determination means of the video information determines a mask video of the platform account based at least on the associated video of the historical operating video. Specifically, the determining device of the video information determines a negatively associated video having a negatively associated relationship with the historical operation video of the platform account as a mask video of the platform account.
For example, in the video display interface shown in fig. 4, the association parameter of the first recommended video is 2/3, the association parameter of the second recommended video is 1/3, and the association parameters of the third recommended video, the fourth recommended video, the fifth recommended video, and the sixth recommended video are all 0. The second recommended video, the third recommended video, the fourth recommended video, the fifth recommended video and the sixth recommended video are negative correlated videos of the current video. The mask video for the platform account includes a second recommended video, a third recommended video, a fourth recommended video, a fifth recommended video, a sixth recommended video.
Optionally, the degree of association between the mask video and the historical operating video is less than a second threshold. The association degree is the association parameter in the step 202. The second threshold is preset. For example, the value may be a default value or a value written by a person according to actual situations.
For example, in the video display interface shown in fig. 4, the association parameter of the first recommended video is 2/3, the association parameter of the second recommended video is 1/3, and the association parameters of the third recommended video, the fourth recommended video, the fifth recommended video, and the sixth recommended video are all 0. The second threshold is 1/4. The second recommended video, the third recommended video, the fourth recommended video, the fifth recommended video and the sixth recommended video are negative correlated videos of the current video. The shielding videos of the platform account include a third recommended video, a fourth recommended video, a fifth recommended video, a sixth recommended video.
In the above scheme, the video information determining device determines the associated video of the historical operation video according to the historical operation video and the association relation of the platform account, and determines the shielding video of the platform account according to the associated video. Therefore, video which is not interested in the platform account can be directly shielded, the possibility of recommending the video to the platform account again is avoided, and the video recommending effect is improved.
It will be appreciated that the above method of determining video information may be implemented by a device for determining video information. The video information determining device comprises a hardware structure and/or a software module for executing the functions. Those of skill in the art will readily appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present disclosure.
The embodiment of the disclosure may divide the functional modules of the above-described video information determination apparatus or the like according to the above-described method example, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present disclosure, the division of the modules is merely a logic function division, and other division manners may be implemented in actual practice.
The embodiment of the disclosure also provides a device for determining the video information. The determining device may be an electronic device, a chip in the electronic device, a control module in the electronic device for determining video information, or a client in the electronic device for determining video information.
Fig. 7 is a schematic diagram showing a configuration of a video information determining apparatus according to an exemplary embodiment. Referring to fig. 7, the determining apparatus includes: an acquisition module 701 and a determination module 702.
The obtaining module 701 is configured to perform a recommended video record of a current account for obtaining a current video, where the current video is a video that is played by the current account, and the recommended video record is at least used to record an interaction operation of the current account on the recommended video, and the recommended video is a video that is displayed on an associated interface for playing the video in the process of playing the video in the current account; for example, referring to fig. 2, the acquisition module 701 is configured to perform step 201.
The determining module 702 is configured to determine an association relationship between each recommended video and the current video at least according to the interaction operation of each current account on the recommended video and the current video acquired by the acquiring module 701. For example, referring to FIG. 2, the determination module 702 is configured to perform step 202.
Optionally, the determining module 702 is specifically configured to perform: according to the interaction operation of each current account on the recommended video and the current video, determining a positive association video and a negative association video, wherein the positive association video and the current video have a positive association relationship, the negative association video and the current video have a negative association relationship, and the association relationship comprises a positive association relationship and a negative association relationship; and recording the positive associated video and the negative associated video of the current video.
Optionally, the determining module 702 is specifically configured to perform: determining associated parameters of the recommended video based on the interactive operation of each current account on the recommended video and the playing operation of the current video, wherein the associated parameters are used for representing the probability of playing the recommended video under the condition that the current account performs the playing operation on the current video; based on the association parameters of the recommended videos, positive-associated videos and negative-associated videos are determined.
Optionally, the determining module 702 is specifically configured to perform: sequencing the recommended videos according to the size sequence of the association parameters, and determining positive association videos and negative association videos according to the sequenced recommended videos; or determining the recommended video with the association parameter meeting the first preset condition as a forward associated video; and determining the recommended video with the association parameter meeting the second preset condition as the negative association video.
Optionally, the determining module 702 is specifically configured to perform: determining a first behavior number and a second behavior number based on the interaction operation of each current account on the recommended video and the playing operation of the current video; the first row is: each current account performs the sum of the number of identical interactions for one recommended video; the second behavior is that the number of recommended videos is displayed on an associated interface of the played video in the process of playing the current video; and determining the ratio of the first behavior number to the second behavior number as the association parameter of the current video to one recommended video.
Optionally, the processing device further includes a processing module 703; a processing module 703 configured to perform: adding a first identifier for the forward association video, wherein the first identifier is used for indicating that the forward association video has a forward association relationship with the current video; and adding a second identifier for the negative association video, wherein the second identifier is used for indicating that the negative association video has a negative association relationship with the current video.
Fig. 8 is a schematic structural view of another video information determining apparatus according to an exemplary embodiment. Referring to fig. 8, the determining apparatus includes: an acquisition module 801 and a determination module 802.
The acquiring module 801 is configured to execute a video recommendation request sent by the platform account, read a historical operation video of the platform account, where the historical operation video is a video in which the platform account has performed interactive operation in a historical manner; for example, referring to fig. 5, the acquisition module 801 is configured to perform step 301.
The determining module 802 is configured to execute an association video based on the historical operation video, and determine a recommended video of the platform account, where the association video is a video having an association relationship with the historical operation video, and the association relationship is obtained based on the determining device of the video information in fig. 7. For example, referring to fig. 5, the acquisition module 801 is configured to perform step 302.
Optionally, in the association relationship, the recommended video and the historical operation video have a forward association relationship, and the association degree between the recommended video and the historical operation video is greater than a first threshold.
Optionally, the determining module 802 is further configured to execute an association video based at least on the historical operating video, determine a mask video for the platform account, wherein the mask video is a video having a negative association relationship with the historical operating video. For example, referring to fig. 6, the acquisition module 801 is configured to perform step 303.
Optionally, the degree of association between the mask video and the historical operating video is less than a second threshold.
Fig. 9 is a schematic diagram showing a hardware configuration of a video information determination apparatus according to an exemplary embodiment. The video information determining apparatus may include a processor 902, where the processor 902 is configured to execute application program codes to implement the video information determining method in the present disclosure.
The processor 902 may be a central processing unit (central processing unit, CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs in accordance with the present disclosure.
As shown in fig. 9, the video information determining apparatus may further include a memory 903. The memory 903 is used to store application code for executing the disclosed aspects and is controlled by the processor 902 for execution.
The memory 903 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), a compact disc (compact disc read-only memory) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 903 may be separate and coupled to the processor 902 through a bus 904. Memory 903 may also be integrated as processor 902.
As shown in fig. 9, the video information determining apparatus may further include a communication interface 901, wherein the communication interface 901, the processor 902, and the memory 903 may be coupled to each other, for example, via a bus 904. The communication interface 901 is used for information interaction with other devices, for example, information interaction between the determining device supporting video information and other devices.
It is to be noted that the apparatus structure shown in fig. 9 does not constitute a limitation of the determination means of the video information, and the determination means of the video information may include more or less components than those shown in fig. 9, or may combine some components, or may be a different arrangement of components.
In actual implementation, the functions implemented by the acquisition module 701, the determination module 702, and the processing module 703 may be implemented by the processor 902 shown in fig. 9 calling program code in the memory 903. The specific implementation process may refer to the description of the part of the method for determining video information shown in fig. 2, and will not be repeated here.
Fig. 10 is a schematic diagram showing a hardware configuration of another video information determination apparatus according to an exemplary embodiment. The means for determining video information may be relatively large, may vary in configuration or performance, and may include one or more processors 1001 and one or more memories 1002. The memory 1002 stores at least one instruction, where the at least one instruction is loaded and executed by the processor 1001 to implement the method for determining video information provided by the above-described method embodiments. Of course, the video information determining apparatus may also have a wired or wireless network interface, a keyboard, an input/output interface, and other components for implementing functions of the device, which are not described herein.
Another embodiment of the present disclosure also provides a computer-readable storage medium having instructions stored therein, which when executed on a video information determining apparatus performs the video information determining method of the embodiment shown in fig. 2 or performs the video information determining method of the embodiment shown in fig. 5.
In another embodiment of the present disclosure, there is also provided a computer program product comprising computer-executable instructions stored in a computer-readable storage medium. The processor of the video information determining apparatus may read the computer-executable instructions from the computer-readable storage medium, and the processor executes the computer-executable instructions to cause the video information determining apparatus to perform the video information determining method of the embodiment shown in fig. 2 or to perform the video information determining method of the embodiment shown in fig. 5.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
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 adaptations, uses, or adaptations of the disclosure following the general 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 is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (18)
1. A method for determining video information, comprising:
acquiring a recommended video record of a current account of a current video, wherein the current video is a video of which playing operation is executed by the current account, the recommended video record is at least used for recording interactive operation of the current account on the recommended video, and the recommended video is a video displayed on an associated interface of the playing video in the process of playing the video by the current account;
Determining a first behavior and a second behavior based on the interaction operation of each current account on the recommended video and the playing operation of each current account on the current video; the first behavior is the sum of the number of behaviors that the playing time of each current account for one recommended video is longer than a third threshold value; the second behavior is that the number of the recommended videos is displayed on an associated interface of the played video in the process of playing the current video;
determining the ratio of the first behavior number to the second behavior number as a correlation parameter from the current video to the recommended video, wherein the correlation parameter is used for representing the probability of performing a playing operation on the recommended video under the condition that a current account performs the playing operation on the current video;
and determining positive associated videos and negative associated videos based on the associated parameters of the recommended videos.
2. The determination method according to claim 1, wherein the positive-direction associated video has a positive-direction associated relation with the current video, the negative-direction associated video has a negative-direction associated relation with the current video, and the associated relation includes a positive-direction associated relation and a negative-direction associated relation; the method further comprises the steps of:
And recording the positive correlation video and the negative correlation video of the current video.
3. The method of determining according to claim 1, wherein the determining the positively correlated video and the negatively correlated video based on the correlation parameters of the recommended video includes:
sorting the recommended videos according to the size sequence of the association parameters, and determining the positive association video and the negative association video according to the sorted recommended videos;
or,
determining the recommended video with the association parameters meeting the first preset conditions as the forward associated video; and determining the recommended video with the association parameter meeting the second preset condition as the negative association video.
4. The determination method according to claim 2, characterized in that the determination method further comprises:
adding a first identifier for the forward associated video, wherein the first identifier is used for indicating that the forward associated video has a forward associated relationship with the current video;
and adding a second identifier for the negative association video, wherein the second identifier is used for indicating that the negative association video has a negative association relationship with the current video.
5. A method for determining video information, comprising:
Responding to a video recommendation request sent by a platform account, and reading historical operation videos of the platform account, wherein the historical operation videos are videos of the platform account subjected to interactive operation in a historical manner;
determining a recommended video of the platform account at least based on an associated video of the historical operating video, wherein the associated video is a video having an associated relation with the historical operating video, and the associated relation is obtained based on the method for determining video information according to any one of claims 1 to 4.
6. The method for determining according to claim 5, wherein,
in the association relationship, the recommended video and the historical operation video have a forward association relationship, and the association degree between the recommended video and the historical operation video is larger than a first threshold.
7. The determination method according to claim 5, characterized in that the determination method further comprises:
and determining a shielding video of the platform account at least based on the associated video of the historical operation video, wherein the shielding video is a video with a negative association relationship with the historical operation video.
8. The determination method according to claim 7, characterized in that the determination method further comprises:
The degree of association between the mask video and the historical operating video is less than a second threshold.
9. The device for determining the video information is characterized by comprising an acquisition module and a determination module;
the acquisition module is configured to execute a recommended video record of a current account for acquiring a current video, wherein the current video is a video of which playing operation is executed by the current account, the recommended video record is at least used for recording interactive operation of the current account on the recommended video, and the recommended video is a video displayed on an associated interface of the playing video in the process of playing the video by the current account;
the determining module is configured to determine a first behavior and a second behavior based on the interaction operation of each current account on the recommended video and the playing operation of each current account on the current video; the first behavior is the sum of the number of behaviors that the playing time of each current account for one recommended video is longer than a third threshold value; the second behavior is that the number of the recommended videos is displayed on an associated interface of the played video in the process of playing the current video;
The determining module is further configured to determine that the ratio of the first behavior to the second behavior is a correlation parameter from the current video to the one recommended video, where the correlation parameter is used to represent a probability of performing a play operation on the recommended video in a case that a current account performs the play operation on the current video;
the determination module is further configured to determine a positively-associated video and a negatively-associated video based on the association parameters of the recommended videos.
10. The determination device according to claim 9, wherein the positive-direction associated video has a positive-direction associated relation with the current video, the negative-direction associated video has a negative-direction associated relation with the current video, and the associated relation includes a positive-direction associated relation and a negative-direction associated relation;
the determination module is specifically configured to perform:
and recording the positive correlation video and the negative correlation video of the current video.
11. The determining apparatus of claim 9, wherein the determining apparatus comprises,
the determination module is specifically configured to perform:
sorting the recommended videos according to the size sequence of the association parameters, and determining the positive association video and the negative association video according to the sorted recommended videos;
Or,
determining the recommended video with the association parameters meeting the first preset conditions as the forward associated video; and determining the recommended video with the association parameter meeting the second preset condition as the negative association video.
12. The determination device according to claim 10, wherein the determination device further comprises a processing module;
the processing module is configured to perform:
adding a first identifier for the forward associated video, wherein the first identifier is used for indicating that the forward associated video has a forward associated relationship with the current video;
and adding a second identifier for the negative association video, wherein the second identifier is used for indicating that the negative association video has a negative association relationship with the current video.
13. The device for determining the video information is characterized by comprising an acquisition module and a determination module;
the acquisition module is configured to execute a video recommendation request sent by a platform account, and read historical operation video of the platform account, wherein the historical operation video is video of the platform account subjected to interactive operation in a historical manner;
the determining module is configured to execute an associated video based on the historical operation video, and determine a recommended video of the platform account, wherein the associated video is a video with an association relationship with the historical operation video, and the association relationship is obtained based on the determining device of the video information of any one of claims 9-12.
14. The apparatus according to claim 13, wherein,
in the association relationship, the recommended video and the historical operation video have a forward association relationship, and the association degree between the recommended video and the historical operation video is larger than a first threshold.
15. The apparatus according to claim 13, wherein,
the determination module is further configured to perform a determination of a mask video for the platform account based at least on the associated video of the historical operating video, wherein the mask video is a video having a negative association with the historical operating video.
16. The apparatus according to claim 15, wherein,
the degree of association between the mask video and the historical operating video is less than a second threshold.
17. A video information determining apparatus, comprising:
a processor;
a memory for storing instructions executable by the processor;
wherein the processor is configured to execute the instructions to implement the method of determining video information according to any of claims 1-4 or to implement the method of determining video information according to any of claims 5-8.
18. A computer-readable storage medium having instructions stored thereon, which, when executed by a processor of a video information determining apparatus, enable the video information determining apparatus to perform the video information determining method according to any one of claims 1 to 4 or enable the video information determining apparatus to perform the video information determining method according to any one of claims 5 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011287923.1A CN114513686B (en) | 2020-11-17 | 2020-11-17 | Video information determining method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011287923.1A CN114513686B (en) | 2020-11-17 | 2020-11-17 | Video information determining method, device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114513686A CN114513686A (en) | 2022-05-17 |
CN114513686B true CN114513686B (en) | 2024-04-16 |
Family
ID=81546643
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011287923.1A Active CN114513686B (en) | 2020-11-17 | 2020-11-17 | Video information determining method, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114513686B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117150077A (en) * | 2023-09-05 | 2023-12-01 | 北京有竹居网络技术有限公司 | Method, device, electronic equipment and medium for displaying recommended information set |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103870972A (en) * | 2012-12-07 | 2014-06-18 | 盛乐信息技术(上海)有限公司 | Data recommendation method and data recommendation system |
CN105868259A (en) * | 2015-12-29 | 2016-08-17 | 乐视致新电子科技(天津)有限公司 | Video recommendation method and device based on face identification |
CN108460060A (en) * | 2017-02-22 | 2018-08-28 | 合网络技术(北京)有限公司 | Video recommendation method and device |
WO2020205136A1 (en) * | 2019-03-29 | 2020-10-08 | Rovi Guides, Inc. | Content recommendation based on game progress |
-
2020
- 2020-11-17 CN CN202011287923.1A patent/CN114513686B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103870972A (en) * | 2012-12-07 | 2014-06-18 | 盛乐信息技术(上海)有限公司 | Data recommendation method and data recommendation system |
CN105868259A (en) * | 2015-12-29 | 2016-08-17 | 乐视致新电子科技(天津)有限公司 | Video recommendation method and device based on face identification |
CN108460060A (en) * | 2017-02-22 | 2018-08-28 | 合网络技术(北京)有限公司 | Video recommendation method and device |
WO2020205136A1 (en) * | 2019-03-29 | 2020-10-08 | Rovi Guides, Inc. | Content recommendation based on game progress |
Also Published As
Publication number | Publication date |
---|---|
CN114513686A (en) | 2022-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110378732B (en) | Information display method, information association method, device, equipment and storage medium | |
US9838743B2 (en) | Techniques for context aware video recommendation | |
CN107885796B (en) | Information recommendation method, device and equipment | |
CN106326391B (en) | Multimedia resource recommendation method and device | |
CN110727868B (en) | Object recommendation method, device and computer-readable storage medium | |
CN107426328B (en) | Information pushing method and device | |
CN107506367B (en) | Method and device for determining application display content and server | |
CN108399565A (en) | Financial product recommendation apparatus, method and computer readable storage medium | |
CN109862100B (en) | Method and device for pushing information | |
WO2015038444A2 (en) | Strength based modeling for recommendation system | |
CN116821475B (en) | Video recommendation method and device based on client data and computer equipment | |
CN113873330A (en) | Video recommendation method and device, computer equipment and storage medium | |
CN113836429A (en) | Book recommendation method, terminal and storage medium | |
CN114595016B (en) | Comment information display method, comment information generation method, comment information display device, comment information generation device and electronic equipment | |
CN110362751B (en) | Service recommendation method, device, computer equipment and storage medium | |
CN114513686B (en) | Video information determining method, device and storage medium | |
CN112423134A (en) | Video content recommendation method and device and computer equipment | |
CN112784103A (en) | Information pushing method and device | |
CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium | |
CN111683280B (en) | Video processing method and device and electronic equipment | |
CN111083534B (en) | Method and equipment for providing recommended video list | |
CN112749327A (en) | Content pushing method and device | |
CN114938458B (en) | Object information display method and device, electronic equipment and storage medium | |
CN115065870B (en) | Target business list display method and device, electronic equipment and storage medium | |
CN111625721B (en) | Content recommendation method and device |
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 |