CN114168794A - Video recommendation method and device, electronic equipment and storage medium - Google Patents

Video recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114168794A
CN114168794A CN202111433516.1A CN202111433516A CN114168794A CN 114168794 A CN114168794 A CN 114168794A CN 202111433516 A CN202111433516 A CN 202111433516A CN 114168794 A CN114168794 A CN 114168794A
Authority
CN
China
Prior art keywords
video
series
videos
priority
target
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.)
Pending
Application number
CN202111433516.1A
Other languages
Chinese (zh)
Inventor
池源
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Shareit Information Technology Co Ltd
Original Assignee
Beijing Shareit Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Shareit Information Technology Co Ltd filed Critical Beijing Shareit Information Technology Co Ltd
Priority to CN202111433516.1A priority Critical patent/CN114168794A/en
Publication of CN114168794A publication Critical patent/CN114168794A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/74—Browsing; Visualisation therefor
    • G06F16/743—Browsing; Visualisation therefor a collection of video files or sequences
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering

Abstract

The disclosed embodiment relates to a video recommendation method and device, an electronic device and a storage medium, wherein the video recommendation method is applied to a server side and comprises the following steps: if the update request is detected, determining the related video of the current video being played in the application program; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation; determining a target video to be recommended according to the associated video; determining the recommendation priority of the target video according to historical playing data; and sending the video information of the target video to the application program according to the recommendation priority. Therefore, the same series of videos of the currently played videos are provided for the application program based on a certain priority order, and therefore accuracy and intelligence of recommending the videos to the user are improved.

Description

Video recommendation method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of information technologies, and in particular, to a video recommendation method and apparatus, an electronic device, and a storage medium.
Background
In a User Generated Content (UGC) application (for example, trembling, fast-hand, etc.) of a mobile terminal Content stream, more and more series of short videos appear, for example, the same author indicates the same series in a plurality of videos by title, etc. When the user sees the videos in the information stream, the current video recommendation list usually does not contain the videos of the same series, and the requirement that the user wants to see all the videos of the same series cannot be met in real time.
The current major solutions include:
1. after clicking, jumping to a related content recommendation list, but the content recommendation list usually only contains a certain video of the same series, and a complete series video list cannot be provided.
2. And jumping to a work page of an author after clicking, and checking the same author in a video list in sequence, but the work page is often too many in video and difficult to search, and the work page can not accurately jump to a series of videos which a user needs to search.
Disclosure of Invention
The embodiment of the disclosure provides a video recommendation method and device, electronic equipment and a storage medium.
A first aspect of the embodiments of the present disclosure provides a video recommendation method, which is applied to a server side, and the method includes:
if the update request is detected, determining the related video of the current video being played in the application program; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation;
determining a target video to be recommended according to the associated video;
determining the recommendation priority of the target video according to historical playing data;
and sending the video information of the target video to the application program according to the recommendation priority.
Based on the above scheme, the determining the recommendation priority of the target video according to the historical playing data includes:
according to historical playing data, determining the strength sequence of the content relevance of the unplayed target video and the current video;
and determining the recommendation priority of the target video according to the strength sequence.
Based on the above scheme, the determining the recommendation priority of the target video according to the strength ranking includes:
according to the strong and weak sequencing, dividing the recommendation priority of the target video which is not played into a first priority, a second priority and a third priority;
wherein the strength of the content association between the target video and the current video of the first priority is stronger than the strength of the content association between the target video and the current video of the second priority;
the content relevance strength between the target video and the current video of the second priority is stronger than the content relevance strength between the target video and the current video of the third priority.
Based on the above scheme, the method further comprises:
if one recommendation priority comprises a plurality of target videos, setting the arrangement sequence of the plurality of target videos in the recommendation priority according to the sequence from strong to weak of the content relevance of the plurality of target videos and the current video;
the sending the video information of the target video to the application program according to the recommended priority comprises:
sending the video information of the target video to the application program according to the recommended priority and the arrangement sequence; and the video information is used for triggering the application program to sequence the videos in the recommendation priorities according to the sequencing order, and then recommending the target video according to the recommendation priorities.
Based on the above scheme, any two videos in the video series have a preset association relationship, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
A second aspect of the embodiments of the present disclosure provides a video recommendation method, which is applied to an application side, and the method includes:
determining whether a current video being played is contained in a video series; any two videos in the video series have a preset incidence relation;
if the current video is contained in a video series, sending an updating request to a server; the updating request is used for triggering the server to update the target video to be recommended;
receiving video information of the target video returned by the server;
and adding the target video to a video sequence to be played according to the video information.
Based on the above solution, the determining whether the current video being played is included in a video series includes:
after the current video which is being played is played for a preset time, whether the current video is contained in a video series is determined.
Based on the above scheme, the determining whether the current video is included in a video series includes:
acquiring series information of the published at least one video series from a server; the series of information at least includes: content information of videos in the video series, and/or publisher information of videos in the video series;
matching with the series information of the at least one video series based on the content information and/or the publisher information of the current video;
and if the current video and any one of the videos in one video series have a preset association relationship, determining that the current video is contained in the video series.
Based on the above scheme, any two videos in the video series have a preset association relationship, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
A third aspect of the embodiments of the present disclosure provides a video recommendation apparatus, which is applied to a server side, and the apparatus includes:
the first determining unit is used for determining the related video of the current video which is played in the application program if the updating request is detected; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation;
the second determining unit is used for determining a target video to be recommended according to the associated video;
the third determining unit is used for determining the recommendation priority of the target video according to historical playing data;
and the first sending unit is used for sending the video information of the target video to the application program according to the recommended priority.
Based on the foregoing scheme, the third determining unit is specifically configured to:
according to historical playing data, determining the strength sequence of the content relevance of the unplayed target video and the current video;
and determining the recommendation priority of the target video according to the strength sequence.
Based on the foregoing scheme, the third determining unit is specifically configured to:
according to the strong and weak sequencing, dividing the recommendation priority of the target video which is not played into a first priority, a second priority and a third priority;
wherein the strength of the content association between the target video and the current video of the first priority is stronger than the strength of the content association between the target video and the current video of the second priority;
the content relevance strength between the target video and the current video of the second priority is stronger than the content relevance strength between the target video and the current video of the third priority.
Based on the above scheme, the apparatus further comprises:
the setting unit is used for setting the arrangement sequence of the target videos in the recommendation priority according to the sequence from strong to weak of the content relevance of the target videos and the current video if one recommendation priority comprises the target videos;
the first sending unit is specifically configured to:
sending the video information of the target video to the application program according to the recommended priority and the arrangement sequence; and the video information is used for triggering the application program to sequence the videos in the recommendation priorities according to the sequencing order, and then recommending the target video according to the recommendation priorities.
Based on the above scheme, any two videos in the video series have a preset association relationship, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
A fourth aspect of the embodiments of the present disclosure provides a video recommendation apparatus, which is applied to an application side, and the apparatus includes:
a fourth determination unit for determining whether the current video being played is contained in a video series; any two videos in the video series have a preset incidence relation;
a second sending unit, configured to send an update request to the server if the current video is included in a video series; the updating request is used for triggering the server to update the target video to be recommended;
the receiving unit is used for receiving the video information of the target video returned by the server;
and the adding unit is used for adding the target video to a video sequence to be played according to the video information.
Based on the foregoing scheme, the fourth determining unit is specifically configured to:
after the current video which is being played is played for a preset time, whether the current video is contained in a video series is determined.
Based on the foregoing scheme, the fourth determining unit is specifically configured to:
acquiring series information of the published at least one video series from a server; the series of information at least includes: content information of videos in the video series, and/or publisher information of videos in the video series;
matching with the series information of the at least one video series based on the content information and/or the publisher information of the current video;
and if the current video and any one of the videos in one video series have a preset association relationship, determining that the current video is contained in the video series.
Based on the above scheme, any two videos in the video series have a preset association relationship, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
A fifth aspect of an embodiment of the present disclosure provides an electronic device, including:
a memory for storing processor-executable instructions;
a processor coupled to the memory;
wherein the processor is configured to execute the video recommendation method according to any of the preceding claims.
A sixth aspect of the embodiments of the present disclosure provides a non-transitory computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instructions implement the video recommendation method provided in any of the foregoing technical solutions.
The video recommendation method provided by the embodiment of the disclosure is applied to a server side, and comprises the following steps: if the update request is detected, determining the related video of the current video being played in the application program; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation; determining a target video to be recommended according to the associated video; determining the recommendation priority of the target video according to historical playing data; and sending the video information of the target video to the application program according to the recommendation priority. Therefore, videos which are in the same series with videos being played are provided for the application program and serve as videos recommended to the user on the basis of the recommendation priority sequence determined by the historical playing data, the association between the recommended videos and the historical playing behaviors can be better improved, the recommendation effect of the target videos is optimized on the basis of the recommendation priority, and the watching experience of the user is enriched.
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 invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic flow chart diagram illustrating a video recommendation method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart diagram illustrating a video recommendation method according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of an associated video information presentation interface according to an embodiment of the disclosure;
fig. 4 is a schematic structural diagram of a video recommendation apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a video recommendation apparatus according to an embodiment of the present disclosure;
fig. 6 is a flowchart illustrating a method for recommending a video by a server according to an embodiment of the disclosure;
fig. 7 is a flowchart illustrating a client video recommendation method according to an embodiment of the present disclosure.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
As shown in fig. 1, an embodiment of the present disclosure provides a video recommendation method applied to a server side, where the method includes:
s110: if the update request is detected, determining the related video of the current video being played in the application program; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation;
s120: determining a target video to be recommended according to the associated video;
s130: determining the recommendation priority of the target video according to historical playing data;
s140: and sending the video information of the target video to the application program according to the recommendation priority.
In the disclosed embodiment, the application program can be used for browsing and playing videos, such as applications installed on mobile devices, such as trembling, fast hands, and the like. The application may be any application capable of playing video.
The server may provide functional support for the application program, such as data processing, storage, and the like, for example, may be a cloud server of the application program, and the like. The update request is request information which is received by the server when the current video is played by the application program and is used for updating the video to be recommended.
In one embodiment, the video series includes a plurality of videos having a preset association relationship, for example, the preset association relationship may be a certain association relationship on a content, a certain association relationship on a title, a certain association relationship on a publisher of a video, or the like. Illustratively, a video series includes video titles "x episode 1", "x episode 2", and "x episode 3", so that the content of the videos in the video series can be considered as part of the content of a complete work. Based on this, if the current video being played is "x episode 1", the associated video is "x episode 2" and "x episode 3".
In another embodiment, the target video to be recommended is determined according to the associated videos, and all or part of the associated videos may be determined as the target video to be recommended. For example, the determining that the partial associated video is the target video may be determining that an associated video in the video series, the release time of which is later than that of the current video, is the target video, determining that an associated video in the video series, the release time of which is earlier than that of the current video, is the target video, determining that an associated video in the video series, which is not played, is the target video, and the like.
Here, when a video publisher distributes a plurality of videos in one video series, the distribution time of the videos often has a correlation with the arrangement position of the videos in the video series, and for example, in the video series of "x episode", the x episode 1 "with the most front arrangement position often has the earliest distribution time, and then" x episode 2 "," x episode 3 "…, and the like are distributed in the order of arrangement positions. Therefore, the content relevance between the associated video and the current video can be determined based on the publishing time, and the content relevance direction is the subsequent content or the previous content of the current video, so that accurate recommendation can be performed.
In one embodiment, S130 may include: determining the associated video which is not played according to the historical playing data; and determining the recommended priority of the target video according to the associated video which is not played. Here, the associated video that has not been played is determined according to the historical playing data, and the associated video that has not been played in the video series may be determined according to the historical playing data within a period of time, for example, historical playing data within a day, a month, or all.
In another embodiment, the video information of the target video may include title content, publisher information, and the like of the target video, and may further include an ontology of the target video or an index link of the target video, and the like, so that a user may view the target video directly in an application program or may enter into viewing the target video by clicking on the index link. And sending the video information of the target video to the application program according to the recommended priority, wherein the video information of the target video can be sent to the application program in sequence according to the priority order indicated by the recommended priority, and the video information of the recommended priority and the video information of the target video can also be recorded in a data packet together and sent to the application program.
Here, the recommendation priority may be used to instruct the application program to recommend the target videos in order of recommendation priority, for example, the target videos with higher recommendation priority are recommended with higher priority. Or, the recommendation priority may be used for determining a display position on an application interface of the application program according to the recommendation priority of the target video when the application program recommends each target video to be recommended. For example, the higher the recommendation priority, the closer the position distance between the display position of the corresponding target video and the current visual center point of the application program is, or the higher the recommendation priority, the further forward the display position of the corresponding target video is in the display queue of all target videos.
In this way, the related videos of the same series are determined according to the video series to which the current video belongs, and further, the videos to be recommended and the video recommendation sequence are provided for the application program based on the recommendation priority determined by the historical playing data. Therefore, the association relation between the recommended video and the current video and the association between the recommended video and the historical playing behavior can be better improved, the content which is possibly interested by the user at present can be better met, and the recommendation effect of the target video can be further optimized based on the setting of the recommendation priority.
In some embodiments, the S130 may include:
according to historical playing data, determining the strength sequence of the content relevance of the unplayed target video and the current video;
and determining the recommendation priority of the target video according to the strength sequence.
In the embodiment of the present disclosure, the content relevance may include relevance of picture content, text content, and the like in the video, and may also include relevance of title content or video publisher information, and the like. The strength sequencing of the content relevance between the unplayed target video and the current video is determined, and may be the strength sequencing of the content relevance between the analysis target video and the text content in the current video, or the strength sequencing of the relevance between the title content of the target video and the title content of the current video by performing text analysis on the title content of the target video and the title content of the current video.
For example, keywords indicating the arrangement positions of the videos in the video series in the title contents of the unplayed target video and the current video can be determined through text analysis, and further, based on the association degree of the keywords, the strong and weak ranking of the content association between the unplayed target video and the current video is determined. For example, when the title content of the current video is determined to be x episode 3, the keyword representing the arrangement position in the title content of the associated video which is not played in the same video series is determined to be the last number of the title content, so that the content relevance rank can be determined to be x episode 4, x episode 2, x episode 5 … and the like according to the proximity of the numbers.
In one embodiment, the rank of the relevance of the content may also be determined according to the publishing time of the unplayed target video and the current video, and the closer the publishing time is to the publishing time of the current video, the stronger the relevance of the content is. For example, publishers often publish in the order of the series of videos, namely "x episode 1", "x episode 2", "x episode 3", "x episode 4" …, and so on. Therefore, the relevance of the content determined based on the release time can effectively characterize the relevance between the associated videos.
In another embodiment, the rank of the content relevance may also be determined according to the arrangement position of the unplayed target video and the current video in the video series. The arrangement position may be determined according to a keyword representing the arrangement position in the title content of the video, for example, the keyword may be an upper, middle, lower or 1, 2, 3 or the like, which represents an order. For example, the closer the content is to the current video arrangement position, the stronger the content relevance, and if the arrangement position distance is the same, the stronger the content relevance of the target video having the arrangement position after the current video is. Illustratively, when the current video is "x episode 3", the content relevance strength ranking may be "x episode 4", "x episode 2", "x episode 5", "x episode 1" …, and so on.
In one embodiment, the method may further comprise: and determining the target video which is not played within the preset time according to the historical playing data. Here, the unplayed target video may be a target video that has not been played for a period of time determined from the historical play data, for example, a target video that has not been played for a day, a week, or the like, so as to suppress the possibility that the target video that has been played for a longer time before is of interest to the user at the current time but is not considered as a recommended video.
In another embodiment, the recommendation priority of the target video is determined according to the strong and weak orders, and the recommendation priority of the target video determined to be more associated with the content of the current video is higher, that is, the order of the recommendation priority from high to low corresponds to the order of the content association of the target video with the current video from strong to weak. In this way, the video with high relevance to the currently played video is preferentially recommended to the user based on the recommendation priority.
Therefore, the content relevance between the target video to be recommended and the current video can be represented through the recommendation priority, so that the application program can be instructed to recommend the target video to the user according to the content relevance order, and the intelligence and the recommendation effect of video recommendation are further optimized.
In some embodiments, the determining the recommendation priority of the target video according to the ranking of the strength and weakness includes:
according to the strong and weak sequencing, dividing the recommendation priority of the target video which is not played into a first priority, a second priority and a third priority;
wherein the strength of the content association between the target video and the current video of the first priority is stronger than the strength of the content association between the target video and the current video of the second priority;
the content relevance strength between the target video and the current video of the second priority is stronger than the content relevance strength between the target video and the current video of the third priority.
In the embodiment of the present disclosure, the recommended priority of the target video in the first priority is the highest, and the recommended priority of the target video in the second priority is lower than the first priority and higher than the third priority. Thus, the recommendation priority may be used to instruct the application to recommend the target video in the recommendation order of the first priority, the second priority, and the third priority.
In one embodiment, the target video of the first priority may be an unplayed target video adjacent to the current video in the video series, the second priority may be an unplayed target video arranged before or after the current video in the video series other than the first priority video, and the third priority may be a remaining unplayed target video in the video series other than the first and second priorities.
For example, when the current video is "x episode 4", the first priority may be "x episode 3" and "x episode 5", the second priority may be "x episode 1" and "x episode 2", and the third priority is the remaining associated videos.
In another embodiment, the target video of the first priority may be one of the target videos in the video series that is closest to the current video release time, the target video of the second priority may be one of the target videos in the video series that is next to the first priority video in proximity to the current video release time, and the target video of the third priority may be the target videos that remain unplayed except for the first and second priorities.
For example, the video of the first priority may be a next video of the current video in the video series, the video of the second priority may be a previous video of the current video in the video series, and the video of the third priority may be the remaining videos of the current video in the video series except for the first and second priority videos. For example, when the current video is x episode 3, the first priority is x episode 4, the second priority is x episode 2, and the third priority is x episode 1, x episode 5, x episode 6 …, etc.
In some embodiments, the method further comprises:
if one recommendation priority comprises a plurality of target videos, setting the arrangement sequence of the plurality of target videos in the recommendation priority according to the sequence from strong to weak of the content relevance of the plurality of target videos and the current video;
the sending the video information of the target video to the application program according to the recommended priority comprises:
sending the video information of the target video to the application program according to the recommended priority and the arrangement sequence; and the video information is used for triggering the application program to sequence the videos in the recommendation priorities according to the sequencing order, and then recommending the target video according to the recommendation priorities.
In the embodiment of the disclosure, for a plurality of target videos in the same recommendation priority, the videos are further sorted according to the strong and weak order of the relevance with the current video content, so that the video information can be used for instructing the application program to recommend the videos according to the recommendation priority and the arrangement order of the plurality of target videos in the same recommendation priority.
In one embodiment, the content relevance of the target videos and the current video is in an order from strong to weak, which may be an order from close to far of the distribution time of the target videos and the distribution time of the current video, that is, the closer the distribution time is to the distribution time of the current video, the stronger the content relevance of the current video is.
In another embodiment, the content relevance of the plurality of target videos and the current video is in an order from strong to weak, and the order of the arrangement positions of the plurality of target videos in the video series from close to far from the current video may also be used. For example, the closer the arrangement position is to the target video of the current video, the more strongly the content association with the current video.
Therefore, through the initial sequencing of the recommendation priority and the further sequencing of the arrangement sequence among the target videos in the same recommendation priority, the generated video information can indicate an application program to perform finer-grained and accurate sequencing when recommending the target videos, and the video recommendation effect is further optimized.
In some embodiments, the method may further comprise:
when a user uploads a video, performing text analysis on the title content of the uploaded video;
and determining the video series to which the uploaded video belongs based on the title content after the text analysis.
In the embodiment of the present disclosure, when it is detected that a user uploads a video, or when a classification instruction of an application is received, a video series to which the user belongs may be determined according to the content of a video title. The text analysis of the title content may be performed through an Application Programming Interface (API).
In one embodiment, the uploaded video is added to the belonging video series, for example, a series title or series identification information of the belonging video series is recorded in the video information, or the video title or video identification information of the uploaded video may also be recorded in the series information of the belonging video series.
In another embodiment, if the video series is not matched, the uploaded video is stored and published separately.
In some embodiments, any two videos in the video series have a preset association relationship therebetween, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
In the embodiment of the present disclosure, the preset association relationship between videos belonging to the same video series may be a content association relationship, for example, a video title content has an association relationship, a text content has an association relationship, and the like, or may also be an association relationship between publishers, for example, publishers are the same or publishers have a preset social relationship, and the like.
In one embodiment, the content relevance relationship may be a relevance relationship between video title contents, for example, text analysis and similarity matching are performed on the video title contents, and the text similarity of the title contents of any two videos in the same video series is not lower than a first preset value. Illustratively, video title content in the same video series tends to be in the form of the same episode name + video order.
In another embodiment, the relationship of the publisher associations may be the same for the publishers, or may be a preset social relationship for the publishers, for example, the number of interactions between publishers of any two videos in the same video series is not lower than a second preset value, or there are other social relationships between publishers, such as mutual attention, posting of at least one video series, and the like.
As shown in fig. 2, an embodiment of the present disclosure provides a video recommendation method applied to an application side, where the method includes:
s210: determining whether a current video being played is contained in a video series; any two videos in the video series have a preset incidence relation;
s220: if the current video is contained in a video series, sending an updating request to a server; the updating request is used for triggering the server to update the target video to be recommended;
s230: receiving video information of the target video returned by the server;
s240: and adding the target video to a video sequence to be played according to the video information.
In the embodiment of the present disclosure, it may be determined whether the current video is included in one video series according to the title content of the current video being played, for example, the series title content of each published video series is obtained, and the video series with the highest similarity between the series title content and the title content of the current video is determined as the video series including the current video. Or matching the video series containing the current video according to the preset incidence relation between the current video and the video in the video series. For example, if it is determined that the current video and a certain number of videos in a video series have a preset association relationship, it may be determined that the video series includes the current video.
In one embodiment, S210 may also be: and inquiring the video series containing the video identification information of the current video according to the video identification information of the current video. For example, video identification information of all videos included in a video series may be recorded in series information of the video series when the video series is distributed, and based on the series information of the video series and the video identification information of the current video, it may be determined whether the current video is included in one video series.
In another embodiment, S210 may also be: determining a series title or series identification information of a video series recorded in the video information according to the video information of the current video. For example, when a video or a video series is distributed, a video series to which the video belongs is determined, and a series title or series identification information of the video series is recorded in video information of the video. Therefore, according to the series title or series identification information in the video information, the affiliated video series can be directly inquired.
In another embodiment, it may also be determined whether the current video is included in a video series after the current video is played for a preset time period, for example, the preset time period may be 10 s. The preset duration may also be determined according to the total video duration of the current video, for example, the preset duration may be set to be one tenth of the total video duration of the current video, and so on.
In one embodiment, the received video information may be sent by the server in the order indicated by the recommendation priority, so that the target video is added to the video sequence to be played according to the video information, and the target video may be added to the video sequence to be played according to the order of the received video information.
In another embodiment, the received video information may also carry a recommendation priority of a target video to be recommended. Therefore, the target video is added to the video sequence to be played according to the video information, and the target video can also be added to the video sequence to be played according to the sequence indicated by the recommended priority recorded in the video information.
In yet another embodiment, the received video information may also carry a recommendation priority of a target video to be recommended and an arrangement order of a plurality of target videos in the same recommendation priority. Therefore, the target videos are added to the video sequence to be played according to the video information, and the target videos in each recommendation priority can be sorted according to the sorting order recorded in the video information and added to the video sequence to be played according to the order indicated by the recommendation priority.
Here, the video sequence to be played may be a sequence used by the application program for arranging videos to be recommended, for example, when the application program plays a current video, if an instruction (for example, an operation such as sliding a playing interface) that a user requests to watch a next video is detected, the first video in the video sequence to be played starts to be played, and the recommended playing is sequentially performed according to the video sequence in the video sequence to be played.
In one embodiment, step S240 may include: displaying the associated video in the target video to be recommended on a playing interface of the current video according to the video information; and if detecting that the user selects one of the associated videos, playing the selected associated video, and adding the rest videos except the selected video in the target video to the video sequence to be played according to the recommended priority. Here, the displaying of the associated video on the play interface may be displaying the associated video on the bottom or the side of the play interface, or displaying the video cover and/or the video title of the associated video on the bottom or the side of the play interface, as shown in fig. 3, for example, regarding the associated video as a series video of the same video series, and displaying the video titles "title 1" … "title N" of the 1 st to nth associated videos in the form of a series video list.
Based on the above, the associated videos are displayed during the current video playing so as to determine whether the user is interested in the associated videos, if it is detected that the user selects one associated video, the remaining target videos are added to the video sequence to be played, and targeted video recommendation is performed, so that the video watching requirement of the user is fully met, and unnecessary video sequence updating to be played is not performed when the user is not interested in the video sequence.
In another embodiment, the target video is added to the video sequence to be played, and the target video may be added to the video sequence to be played according to a recommended priority, or after a plurality of target videos in the same recommended priority are sorted according to the sorting order, the target videos are added to the video sequence to be played according to the order indicated by the recommended priority.
In another embodiment, the target video may be added to the top of the video sequence to be played, and the original video to be played in the video sequence to be played is reordered according to the release time.
In one embodiment, upon detecting a user publishing a video, a series of videos to which the published video may belong may be presented. Accordingly, the method may further comprise: when the videos uploaded by the user are detected, a certain number of recently uploaded video series are provided for the user to select whether the currently uploaded video belongs to one of the video series. If so, recording the corresponding relationship between the uploaded video and the video series, for example, recording video identification information in the series information of the video series, or recording the series identification information of the video series in the video information of the video. And if the fact that the user selects the video series is not detected, issuing a classification instruction to the server for indicating the server to determine the video series to which the currently uploaded video belongs.
Here, a certain number of recently uploaded video series are provided, the certain number may be 3, 5, and the like, or the video series uploaded within a certain period of time may be provided, for example, all the video series uploaded within 5 days from the current time are provided.
Therefore, when the current video is detected to belong to the video series, the target video to be recommended and the recommendation priority thereof are obtained from the server, unnecessary searching for the current video without the video associated with the series is reduced, and the working pressure of the server can be reduced. Furthermore, the video sequence to be played is updated based on the video information provided by the server, so that the intelligence of video recommendation playing can be fully improved.
In some embodiments, the S210 may include:
after the current video which is being played is played for a preset time, whether the current video is contained in a video series is determined.
In the embodiment of the present disclosure, based on the playing interval of the preset time length, it may be better determined whether the user is interested in the current video, for example, in an application program, the user may decide whether to instruct to play the next video based on whether the user is interested after the video is played, and the preset time length may be 10s, 20s, and the like. After the preset time is played, the user is often indicated to be interested in the current video, and at the moment, the video series are determined and the video information with the recommendation priority is acquired, so that the interest requirements of the user can be better met, and unnecessary target video acquisition operations are reduced.
In some embodiments, the S210 may include:
acquiring series information of the published at least one video series from a server; the series of information at least includes: content information of videos in the video series, and/or publisher information of videos in the video series;
matching with the series information of the at least one video series based on the content information and/or the publisher information of the current video;
and if the current video and any one of the videos in one video series have a preset association relationship, determining that the current video is contained in the video series.
In the embodiment of the present invention, the series information may record content information and/or distributor information of all videos belonging to the video series, and the content information and/or distributor information of the current video may be recorded in the video information of the current video. Based on the matching of the series information and the video information of the current video, a preset association relationship may be determined.
In one embodiment, since all videos in one video series have a preset association relationship, if it is determined that the current video and one video in one video series have a preset association relationship, it may be determined that the current video and other videos in the video series also have a preset association relationship.
In another embodiment, it may also be determined that the current video is included in the video series if the current video and a predetermined number of videos of the video series have a predetermined association relationship. Here, the preset number may be 1, 2, 3, etc.
Therefore, the video series to which the current video belongs can be directly determined based on the preset incidence relation, and the video recommendation efficiency is improved.
In some embodiments, any two videos in the video series have a preset association relationship therebetween, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
As shown in fig. 4, an embodiment of the present disclosure provides a video recommendation apparatus applied to a server side, where the apparatus includes:
a first determining unit 110, configured to determine, if an update request is detected, a video associated with a current video being played in an application; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation;
a second determining unit 120, configured to determine, according to the associated video, a target video to be recommended;
a third determining unit 130, configured to determine a recommendation priority of the target video according to historical playing data;
a first sending unit 140, configured to send video information of the target video to the application program according to the recommended priority.
In some embodiments, the third determining unit 130 is specifically configured to:
according to historical playing data, determining the strength sequence of the content relevance of the unplayed target video and the current video;
and determining the recommendation priority of the target video according to the strength sequence.
In some embodiments, the third determining unit 130 is specifically configured to:
according to the strong and weak sequencing, dividing the recommendation priority of the target video which is not played into a first priority, a second priority and a third priority;
wherein the strength of the content association between the target video and the current video of the first priority is stronger than the strength of the content association between the target video and the current video of the second priority;
the content relevance strength between the target video and the current video of the second priority is stronger than the content relevance strength between the target video and the current video of the third priority.
In some embodiments, the apparatus further comprises:
the setting unit is used for setting the arrangement sequence of the target videos in the recommendation priority according to the sequence from strong to weak of the content relevance of the target videos and the current video if one recommendation priority comprises the target videos;
the first sending unit 140 is specifically configured to:
sending the video information of the target video to the application program according to the recommended priority and the arrangement sequence; and the video information is used for triggering the application program to sequence the videos in the recommendation priorities according to the sequencing order, and then recommending the target video according to the recommendation priorities.
In some embodiments, any two videos in the video series have a preset association relationship therebetween, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
As shown in fig. 5, an embodiment of the present disclosure provides a video recommendation apparatus applied to an application side, where the apparatus includes:
a fourth determination unit 210 for determining whether the current video being played is contained in a video series; any two videos in the video series have a preset incidence relation;
a second sending unit 220, configured to send an update request to the server if the current video is included in a video series; the updating request is used for triggering the server to update the target video to be recommended;
a receiving unit 230, configured to receive video information of the target video returned by the server;
an adding unit 240, configured to add the target video to a video sequence to be played according to the video information.
In some embodiments, the fourth determining unit 210 is specifically configured to:
after the current video which is being played is played for a preset time, whether the current video is contained in a video series is determined.
In some embodiments, the fourth determining unit 210 is specifically configured to:
acquiring series information of the published at least one video series from a server; the series of information at least includes: content information of videos in the video series, and/or publisher information of videos in the video series;
matching with the series information of the at least one video series based on the content information and/or the publisher information of the current video;
and if the current video and any one of the videos in one video series have a preset association relationship, determining that the current video is contained in the video series.
In some embodiments, any two videos in the video series have a preset association relationship therebetween, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
One specific example is provided below in connection with any of the embodiments described above:
the embodiment of the disclosure provides a real-time content recommendation system and method based on user behaviors, which allow a user to independently select an affiliated episode, allow the user to display a series of videos on a current page when the user sees the videos, allow the user to quickly select any one of the series of videos, shorten a user operation path, and accurately display related series of videos.
The scheme has the following flow:
step 1: the client regularly updates the episode list which is formally released by the current user. When a user publishes a video, filling in video Title content (Title), showing 3-5 episodes recently published by the user in real time, allowing the user to select the episode to which the currently published video belongs, and processing the episode at a server by default when the user does not select the episode.
Step 2: the server analyzes whether the titles belong to the same series or not by using a regular expression according to the video titles uploaded by the user, and stores series information (series info) for the video, wherein specific values of the series information can comprise a series name (series name) and/or a series index (series index).
Specifically, as shown in fig. 6, the server adds episode information according to video information uploaded by the user, and when the episode information is not selected by the user, a text analysis API is performed on video title content, and the titles are analyzed to determine whether the episodes belong to the same series, so as to store a series of information for the video, for example, "milk health promotion" (first) "," milk health promotion "(second)", "milk health promotion" (third) ", and" milk health promotion "(fourth)", so as to belong to the same series of "milk health promotion". The stored series is named as 'health preserving of milk', and the series indexes are 1, 2, 3 and 4 respectively.
Step 3: as shown in fig. 7, when the user starts playing the video for more than T-10 s (the playing time period T allows dynamic adjustment), it is determined whether the current video is a series video. When the current video is a serial video, sending a stored serial video list SerisList to a server side, wherein the serial video list can be adjusted according to the watching history behavior of the user and the serial video list. And (3) a specific sequencing display strategy, which is in mixed sequencing according to the priority and the release time, wherein the lower the priority value is, the earlier the priority is displayed, and the latest release time is displayed firstly:
1. the video viewed by the user is no longer shown
2. The next set of the current video of the user is displayed with the priority of 0;
3. the previous set of the current video of the user is relatively prior, and the priority is 1;
4. other series of videos of the user with the priority of 2 are displayed firstly according to the latest release time
5. And (4) recommending other videos to the user, wherein the priority is 3, and the videos are displayed firstly according to the latest release time.
For example, when looking at "health of milk" (two), the recommendation list may include: three health-preserving of milk, one of the first one, videos not seen by all users who started.
Step 4: when the series video list is acquired and the user is still watching the current video at this time, the video list with a fixed height is displayed at the bottom of the current mobile terminal device, and the display content may include: video covers and video titles. Allowing the user to click on a particular video in the list and allowing the user to slide through more related videos and allowing the user to close the list. The video list can be displayed in a vertical mode or a horizontal mode.
Step 5: when the user clicks any video in the list, the series video list disappears, the current clicked video starts to be played, and the video list acquired from the server is added to the recommendation list. When the user does not click, the current playing order is not updated. For example: when the user clicks 'health of milk' (one), the user starts to play 'health of milk' (one), and 2, 3 and 4 are added into the recommendation list, so that the user can watch the milk in sequence.
An embodiment of the present disclosure provides an electronic device, including:
a memory for storing processor-executable instructions;
a processor connected with the memory;
wherein the processor is configured to execute the pressure measurement method provided by any of the above technical solutions.
The processor may include various types of storage media, which are non-transitory computer storage media capable of continuing to remember the information stored thereon after a power failure of the electronic device.
The processor may be connected to the memory via a bus or the like for reading the executable program stored in the memory, for example, to be able to perform one or more of the methods described in the preceding claims.
An embodiment of the present disclosure shows a structure of an electronic device. The electronic device includes a processing component that further includes one or more processors, and memory resources, represented by memory, for storing instructions, such as application programs, that are executable by the processing component. The application program stored in the memory may include one or more modules that each correspond to a set of instructions. Furthermore, the processing component is configured to execute the instructions to perform any of the methods described above as applied to the electronic device, for example, the methods described in one or more of the preceding claims.
The electronic device may also include a power supply component configured to perform power management of the electronic device, a wired or wireless network interface configured to connect the electronic device to a network, and an input-output (I/O) interface. The electronic device may operate based on an operating system stored in memory, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
The embodiment of the present disclosure provides a non-transitory computer-readable storage medium, and when instructions in the storage medium are executed by a processor of a computer, the computer is enabled to execute the pressure measurement method according to one or more of the foregoing technical solutions.
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 (20)

1. A video recommendation method is applied to a server side, and comprises the following steps:
if the update request is detected, determining the related video of the current video being played in the application program; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation;
determining a target video to be recommended according to the associated video;
determining the recommendation priority of the target video according to historical playing data;
and sending the video information of the target video to the application program according to the recommendation priority.
2. The method of claim 1, wherein determining the recommendation priority for the target video based on historical play data comprises:
according to historical playing data, determining the strength sequence of the content relevance of the unplayed target video and the current video;
and determining the recommendation priority of the target video according to the strength sequence.
3. The method of claim 2, wherein determining the recommendation priority of the target video according to the ranking of the strength and weakness comprises:
according to the strong and weak sequencing, dividing the recommendation priority of the target video which is not played into a first priority, a second priority and a third priority;
wherein the strength of the content association between the target video and the current video of the first priority is stronger than the strength of the content association between the target video and the current video of the second priority;
the content relevance strength between the target video and the current video of the second priority is stronger than the content relevance strength between the target video and the current video of the third priority.
4. The method of claim 3, further comprising:
if one recommendation priority comprises a plurality of target videos, setting the arrangement sequence of the plurality of target videos in the recommendation priority according to the sequence from strong to weak of the content relevance of the plurality of target videos and the current video;
the sending the video information of the target video to the application program according to the recommended priority comprises:
sending the video information of the target video to the application program according to the recommended priority and the arrangement sequence; and the video information is used for triggering the application program to sequence the videos in the recommendation priorities according to the sequencing order, and then recommending the target video according to the recommendation priorities.
5. The method of claim 1, wherein any two videos in the video series have a preset association relationship therebetween, comprising:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
6. A video recommendation method applied to an application side, the method comprising:
determining whether a current video being played is contained in a video series; any two videos in the video series have a preset incidence relation;
if the current video is contained in a video series, sending an updating request to a server; the updating request is used for triggering the server to update the target video to be recommended;
receiving video information of the target video returned by the server;
and adding the target video to a video sequence to be played according to the video information.
7. The method of claim 6, wherein determining whether the current video being played is contained in a video series comprises:
after the current video which is being played is played for a preset time, whether the current video is contained in a video series is determined.
8. The method of claim 7, wherein determining whether the current video is included in a video sequence comprises:
acquiring series information of the published at least one video series from a server; the series of information at least includes: content information of videos in the video series, and/or publisher information of videos in the video series;
matching with the series information of the at least one video series based on the content information and/or the publisher information of the current video;
and if the current video and any one of the videos in one video series have a preset association relationship, determining that the current video is contained in the video series.
9. The method of claim 6, wherein any two videos in the video series have a preset association relationship therebetween, comprising:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
10. A video recommendation apparatus, applied to a server side, the apparatus comprising:
the first determining unit is used for determining the related video of the current video which is played in the application program if the updating request is detected; the associated video and the current video belong to the same video series; any two videos in the video series have a preset incidence relation;
the second determining unit is used for determining a target video to be recommended according to the associated video;
the third determining unit is used for determining the recommendation priority of the target video according to historical playing data;
and the first sending unit is used for sending the video information of the target video to the application program according to the recommended priority.
11. The apparatus according to claim 10, wherein the third determining unit is specifically configured to:
according to historical playing data, determining the strength sequence of the content relevance of the unplayed target video and the current video;
and determining the recommendation priority of the target video according to the strength sequence.
12. The apparatus according to claim 11, wherein the third determining unit is specifically configured to:
according to the strong and weak sequencing, dividing the recommendation priority of the target video which is not played into a first priority, a second priority and a third priority;
wherein the strength of the content association between the target video and the current video of the first priority is stronger than the strength of the content association between the target video and the current video of the second priority;
the content relevance strength between the target video and the current video of the second priority is stronger than the content relevance strength between the target video and the current video of the third priority.
13. The apparatus of claim 12, further comprising:
the setting unit is used for setting the arrangement sequence of the target videos in the recommendation priority according to the sequence from strong to weak of the content relevance of the target videos and the current video if one recommendation priority comprises the target videos;
the first sending unit is specifically configured to:
sending the video information of the target video to the application program according to the recommended priority and the arrangement sequence; and the video information is used for triggering the application program to sequence the videos in the recommendation priorities according to the sequencing order, and then recommending the target video according to the recommendation priorities.
14. The apparatus of claim 10, wherein any two videos in the video series have a predetermined association relationship therebetween, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
15. A video recommendation apparatus applied to an application side, the apparatus comprising:
a fourth determination unit for determining whether the current video being played is contained in a video series; any two videos in the video series have a preset incidence relation;
a second sending unit, configured to send an update request to the server if the current video is included in a video series; the updating request is used for triggering the server to update the target video to be recommended;
the receiving unit is used for receiving the video information of the target video returned by the server;
and the adding unit is used for adding the target video to a video sequence to be played according to the video information.
16. The apparatus according to claim 15, wherein the fourth determining unit is specifically configured to:
after the current video which is being played is played for a preset time, whether the current video is contained in a video series is determined.
17. The apparatus according to claim 16, wherein the fourth determining unit is specifically configured to:
acquiring series information of the published at least one video series from a server; the series of information at least includes: content information of videos in the video series, and/or publisher information of videos in the video series;
matching with the series information of the at least one video series based on the content information and/or the publisher information of the current video;
and if the current video and any one of the videos in one video series have a preset association relationship, determining that the current video is contained in the video series.
18. The apparatus of claim 15, wherein any two videos in the video series have a predetermined association relationship therebetween, including:
any two videos in the video series meet the content relevance relationship;
and/or the presence of a gas in the gas,
the publishers of any two videos in the video series meet the condition that the publishers are the same or have a preset social relationship.
19. An electronic device, comprising:
a memory for storing processor-executable instructions;
a processor coupled to the memory;
wherein the processor is configured to perform the video recommendation method as provided in any one of claims 1 to 9.
20. A non-transitory computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, implement the video recommendation method provided in any one of claims 1 to 9.
CN202111433516.1A 2021-11-29 2021-11-29 Video recommendation method and device, electronic equipment and storage medium Pending CN114168794A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111433516.1A CN114168794A (en) 2021-11-29 2021-11-29 Video recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111433516.1A CN114168794A (en) 2021-11-29 2021-11-29 Video recommendation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114168794A true CN114168794A (en) 2022-03-11

Family

ID=80481567

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111433516.1A Pending CN114168794A (en) 2021-11-29 2021-11-29 Video recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114168794A (en)

Similar Documents

Publication Publication Date Title
US11550451B2 (en) Systems and methods for providing and updating live-streaming online content in an interactive web platform
US20180253173A1 (en) Personalized content from indexed archives
US20180039627A1 (en) Creating a content index using data on user actions
CN109241242B (en) Live broadcast room topic recommendation method and device, server and storage medium
US8566315B1 (en) Sequenced video segment mix
US11055340B2 (en) System and method for creating synopsis for multimedia content
US7840563B2 (en) Collective ranking of digital content
US8595375B1 (en) Segmenting video based on timestamps in comments
US8606725B1 (en) Automatic client-side user-behavior analysis for inferring user intent
CN104782138B (en) Thumbnail image selects system, method and computer-readable medium
US8880623B2 (en) Prioritization in a continuous video playback experience
US20100287475A1 (en) Content summary and segment creation
US20100077290A1 (en) Time-tagged metainformation and content display method and system
US9088808B1 (en) User interaction based related videos
US10747802B1 (en) Image recommendations for thumbnails for online media items based on user activity
EP3322192A1 (en) Method for intuitive video content reproduction through data structuring and user interface device therefor
US10051044B2 (en) Community space for sharing content
US20170272793A1 (en) Media content recommendation method and device
CN110177306A (en) Video broadcasting method, device, mobile terminal and medium based on mobile terminal
US20230161826A1 (en) Systems and methods for processing emojis in a search and recommendation environment
CN111046292A (en) Live broadcast recommendation method and device, computer-readable storage medium and electronic device
CN111949807A (en) Data processing method, data processing device, computer equipment and storage medium
RU2678088C1 (en) Programming of notifications based on following user activity
CN111104583A (en) Live broadcast room recommendation method, storage medium, electronic device and system
CN114168794A (en) Video recommendation method and device, electronic equipment and storage medium

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