CN112714359A - Video recommendation method and device, computer equipment and storage medium - Google Patents
Video recommendation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112714359A CN112714359A CN201911016642.XA CN201911016642A CN112714359A CN 112714359 A CN112714359 A CN 112714359A CN 201911016642 A CN201911016642 A CN 201911016642A CN 112714359 A CN112714359 A CN 112714359A
- Authority
- CN
- China
- Prior art keywords
- video
- browsing record
- video browsing
- target
- record table
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- 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]
- H04N21/20—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
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—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)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The disclosure relates to a video recommendation method, a video recommendation device, a computer device and a storage medium, wherein a first video browsing record table is obtained when detecting that an increment in the first video browsing record table meets a target condition; extracting video browsing records of a plurality of target videos from the first video browsing record table to generate a second video browsing record table; when any target video in the second video browsing record list is expired or the video browsing record is expired, deleting the video browsing record corresponding to the target video from the second video browsing record list; filtering repeated videos in a video list to be recommended of any user and in the first video browsing record table and the second video browsing record table; and recommending the videos to the user based on the filtered video list to be recommended. According to the embodiment of the disclosure, the video browsing record with the long life cycle is extracted, and the offline video browsing record table is established for duplicate removal, so that the duplicate removal accuracy rate of the video with the long life cycle is improved, and repeated recommendation to a user is avoided.
Description
Technical Field
The present disclosure relates to the field of video recommendation technologies, and in particular, to a video recommendation method and apparatus, a computer device, and a storage medium.
Background
In a short video recommendation scene, a user obtains a new recommended video every time the user refreshes, the repeatedly recommended video affects user experience, resources of video display positions are wasted, and more high-quality videos cannot be displayed, so that the videos which are watched by the user in the recommended videos need to be deduplicated; in addition to the above scenarios, deduplication is also needed in some other video recommendation scenarios to achieve effective delivery of video.
At present, a video recommendation strategy is to set a corresponding validity period according to the quality of video content, so that a video can be recommended in the validity period, correspondingly, a longer life cycle can be set for a video with better content quality, and the video can be repeatedly recommended to a user in the life cycle, so that the video can be released for a long time to obtain the maximum benefit; meanwhile, for videos that the user has viewed, a video browsing record table is also needed to record videos that the user has browsed, and due to the reasons of limited storage space and the like, the video browsing record table can also set a corresponding validity period, and outdated video browsing records in the video browsing record table are deleted at regular time.
However, the above conventional scheme has a problem that, for a video with better content quality, the life cycle of the video is usually much longer than the validity period of the video browsing record table, and when the video browsing record of a video with a long life cycle is after the video browsing record table is over, the life cycle of the video may still be valid, which may cause the video to be pushed to the user again, which affects the recommendation efficiency of recommending the video and wastes the resources of video display. Therefore, how to effectively perform deduplication on a target video becomes a problem to be solved at present.
Disclosure of Invention
The present disclosure provides a video recommendation method, apparatus, computer device and storage medium, to at least solve the problem in the related art that duplicate removal cannot be performed on a video with a long life cycle. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a video recommendation method, including
When detecting that the increment in a first video browsing record table meets a target condition, acquiring the first video browsing record table, wherein the first video browsing record table comprises video browsing records of a plurality of users, and one video browsing record is used for recording video information of videos browsed by the users;
extracting video browsing records of a plurality of target videos from the first video browsing record table to generate a second video browsing record table, wherein the second video browsing record table records the set valid period of the video browsing record of each target video, and the valid period of the video browsing record is used for indicating the valid duration of the video browsing record in the second video browsing record table;
when the validity period of any video browsing record in the second video browsing record table is expired, deleting the video browsing record from the second video browsing record table;
matching the video information of the video to be recommended in the video list to be recommended of any user with the video information corresponding to the video browsing record in the second video browsing record list, and filtering the video to be recommended matched with the video information;
video recommendation based on filtered video list to be recommended
In an embodiment of the present disclosure, the extracting video browsing records of a plurality of target videos from the first video browsing record table and generating a second video browsing record table includes:
acquiring a target video list, wherein the target video list comprises video information of a plurality of target videos;
and matching the video information corresponding to the video browsing record in the first video browsing record list with the video information of the target video list, extracting a plurality of video browsing records matched with the video information, and generating a second video browsing record list.
In an embodiment of the present disclosure, after generating the second video browsing recording list, the method further includes:
matching the video information of each target video in the second video browsing record list with the target video information in the target cache;
and filtering the video browsing record with the video information which is not successfully matched from the second video browsing record table to obtain the filtered second video browsing record table.
In an embodiment of the present disclosure, the video browsing record is stored in the database with a key-value key value, wherein the user information in the video browsing record is stored with a key value, and the video information corresponding to the user information is stored with a value.
According to a second aspect of the embodiments of the present disclosure, there is provided a video recommendation apparatus including:
the acquisition unit is configured to acquire a first video browsing record table when detecting that the increment in the first video browsing record table meets a target condition, wherein the first video browsing record table comprises video browsing records of a plurality of users, and one video browsing record is used for recording video information of videos browsed by the users;
the generating unit is configured to extract video browsing records of which the valid periods of a plurality of target videos are greater than a preset time length from the first video browsing record table, set the valid period of the video browsing record of each target video, and generate a second video browsing record table, wherein the valid period of the target video is used for indicating the valid time length of the target video recommended in the video recommending system, and the valid period of the video browsing record is used for indicating the time length of the video browsing record valid in the second video browsing record table;
the filtering unit is configured to delete a video browsing record from the second video browsing record table when the validity period of any one video browsing record in the second video browsing record table expires;
the duplication removing unit is configured to match video information of a video to be recommended in a video list to be recommended of any user with video information corresponding to video browsing records in the second video browsing record table, and filter the video to be recommended with the video information matched;
and the recommending unit is configured to recommend videos based on the filtered list of videos to be recommended.
In one embodiment of the present disclosure, the generating unit is configured to:
acquiring a target video list, wherein the target video list comprises video information of a plurality of target videos;
and matching the video information corresponding to the video browsing record in the first video browsing record list with the video information of the target video list, extracting a plurality of video browsing records matched with the video information, and generating a second video browsing record list.
In an embodiment of the present disclosure, the generating unit is further configured to:
matching the video information of each target video in the second video browsing record list with the target video information in the target cache;
and filtering the video browsing record with the video information which is not successfully matched from the second video browsing record table to obtain the filtered second video browsing record table.
In an embodiment of the present disclosure, the video browsing record is stored in the database with a key-value key value, wherein the user information in the video browsing record is stored with a key value, and the video information corresponding to the user information is stored with a value.
According to a third aspect of embodiments of the present disclosure, there is provided a computer device comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the video recommendation method of any one of the above.
According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium having instructions that, when executed by a processor of a computer device, enable the computer device to perform the video recommendation method of any one of the above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising executable instructions that, when executed by a processor of a computer device, enable the computer device to perform the video recommendation method of any one of the above.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects: by extracting the video browsing records with long life cycle and establishing an offline video browsing record table for the video browsing records to independently perform video deduplication, the deduplication accuracy rate of the videos with long life cycle is improved, and repeated recommendation of target videos to users is avoided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
Fig. 1 is a flow diagram illustrating a video recommendation method according to an example embodiment.
Fig. 2 is a flowchart illustrating an implementation of generating a second video browsing record table according to an exemplary embodiment.
Fig. 3 is a diagram illustrating generation of a second video browsing record table according to an exemplary embodiment.
Fig. 4 is a flow chart illustrating an implementation of setting a validity period for a second video browsing record table according to an exemplary embodiment.
Fig. 5 is a diagram illustrating setting of a validity period for a video browsing record in the second video browsing record table according to an exemplary embodiment.
Fig. 6 is a flow chart illustrating an implementation of maintaining a second video browsing record table according to an example embodiment.
Fig. 7 is a diagram illustrating maintenance of a second video browsing record table in accordance with an exemplary embodiment.
Fig. 8 is a flow diagram illustrating an implementation of deduplication for video in accordance with an example embodiment.
Fig. 9 is a diagram illustrating a process of de-duplicating a recommended video list according to an example embodiment.
Fig. 10 is a block diagram illustrating a video recommendation device according to an example embodiment.
FIG. 11 is a block diagram illustrating a video recommendation system in accordance with an exemplary embodiment.
FIG. 12 is a block diagram illustrating a computer device according to an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
In some specific scenes, such as embedded pages of apps, because the life cycle of videos recommended to users is long or short, and the video browsing record table for recording video browsing records of users also has a validity period, when the life cycle of a video recommended to a user is longer than the validity period of the video browsing records in the video browsing record table, repeated videos are easily recommended to the user, and therefore, how to effectively duplicate a target video becomes a problem to be solved at present. In order to solve the above problem, a long-life-cycle video browsing record can be extracted separately, a long-life-cycle video browsing record table is established for maintenance separately, and accurate deduplication of a long-life-cycle video is achieved based on the long-life-cycle video browsing record table, and fig. 1 is a flowchart of a video recommendation method according to an exemplary embodiment, as shown in fig. 1, the video recommendation method is used in a computer device and includes the following steps.
In step 101, when it is detected that the increment in the first video browsing record table meets the target condition, the first video browsing record table is obtained, where the first video browsing record table includes video browsing records of multiple users, and one video browsing record is used to indicate videos that have been browsed by the users.
In a possible implementation manner, after obtaining an authorization of a user, a video browsing record of the user is obtained from a terminal of the user, where the video browsing record includes video information of a video browsed by the user and Identity information of the user, where the video information may be represented by a Unique identification number, a serial number, and the like, and the Identity information of the user may be represented by an identification number, a serial number, an account number, and the like corresponding to the user, or an Equipment identification code of the terminal is used as the Identity information of the user, and the Equipment identification code may be an International Mobile Equipment Identity (IMEI) of the terminal, a Unique Equipment identification code (UDID, Unique Device Identifier), a universal Unique identification code (UUID, universal Unique Identifier), and the like.
In a possible implementation manner, after the device identification code is obtained, hash processing may be performed on the device identification code to generate a hash number sequence in a range of 0 to 0000, and the hash data is additionally written into the video browsing record in a set data type, so that reduction of additional storage is achieved.
In step 102, video browsing records of a plurality of target videos are extracted from the first video browsing record table, and a second video browsing record table is generated, wherein the validity period of each target video is greater than a preset time length.
In a possible implementation manner, the first video browsing record table is generally maintained on line, that is, a video browsing record of a user is obtained from a user terminal in real time and is written into the first video browsing record table, and the videos in the video recommendation list are subjected to deduplication processing, so that, in order to not affect the above-mentioned on-line relevant operations, the video browsing record of the target video in the first video browsing record table is extracted through a preset target video list, and a second video browsing record table for storing the video browsing record of the target video is generated off line.
In step 103, when any one of the target videos in the second video browsing record table expires or the video browsing record expires, the video browsing record corresponding to the target video is deleted from the second video browsing record table.
In a possible implementation manner, validity periods are respectively set for a target video and video browsing records of the target video according to a preset rule, wherein the validity period of the target video is a validity period during which the target video can be recommended, for example, in a video recommendation system, a corresponding validity period is set for each video, and in the validity period, the video recommendation system can recommend the video to a user, meanwhile, since each user can generate a large number of video browsing records, in order to reduce the storage pressure for storing the video browsing records, a validity period is set for a record table for storing the video browsing records of the user, and outdated video browsing records in the video browsing record table are deleted regularly, so that the accuracy and high efficiency of video deduplication are ensured.
In step 104, repeated videos between the first video browsing record table and the second video browsing record table in the video list to be recommended of any user are filtered out.
In a possible implementation manner, in response to a video refresh request of a user, a video recommendation system obtains a certain number of videos to be recommended from a video library to be recommended, generates a video list to be recommended, and matches video information of the videos to be recommended with video information recorded in a first video browsing record table and a maintained second video browsing record table. The matching method is only illustrated by way of example, and the embodiment of the disclosure is not particularly limited
When the video information of the video to be recommended is successfully matched with any one of the first video browsing record table and the maintained second video browsing record table, the video to be recommended is determined to be a target video browsed by the user, the target video is deleted from the video list to be recommended, each video to be recommended in the video list to be recommended is sequentially matched until all videos browsed by the user are filtered, and the filtered video list to be recommended is pushed to the user.
In step 105, video recommendation is performed based on the filtered video list to be recommended.
In a possible implementation manner, in response to a video recommendation request of any user, a video recommendation list corresponding to the user is obtained, a video browsing record matched with the identity information of the user is determined from the first video browsing record table and the second video browsing record table, video information in the video recommendation list is matched with video information of the video browsing record of the user, for example, the video information may be identification information of the video, whether the identification information of the matched video is consistent or not, when the identification information is consistent, the matching is successful, the video matched with the video information is filtered from the video recommendation list of the user, and video recommendation is performed on the user based on the filtered video recommendation list.
According to the embodiment of the disclosure, the video browsing record with a long life cycle is extracted, and an offline video browsing record table is established for the video browsing record table to independently perform video charging, so that the duplicate removal accuracy rate of the video with a long life cycle is improved, and the target video is prevented from being repeatedly recommended to a user.
In order to implement the video recommendation method, a video browsing record of a target video is extracted from a first video browsing record table, an offline second video browsing record table is generated, and repeatedly pushed videos in a recommended video list are filtered out based on the first video browsing record table and the second video browsing record table. Specifically, how to extract the video browsing record of the target video from the first video browsing record table to generate the offline second video browsing record table may be performed in the following implementation manner shown in fig. 2.
201. And acquiring a target video list, wherein the target video list comprises video information of a plurality of target videos.
In a possible implementation manner, all target videos are screened out from a video database in an offline manner, a target video list is generated based on video information of the target videos, specifically, a corresponding key value is generated for video information of each target video, a target video list including a key value corresponding to each target video is generated in the database, and the target video list is maintained in an offline manner, where the offline maintenance operation includes: adding video information newly determined as a target video to the target video list, and deleting video information of an expired target video from the target video list, and the like.
202. And determining the video browsing record which is obtained by matching the video information of the browsed video in the first video browsing record list with the video information of the target video list as the video browsing record of the target video.
In one possible implementation manner, based on the target video list, matching is performed on video information of each browsed video in the first video browsing record table, for example, the video information may be identification information of the video, whether the identification information of the matched video is consistent or not, when the identification information is consistent, the browsed video matched with the video information is determined as the target video, and the video browsing record of the target video is extracted from the first video browsing record table, so as to implement generation of a second video browsing record table containing the video browsing record of the target video.
In one possible implementation manner, a first validity period is added to each video browsing record in the second video browsing record table based on validity periods of a plurality of target videos, and the first validity period is used for indicating whether the target videos are expired.
In a possible implementation manner, a second validity period is added to each video browsing record in the second video browsing record table based on the validity period of the video browsing record, and the second validity period is used for indicating whether the video browsing record is expired.
In one possible implementation manner, matching the video information of each target video in the second video browsing record table with the target video information in the target cache; for example, the video information may be identification information of a video, whether the identification information of the matched video is consistent or not, and when the identification information is inconsistent, that is, the matching fails, the video browsing record of which the video information fails is filtered from the second video browsing record table, so as to obtain the filtered second video browsing record table.
In a possible implementation manner, the video browsing records of the target video extracted in step 202 are generated into corresponding key values, and a second target video list including the key values corresponding to the video browsing records of each target video is generated in the database.
In an embodiment of the present disclosure, the database for storing the target video list, the first video browsing recording table, and the second video browsing recording table may be implemented by a key-value storage system, such as a Redis, where the Redis storage system may directly store the identity information of the user in the video browsing recording and the browsed video recording as a long type, so as to save a storage space compared with directly storing the corresponding character string.
In an embodiment of the present disclosure, when the number of the used video browsing records in the second video browsing record table reaches the maximum capacity threshold, the exceeded data is directly discarded until the second video browsing record table has a free storage space, and then the video browsing records are continuously saved.
For example, fig. 3 illustrates a schematic diagram of extracting a video browsing record of a target video from a first video browsing record table to generate an offline second video browsing record table, and referring to fig. 3, the first video browsing record table may be stored in a first database, and a video browsing record of a user is stored in the first video browsing record table, where each video browsing record at least includes video information of the video browsed by the user and identity information of the user, the video information and the identity information are stored in a key value manner, that is, the identity information is stored in a key value, the corresponding video information is stored in a value, and a target video list is stored in a third database in advance, the video information of the target video is stored in the target video list, and the target video may be a long-life period video; matching video information in a first video browsing record table stored in a first database with video information of a target video in a target video list stored in a third database, judging whether the video information is consistent, if the matching result is consistent, recording the matched video information and identity information corresponding to the video information, storing all the recorded matched video information and identity information corresponding to the video information in a second video browsing record table in a second database, wherein the identity information is the same as the first video browsing record table, and storing the matched video information and the identity information corresponding to the video information in a key value mode. Of course, the first video browsing record table, the second video browsing record table, and the target video list may be stored in the same Key-value database, which is not limited in this disclosure.
In order to achieve the accuracy of removing duplicate of the target video, the second video browsing record table generated in the above embodiment needs to be maintained, and the video browsing record of the expired target video is deleted from the second video browsing record table in time by determining whether the life cycle of the target video is expired and whether the video browsing record of the target video is expired, so as to achieve accurate duplicate removal. However, as to how to set the expiration date specifically for the second video browsing recording table generated in the above embodiment, the embodiment of the present disclosure may be implemented by the following implementation manner shown in fig. 4.
401. And setting a first validity period for the target video corresponding to each video browsing record in the second video browsing record table based on the life cycle of the target video, and generating a corresponding first validity period key value.
In a possible implementation manner, a first validity period is set for each target video based on a life cycle of each target video, and is converted into a corresponding first validity period key value, where the validity period may include a time period in which the target video can be recommended in the video recommendation system, for example, 7 days, 15 days, 30 days, and the like may be set according to actual needs, and the target video may be recommended by the video recommendation system in the time period, and accordingly, cannot be recommended by the video recommendation system after the time period is exceeded.
402. And adding the first validity key value to the corresponding video browsing record in the second video browsing record table.
In a possible implementation manner, the maintenance operation on the second video browsing record table is to maintain in a database stored in the second video browsing record table, and therefore, the first validity key value needs to be added to the video browsing record corresponding to the second video browsing record table for performing the related maintenance.
403. And setting a second validity period for each video browsing record in the video browsing records according to a preset rule, and generating a corresponding second validity period key value.
In a possible implementation manner, based on the storage state of the database storing the second video browsing record table, a second validity period is set for each video browsing record in the second video browsing record table, for example, may be set to 1 day, 2 days, and the like according to the storage state of the database, and a corresponding second validity period key value is generated.
404. And adding the second validity key value to the corresponding video browsing record in the second video browsing record table.
In a possible implementation manner, the maintenance operation on the second video browsing record table is to maintain in a database stored in the second video browsing record table, and therefore, the second validity key value needs to be added to the video browsing record corresponding to the second video browsing record table for performing the related maintenance.
For example, fig. 5 illustrates a schematic diagram of setting a validity period for a video browsing record in a second video browsing record table, and referring to fig. 5, a validity period is set for a video browsing record of a target video recorded in the second video browsing record table stored in the second database, specifically, a first validity period and a second validity period are set for the second video browsing record table after a new browsing record of the target video is stored in the second video browsing record table, where the first validity period may be obtained from video information in a target video list in a third database, and the first validity period is used for indicating a life cycle of the target video; the second validity period may be set by a preset rule, and the second validity period is used to indicate a validity period of the video browsing record of the target video in the second video browsing record table, and correspondingly, the first validity period and the second validity period are stored in the second video browsing record table in a key value manner.
After the validity period of each video browsing record in the second video browsing record table is set, the second video browsing record table can be regularly maintained based on the validity period, and the expired video browsing record is deleted from the second video browsing record table, so that accurate duplicate removal of the target video is realized subsequently. However, as to how to maintain the second video browsing record table generated in the foregoing embodiment, the embodiment of the present disclosure may be implemented by the following implementation manner shown in fig. 6.
601. And periodically detecting a first validity key value and a second validity key value of each video browsing record in the second video browsing record table.
In a possible implementation manner, based on the identity information of the user, corresponding video browsing records are periodically extracted from the second video browsing record table, and whether the first validity key value and the second validity key value in each video browsing record are expired is respectively checked.
602. And when any one of the first validity key value and the second validity key value is expired, deleting the corresponding video browsing record from the second video browsing record table to obtain the maintained second video browsing record table.
In a possible implementation manner, after any one of the first validity key value and the second validity key value expires, the corresponding video browsing record is deleted from the second video browsing record table, and after all the video browsing records are checked, the maintained second video browsing record is obtained.
For example, fig. 7 illustrates a schematic diagram of maintaining a second video browsing record table, and referring to fig. 7, the second video browsing record table is periodically maintained, a certain number of video browsing records of a target video can be obtained from the second video browsing record table, a first validity period and a second validity period corresponding to the obtained video browsing records of the target video are compared with a current time, and when a time point of the first validity period and the second validity period is before a time point of the current time, it is determined that the video browsing records are not expired; when the time points of the first validity period and the second validity period are positioned at the time point of the current time or behind the time point of the current time, the expiration is not determined; based on the above, whether the first validity period and the second validity period are expired or not is judged, when any one of the first validity period and the second validity period is expired, the corresponding video browsing records of the target video are deleted from the second video browsing record table, when the obtained video browsing records of the target video with a certain number are checked, the video browsing records of the target video with a certain number, which are not detected, are obtained from the second video browsing record table again until the video browsing records of all the target video in the second video browsing record table are checked, and the maintenance of the current period is finished until the beginning of the next period.
In an embodiment of the present disclosure, in a Redis application, each video browsing record of the second video browsing record table may be stored in a different storage system, and the maintaining of the second video browsing record table may use a scan command of sscan, hscan, and zscan in the Redis to scan a key value of a certain video browsing record in the second video browsing record with a small data size, and perform an optimization adjustment on a detection process according to an increase speed occupied by a memory, so as to implement efficient maintenance of the second video browsing record table.
And after a video duplicate removal request is received, carrying out duplicate removal processing on the video recommendation list based on the first video browsing record list and the maintained second video browsing record list. However, for how to perform video de-duplication specifically for the above embodiment, the embodiment of the present disclosure may be performed by the following implementation shown in fig. 8.
801. And acquiring video information of each video in the video list to be recommended.
802. And matching the video information of each video with the video information of the videos in the first video browsing record list and the second video browsing record list.
803. And filtering the successfully matched video from the video list to be recommended, and outputting the filtered video list to be recommended.
For example, fig. 9 illustrates a schematic diagram of performing deduplication processing on a recommended video list, and referring to fig. 9, after a recommended video list recommended to a user is obtained, video information of each to-be-recommended video in the recommended video list is determined, the video information of each to-be-recommended video is respectively matched with video information of videos browsed by the user and recorded in a first video browsing record table and a second video browsing record table, the video information is the same and determined as a video that is repeatedly recommended, the video information is deleted from the recommended video list, and finally, the recommended video list after deduplication is obtained, the duplicate removal accuracy rate of the video with the long life cycle is improved, and repeated recommendation of the target video to the user is avoided.
Fig. 10 is a block diagram illustrating a video recommendation device according to an example embodiment. Referring to fig. 10, the apparatus includes:
an obtaining unit 1001 configured to obtain a first video browsing record table when detecting that an increment in the first video browsing record table meets a target condition, the first video browsing record table including video browsing records of a plurality of users, one video browsing record being used to indicate videos that the users have browsed;
a generating unit 1002, configured to extract video browsing records of a plurality of target videos from the first video browsing record table, and generate a second video browsing record table, where an effective period of each target video is greater than a preset time length;
a maintenance unit 1003 configured to delete the video browsing record corresponding to the target video from the second video browsing record table when any one of the target videos in the second video browsing record table expires or the video browsing record expires;
the duplicate removal unit 1004 is configured to filter out duplicate videos between the first video browsing record table and the second video browsing record table in the to-be-recommended video list of any user;
a recommending unit 1005 configured to recommend videos based on the filtered list of videos to be recommended.
In an embodiment of the present disclosure, the generating unit 1002 is specifically configured to:
acquiring a target video list, wherein the target video list comprises video information of a plurality of target videos;
and determining the video browsing record which is obtained by matching the video information of the browsed video in the first video browsing record list with the video information of the target video list as the video browsing record of the target video.
In an embodiment of the present disclosure, the generating unit 1002 is specifically configured to:
and adding a first validity period to each video browsing record in the second video browsing record table based on the validity periods of the plurality of target videos, wherein the first validity period is used for indicating whether the target videos are expired.
In an embodiment of the present disclosure, the generating unit 1002 is specifically configured to:
matching the video information of each target video in the second video browsing record list with the target video information in the target cache;
and filtering the successfully matched video from the second video browsing record table to obtain the filtered second video browsing record table.
In an embodiment of the present disclosure, the generating unit 1002 is specifically configured to:
and adding a second validity period to each video browsing record in the second video browsing record table based on the validity period of the video browsing record, wherein the second validity period is used for indicating whether the video browsing record is expired.
In an embodiment of the present disclosure, the deduplication unit 1004 is specifically configured to:
acquiring video information of each video in a video list to be recommended;
matching the video information of each video with the video information of the videos in the first video browsing record list and the second video browsing record list;
and filtering the successfully matched video from the video list to be recommended, and outputting the filtered video list to be recommended.
In one embodiment of the present disclosure, the video browsing record is represented by a key value.
With regard to the apparatus in the above-described embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment related to the method, and will not be described in detail here.
The video recommendation method of the present disclosure is described in detail below with reference to a specific embodiment of a video recommendation system, fig. 11 is a schematic diagram of a video recommendation system 1100 according to an exemplary embodiment, and referring to fig. 11, the system 1100 includes:
the video duplicate removal unit 1101 is configured to filter videos browsed by a user in the video recommendation list, and recommend the filtered video recommendation list to the user;
the first cache unit 1102 is respectively connected to the video duplicate removal and video browsing record extraction unit, and is used for generating a first video browsing record table in the cache and storing video browsing records of a plurality of users;
a target video browsing record extracting unit 1103, configured to extract a target video browsing record from the first cache 1102, and store the extracted target video browsing record in the second cache 1104;
a second cache unit 1104, connected to the target video browsing record extracting unit 1103, the first maintenance unit 1105 and the second maintenance unit 1106, respectively, and configured to generate a second video browsing record table in the cache, store target video browsing records of multiple users, and maintain the second video browsing record table based on the first maintenance unit 1105 and the second maintenance unit 1106;
the first maintenance unit 1105 is connected to the second cache 1104 and the third cache 1107, and filters out the video browsing records corresponding to the expired target video in the second video browsing record table in the second cache 1104;
the second maintenance unit 1106 is connected to the second cache 1104 and filters out the expired second video browsing record in the second cache 1104;
a third caching unit 1107 is connected to the target video browsing record extraction unit 1103 and the first maintenance unit 1105, and is configured to provide the target video browsing record extraction unit 1103 and the first maintenance unit 1105 with target video information.
In an embodiment of the present disclosure, the first cache unit 1102, the second cache unit 1104, and the third cache unit 1107 may be implemented in a key-value distributed storage system, such as a Redis storage system, a Memcached storage system, and the like, and have implemented functions of storing, fast querying, reading and writing with high concurrency for massive video browsing records, and the like.
In an embodiment of the present disclosure, the video deduplication unit 1101 may be implemented by a deduplication unit 1004 in the video recommendation apparatus embodiment, the target video browsing record extraction unit 1103 may be implemented by an acquisition unit 1001 and a generation unit 1002 in the video recommendation apparatus embodiment, and the first maintenance unit 1105 and the second maintenance unit 1106 may be implemented by a maintenance unit 1003 in the video recommendation apparatus embodiment, where specific ways of operations performed by the respective units are described in detail in the embodiment of the method, and will not be described in detail here.
In an embodiment of the present disclosure, each unit in the video recommendation system may be implemented by:
the target video browsing record extracting unit 1103 detects a data volume change of a video browsing record in a first video browsing record table in the first cache unit 1102, and when detecting that an increment of a video record in the first cache unit 1102 meets a target condition, the target video browsing record extracting unit 1103 acquires the first video browsing record table from the first cache unit 1102, where the first video browsing record table includes video browsing records of a plurality of users, and one video browsing record is used to indicate a video browsed by the user, and each video browsing record records user identity information (Device identity information: Device ID) and video information (video information: Photo ID) of the video browsed by the user.
In an embodiment of the present disclosure, the target video browsing record extracting unit 1103 obtains the video information of the target video from the third cache unit 1107, performs intersection matching between the video information of the target video and the extracted video information in the first video browsing record table, determines the video browsing record with successful intersection matching as the video browsing record of the target video, writes the video browsing record of the target video into the second video browsing record table in the second cache unit 1104 through rpush instruction, that is, inserts the key value corresponding to the user identity information in the video browsing record of the target video and the key value corresponding to the video information of the browsed video into corresponding storage locations in the second video browsing record table in sequence, and intercepts the second video browsing record table when the data volume of the second video browsing record table exceeds a preset threshold value, and no new video browsing record is stored in the second video browsing record table.
In an embodiment of the present disclosure, the second maintenance unit 1106 may be configured to maintain the second video browsing record table in the second cache unit 1104, specifically, the second maintenance unit 1106 performs offline maintenance on the second video browsing record table in the second cache unit 1104 through a preset offline task, scans the user identity information of the second video browsing record table in the second cache unit 1104 based on the offline task, obtains a video browsing record of each user, checks whether the video browsing record of each user is expired based on a preset validity period of the video browsing record, deletes the corresponding video browsing record from the second video browsing record table if the video browsing record of each user is expired, and in practical applications, the time for the second maintenance unit 1106 to maintain the second video browsing record table of the second cache unit 1104 is designed to be maintained completely once in 1 hour, therefore, optimization and adjustment can be performed according to the increase speed of the memory of the distributed storage system occupied by the second maintenance unit 1106, so that the second maintenance unit 1106 can completely maintain the second video browsing recording list once in 1 hour.
In an embodiment of the present disclosure, the first maintenance unit 1105 may further maintain the second video browsing record table in the second cache unit 1104, specifically, the first maintenance unit 1105 is connected to the third cache unit 1107, obtains video information of a target video from the third buffer, sets a corresponding validity period for the target video according to a preset policy, and combines the video information of the target video with the video information of the target video, detects whether a target video corresponding to each video browsing record in the second video browsing record table in the second cache unit 1104 is expired, if the target video is expired, deletes the corresponding video browsing record from the second video browsing record table, for example, obtains the second video browsing record table in the second cache unit 1104, sets a validity period for a key value of the video information of each target video in the second video browsing record table, and then scans the validity period of each target video offline, and deleting the video browsing record with the expired target video from the second video browsing record table.
In an embodiment of the present disclosure, the video deduplication unit 1101 includes a first obtaining subunit and a second obtaining subunit, where the first obtaining subunit is configured to obtain a first video browsing record table from the first cache unit 1102, the second obtaining subunit is configured to obtain a second video browsing record table from the second cache unit 1104, obtain a video recommendation list of a corresponding user in response to a video recommendation request of any user, determine a video browsing record corresponding to the identity information of the user from the first video browsing record table and the second video browsing record table, match video information in the video recommendation list with video information of the video browsing record corresponding to the identity information of the user, filter a video with which the video information is matched from the video recommendation list of the user, and recommend a video to the corresponding user based on the filtered video recommendation list, the identity information of the user is written in the end of the video recommendation request of the user, and the identity information in the first video browsing record table and the second video browsing record table is scanned through a pipeline operation instruction, so that only the video browsing record of the specified identity information is scanned, and extra time consumption is not increased.
According to the embodiment of the disclosure, the video browsing record with a long life cycle is extracted, and an offline video browsing record table is established for the video browsing record table to independently perform video charging, so that the duplicate removal accuracy rate of the video with a long life cycle is improved, and the target video is prevented from being repeatedly recommended to a user.
FIG. 12 is a block diagram illustrating a computer device according to an example embodiment. The computer device 1200 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 1201 and one or more memories 1202, where the memory 1202 stores at least one instruction, and the at least one instruction is loaded and executed by the processors 1201 to implement the business data detection method provided by each of the method embodiments. Certainly, the computer device may further have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the computer device may further include other components for implementing the functions of the device, which is not described herein again.
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 application 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 (10)
1. A method for video recommendation, comprising:
when detecting that the increment in a first video browsing record table meets a target condition, acquiring the first video browsing record table, wherein the first video browsing record table comprises video browsing records of a plurality of users, and one video browsing record is used for recording video information of videos browsed by the users;
extracting video browsing records of a plurality of target videos from the first video browsing record table to generate a second video browsing record table, wherein the second video browsing record table records the set valid period of the video browsing record of each target video, and the valid period of the video browsing record is used for indicating the valid duration of the video browsing record in the second video browsing record table;
when the validity period of any video browsing record in the second video browsing record table is expired, deleting the video browsing record from the second video browsing record table;
matching the video information of the video to be recommended in the video list to be recommended of any user with the video information corresponding to the video browsing record in the second video browsing record list, and filtering the video to be recommended matched with the video information;
and recommending videos based on the filtered list of videos to be recommended.
2. The method of claim 1, wherein the extracting the video browsing history of the plurality of target videos from the first video browsing history table to generate a second video browsing history table comprises:
acquiring a target video list, wherein the target video list comprises video information of a plurality of target videos;
and matching the video information corresponding to the video browsing record in the first video browsing record list with the video information of the target video list, extracting a plurality of video browsing records matched with the video information, and generating a second video browsing record list.
3. The method of claim 1 or 2, wherein after the generating the second video browsing record list, the method further comprises:
matching the video information of each target video in the second video browsing record list with the target video information in the target cache;
and filtering the video browsing record with the video information which is not successfully matched from the second video browsing record table to obtain the filtered second video browsing record table.
4. The method according to claim 1, wherein the video browsing record is stored in a database with a key-value key value, wherein the user information in the video browsing record is stored with a key value, and the video information corresponding to the user information is stored with a value.
5. A video recommendation apparatus, comprising:
the acquisition unit is configured to acquire a first video browsing record table when detecting that the increment in the first video browsing record table meets a target condition, wherein the first video browsing record table comprises video browsing records of a plurality of users, and one video browsing record is used for recording video information of videos browsed by the users;
the generating unit is configured to extract video browsing records of which the valid periods of a plurality of target videos are greater than a preset time length from the first video browsing record table, set the valid period of the video browsing record of each target video, and generate a second video browsing record table, wherein the valid period of the target video is used for indicating the valid time length recommended by the target video in the video recommending system, and the valid period of the video browsing record is used for indicating the valid time length of the video browsing record in the second video browsing record table;
the filtering unit is configured to delete a video browsing record from the second video browsing record table when the validity period of any one video browsing record in the second video browsing record table expires;
the duplication removing unit is configured to match video information of a video to be recommended in a video list to be recommended of any user with video information corresponding to video browsing records in the second video browsing record table, and filter the video to be recommended with the video information matched;
and the recommending unit is configured to recommend videos based on the filtered list of videos to be recommended.
6. The apparatus of claim 5, wherein the generating unit is configured to:
acquiring a target video list, wherein the target video list comprises video information of a plurality of target videos;
and matching the video information corresponding to the video browsing record in the first video browsing record list with the video information of the target video list, extracting a plurality of video browsing records matched with the video information, and generating a second video browsing record list.
7. The apparatus of claim 5 or 6, wherein the generating unit is further configured to:
matching the video information of each target video in the second video browsing record list with the target video information in the target cache;
and filtering the video browsing record with the video information which is not successfully matched from the second video browsing record table to obtain the filtered second video browsing record table.
8. The apparatus according to any one of claims 5 to 7, wherein the video browsing record is stored in a database with a key-value key value, wherein the user information in the video browsing record is stored with a key value, and the video information corresponding to the user information is stored with a value.
9. A computer device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the video recommendation method of any of claims 1 to 4.
10. A storage medium in which instructions, when executed by a processor of a computer device, enable the computer device to perform the video recommendation method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911016642.XA CN112714359B (en) | 2019-10-24 | 2019-10-24 | Video recommendation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911016642.XA CN112714359B (en) | 2019-10-24 | 2019-10-24 | Video recommendation method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112714359A true CN112714359A (en) | 2021-04-27 |
| CN112714359B CN112714359B (en) | 2022-09-09 |
Family
ID=75540606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911016642.XA Active CN112714359B (en) | 2019-10-24 | 2019-10-24 | Video recommendation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112714359B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919859A (en) * | 2021-08-25 | 2022-01-11 | 读书郎教育科技有限公司 | Model machine display method |
| CN113949921A (en) * | 2021-08-31 | 2022-01-18 | 上海二三四五网络科技有限公司 | Control method and control device for short video cache cleaning |
| CN114051162A (en) * | 2022-01-12 | 2022-02-15 | 飞狐信息技术（天津）有限公司 | Caching method and device based on play records |
| CN114422150A (en) * | 2022-03-29 | 2022-04-29 | 飞狐信息技术（天津）有限公司 | Method for preventing passive deletion, client and server |
| CN115225603A (en) * | 2022-06-29 | 2022-10-21 | 赤子城网络技术（北京）有限公司 | User matching method and system in social application |
| CN116074378A (en) * | 2023-04-06 | 2023-05-05 | 西南石油大学 | Internet information pushing method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496316A (en) * | 2011-11-30 | 2012-06-13 | 江苏奇异点网络有限公司 | Remote video lesson giving method supporting mobile terminal off-line play |
| CN102843586A (en) * | 2011-06-21 | 2012-12-26 | 华为软件技术有限公司 | Video recommendation method and terminal |
| US20130031173A1 (en) * | 2011-07-30 | 2013-01-31 | Huawei Technologies Co., Ltd. | Information recommendation method, recommendation engine, network system |
| CN102957949A (en) * | 2012-05-18 | 2013-03-06 | 华东师范大学 | Device and method for recommending video to user |
| US8712218B1 (en) * | 2002-12-17 | 2014-04-29 | At&T Intellectual Property Ii, L.P. | System and method for providing program recommendations through multimedia searching based on established viewer preferences |
| CN105007504A (en) * | 2015-07-13 | 2015-10-28 | 无锡天脉聚源传媒科技有限公司 | Browsing history processing method and device |
| CN105282565A (en) * | 2015-09-29 | 2016-01-27 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN105302807A (en) * | 2014-06-06 | 2016-02-03 | 腾讯科技（深圳）有限公司 | Method and apparatus for obtaining information category |
| CN105915949A (en) * | 2015-12-23 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Video content recommending method, device and system |
| CN106878405A (en) * | 2017-01-25 | 2017-06-20 | 咪咕动漫有限公司 | A kind of method and device for adjusting push project |
| CN109189951A (en) * | 2018-07-03 | 2019-01-11 | 上海掌门科技有限公司 | A kind of multimedia resource recommended method, equipment and storage medium |
| CN109559208A (en) * | 2019-01-04 | 2019-04-02 | 平安科技（深圳）有限公司 | A kind of information recommendation method, server and computer-readable medium |
| CN109587527A (en) * | 2018-11-09 | 2019-04-05 | 青岛聚看云科技有限公司 | A kind of method and device that individualized video is recommended |
-
2019
- 2019-10-24 CN CN201911016642.XA patent/CN112714359B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8712218B1 (en) * | 2002-12-17 | 2014-04-29 | At&T Intellectual Property Ii, L.P. | System and method for providing program recommendations through multimedia searching based on established viewer preferences |
| CN102843586A (en) * | 2011-06-21 | 2012-12-26 | 华为软件技术有限公司 | Video recommendation method and terminal |
| US20130031173A1 (en) * | 2011-07-30 | 2013-01-31 | Huawei Technologies Co., Ltd. | Information recommendation method, recommendation engine, network system |
| CN102496316A (en) * | 2011-11-30 | 2012-06-13 | 江苏奇异点网络有限公司 | Remote video lesson giving method supporting mobile terminal off-line play |
| CN102957949A (en) * | 2012-05-18 | 2013-03-06 | 华东师范大学 | Device and method for recommending video to user |
| CN105302807A (en) * | 2014-06-06 | 2016-02-03 | 腾讯科技（深圳）有限公司 | Method and apparatus for obtaining information category |
| CN105007504A (en) * | 2015-07-13 | 2015-10-28 | 无锡天脉聚源传媒科技有限公司 | Browsing history processing method and device |
| CN105282565A (en) * | 2015-09-29 | 2016-01-27 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN105915949A (en) * | 2015-12-23 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Video content recommending method, device and system |
| CN106878405A (en) * | 2017-01-25 | 2017-06-20 | 咪咕动漫有限公司 | A kind of method and device for adjusting push project |
| CN109189951A (en) * | 2018-07-03 | 2019-01-11 | 上海掌门科技有限公司 | A kind of multimedia resource recommended method, equipment and storage medium |
| CN109587527A (en) * | 2018-11-09 | 2019-04-05 | 青岛聚看云科技有限公司 | A kind of method and device that individualized video is recommended |
| CN109559208A (en) * | 2019-01-04 | 2019-04-02 | 平安科技（深圳）有限公司 | A kind of information recommendation method, server and computer-readable medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919859A (en) * | 2021-08-25 | 2022-01-11 | 读书郎教育科技有限公司 | Model machine display method |
| CN113949921A (en) * | 2021-08-31 | 2022-01-18 | 上海二三四五网络科技有限公司 | Control method and control device for short video cache cleaning |
| CN114051162A (en) * | 2022-01-12 | 2022-02-15 | 飞狐信息技术（天津）有限公司 | Caching method and device based on play records |
| CN114422150A (en) * | 2022-03-29 | 2022-04-29 | 飞狐信息技术（天津）有限公司 | Method for preventing passive deletion, client and server |
| CN114422150B (en) * | 2022-03-29 | 2022-07-12 | 飞狐信息技术（天津）有限公司 | Method for preventing passive deletion, client and server |
| CN115225603A (en) * | 2022-06-29 | 2022-10-21 | 赤子城网络技术（北京）有限公司 | User matching method and system in social application |
| CN115225603B (en) * | 2022-06-29 | 2024-05-28 | 赤子城网络技术（北京）有限公司 | User matching method and system in social application |
| CN116074378A (en) * | 2023-04-06 | 2023-05-05 | 西南石油大学 | Internet information pushing method and system |
| CN116074378B (en) * | 2023-04-06 | 2023-06-16 | 西南石油大学 | Internet information pushing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112714359B (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112714359B (en) | Video recommendation method and device, computer equipment and storage medium | |
| CN107832406B (en) | Method, device, equipment and storage medium for removing duplicate entries of mass log data | |
| CN107229420B (en) | Data storage method, reading method, deleting method and data operating system | |
| CN106936441B (en) | Data compression method and device | |
| CN107911461B (en) | Object processing method in cloud storage system, storage server and cloud storage system | |
| CN106874281B (en) | Method and device for realizing database read-write separation | |
| US20140244583A1 (en) | Method of Processing File changes and Electronic Device Thereof | |
| WO2019019642A1 (en) | Application information pushing method and apparatus, and computer device and storage medium | |
| CN109885577B (en) | Data processing method, device, terminal and storage medium | |
| CN103049491A (en) | Method and device for managing picture file | |
| CN105260639A (en) | Face recognition system data update method and device | |
| CN113535708A (en) | Data deduplication method, system, storage medium and equipment | |
| CN111125018B (en) | File exception tracing method, device, equipment and storage medium | |
| CN115114232A (en) | Method, device and medium for enumerating historical version objects | |
| CN112463026A (en) | Method and apparatus for deduplication of supplemental data in a distributed object storage system | |
| CN110222046B (en) | List data processing method, device, server and storage medium | |
| US20190245827A1 (en) | Method and apparatus for synchronizing contact information and medium | |
| CN106899558B (en) | Access request processing method and device and storage medium | |
| CN108491315B (en) | Page residence time counting method and device and computer readable storage medium | |
| CN112817962B (en) | Data storage method and device based on object storage and computer equipment | |
| CN108038253B (en) | Log query processing method and device | |
| CN111913913B (en) | Access request processing method and device | |
| CN104915376A (en) | Cloud storage file archiving and compressing method | |
| KR20150123603A (en) | Method and system for managing database | |
| CN110658993A (en) | Snapshot rollback method, device, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |