CN110996142B - Video recall method and device, electronic equipment and storage medium - Google Patents
Video recall method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110996142B CN110996142B CN201911089842.8A CN201911089842A CN110996142B CN 110996142 B CN110996142 B CN 110996142B CN 201911089842 A CN201911089842 A CN 201911089842A CN 110996142 B CN110996142 B CN 110996142B
- Authority
- CN
- China
- Prior art keywords
- video
- tag
- historical
- user
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/835—Generation of protective data, e.g. certificates
- H04N21/8352—Generation of protective data, e.g. certificates involving content or source identification data, e.g. Unique Material Identifier [UMID]
-
- 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
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- 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
- H04N21/47—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
Abstract
The embodiment of the invention provides a video recall method and device, electronic equipment and a storage medium. The video recall method comprises the following steps: receiving a video acquisition request, wherein the video acquisition request comprises a user identifier; acquiring historical information corresponding to the user identification, wherein the historical information comprises the freezing time of a historical video label; acquiring a to-be-processed video tag corresponding to the user identifier, determining whether the to-be-processed video tag is within the freezing time according to the freezing time of the historical video tag, and filtering the to-be-processed video tag within the freezing time; and recalling the videos corresponding to the residual video tags to be processed after filtering. The embodiment of the invention can avoid the situation that a large number of similar videos are concentrated, improve the accuracy and diversity of the recalled videos and improve the user experience.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a video recall method and apparatus, an electronic device, and a storage medium.
Background
With the rapid development of internet technology, users increasingly rely on obtaining information through networks. In order to meet the requirement of users for watching videos, various video websites come along. In order to meet the user requirements, a video website usually recommends videos to users, and recommends videos which may be interested by the users, so that personalized services are performed according to different users.
When the video recommendation service is performed, video recall is required. When video recalls are performed, videos corresponding to the video tags which are interested by the users are recalled generally according to the video tags which are interested by the users. However, if the video tags which are interested by the user are not changed, the videos corresponding to the video tags are recalled every time, so that a large number of similar videos are concentrated during recommendation, and the user is easily tired. Therefore, the recalled videos are inaccurate and have poor video diversity.
Disclosure of Invention
An embodiment of the present invention provides a video recall method and apparatus, an electronic device, and a storage medium, so as to improve accuracy and diversity of video recall. The specific technical scheme is as follows:
in a first aspect of the present invention, there is provided a video recall method, including:
receiving a video acquisition request, wherein the video acquisition request comprises a user identifier;
acquiring historical information corresponding to the user identification, wherein the historical information comprises the freezing time of a historical video label;
acquiring a to-be-processed video tag corresponding to the user identifier, determining whether the to-be-processed video tag is within the freezing time according to the freezing time of the historical video tag, and filtering the to-be-processed video tag within the freezing time;
and recalling the videos corresponding to the residual video tags to be processed after filtering.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and/or to-be-processed content tags, and the historical video tags include historical user interest tags and/or historical content tags.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and to-be-processed content tags, and the historical video tags include historical user interest tags and historical content tags; the step of obtaining the video tag to be processed corresponding to the user identifier, determining whether the video tag to be processed is within the freezing time according to the freezing time of the historical video tag, and filtering the video tag to be processed within the freezing time includes: acquiring a to-be-processed user interest tag corresponding to the user identifier, determining whether the to-be-processed user interest tag is within the freezing time according to the freezing time of the historical user interest tag, and filtering the to-be-processed user interest tag within the freezing time; and acquiring the to-be-processed content tags corresponding to the filtered residual to-be-processed user interest tags, determining whether the to-be-processed content tags are within the freezing time according to the freezing time of the historical content tags, and filtering the to-be-processed content tags within the freezing time.
Optionally, the method further comprises: after recommending a recalled video to a user, receiving a user behavior log; the user behavior log comprises the user identification, user behavior information and a current video tag of a recommended video; acquiring historical information corresponding to the user identification; when the user behavior information is that the recommended video is not clicked, determining whether the current video label meets a freezing condition or not according to the freezing time of the historical video label; and when the current video label meets the freezing condition, determining the freezing time of the current video label, and recording the freezing time of the current video label into the historical information.
Optionally, the user behavior log further includes occurrence time of user behavior, and the history information further includes last non-click time of a history video tag; before the step of determining whether the current video tag meets the freezing condition according to the freezing time of the historical video tag, the method further comprises the following steps: when the current video tag exists in the historical information, acquiring a time interval between occurrence time of the user behavior and last non-click time of the current video tag; and when the time interval is greater than a preset time threshold, deleting the current video tag from the historical information.
Optionally, after the step of obtaining the history information corresponding to the user identifier, the method further includes: and when the user behavior information is the video which is clicked to recommend and the current video tag exists in the historical information, deleting the current video tag from the historical information.
Optionally, the history information further includes the number of times of non-clicks of the history video tag; before the step of determining whether the current video tag meets the freezing condition according to the freezing time of the historical video tag, the method further comprises the following steps: and increasing the number of times of non-clicking of the current video label once.
Optionally, the user behavior log further comprises occurrence times of user behaviors; the step of determining the freezing time of the current video tag comprises the following steps: calculating the freezing time length of the current video label according to the number of times of non-clicking of the current video label; the freezing time length is positively correlated with the number of times of non-clicks; and determining the time after the duration of the freezing time from the occurrence time of the user behavior as the freezing time of the current video tag.
Optionally, the step of determining whether the current video tag meets a freezing condition according to the freezing time of the historical video tag includes: and when the number of times of non-clicking of the current video label is larger than a preset number threshold value, determining that the current video label meets the freezing condition.
In a second aspect implemented by the present invention, there is also provided a video recall apparatus, comprising:
the system comprises a first receiving module, a second receiving module and a video acquiring module, wherein the first receiving module is used for receiving a video acquiring request which comprises a user identifier;
the first acquisition module is used for acquiring historical information corresponding to the user identifier, wherein the historical information comprises the freezing time of a historical video label;
the filtering module is used for acquiring the video tag to be processed corresponding to the user identifier, determining whether the video tag to be processed is within the freezing time according to the freezing time of the historical video tag, and filtering the video tag to be processed within the freezing time;
and the recall module is used for recalling the videos corresponding to the residual video tags to be processed after filtering.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and/or to-be-processed content tags, and the historical video tags include historical user interest tags and/or historical content tags.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and to-be-processed content tags, and the historical video tags include historical user interest tags and historical content tags; the filtration module includes: the interest filtering unit is used for acquiring the interest tags of the users to be processed corresponding to the user identifications, determining whether the interest tags of the users to be processed are within the freezing time according to the freezing time of the historical interest tags of the users, and filtering the interest tags of the users to be processed within the freezing time; and the content filtering unit is used for acquiring the to-be-processed content tags corresponding to the to-be-processed user interest tags remaining after filtering, determining whether the to-be-processed content tags are within the freezing time according to the freezing time of the historical content tags, and filtering the to-be-processed content tags within the freezing time.
Optionally, the apparatus further comprises: the second receiving module is used for receiving the user behavior log after the recalled video is recommended to the user; the user behavior log comprises the user identification, user behavior information and a current video tag of a recommended video; the second acquisition module is used for acquiring historical information corresponding to the user identification; the first determining module is used for determining whether the current video label meets a freezing condition according to the freezing time of the historical video label when the user behavior information is that the recommended video is not clicked; and the second determining module is used for determining the freezing time of the current video label when the current video label meets the freezing condition, and recording the freezing time of the current video label into the historical information.
Optionally, the user behavior log further includes occurrence time of user behavior, and the history information further includes last non-click time of a history video tag; the device further comprises: a third obtaining module, configured to obtain, when the current video tag exists in the history information, a time interval between occurrence time of the user behavior and last non-click time of the current video tag; and the first deleting module is used for deleting the current video tag from the historical information when the time interval is greater than a preset time threshold.
Optionally, the apparatus further comprises: and the second deleting module is used for deleting the current video label from the historical information when the user behavior information is the video which is clicked to recommend and the current video label exists in the historical information.
Optionally, the history information further includes the number of times of non-clicks of the history video tag; the device further comprises: and the increasing module is used for increasing the number of times of non-clicking of the current video label once.
Optionally, the user behavior log further comprises occurrence times of user behaviors; the second determining module includes: the time length calculating unit is used for calculating the freezing time length of the current video label according to the number of times of non-clicking of the current video label; the freezing time length is positively correlated with the number of times of non-clicks; and the time determining unit is used for determining the time after the duration of the freezing time from the occurrence time of the user behavior as the freezing time of the current video label.
Optionally, the first determining module is specifically configured to determine that the current video tag meets a freezing condition when the number of times of non-clicks of the current video tag is greater than a preset number threshold.
In another aspect of the present invention, there is also provided an electronic device, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus; a memory for storing a computer program; a processor for implementing any of the above methods when executing a program stored in the memory.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to perform any of the methods described above.
In yet another aspect of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the methods described above.
In the embodiment of the invention, a video acquisition request is received, wherein the video acquisition request comprises a user identifier; acquiring historical information corresponding to the user identification, wherein the historical information comprises the freezing time of a historical video label; acquiring a to-be-processed video tag corresponding to the user identifier, determining whether the to-be-processed video tag is within the freezing time according to the freezing time of the historical video tag, and filtering the to-be-processed video tag within the freezing time; and recalling the videos corresponding to the residual video tags to be processed after filtering. Therefore, in the embodiment of the invention, the corresponding history information is set for the user identifier, the freezing time of the history video tag is set in the history information, and the video tag to be processed within the freezing time can be filtered according to the history information corresponding to the user identifier in the video recalling process, so that the video corresponding to the filtered video tag to be processed is not recalled any more. For example, a large number of similar video users who appear in a concentrated manner do not click any more, so that the freezing time of the video tags of the videos can be set, and then videos corresponding to the video tags within the freezing time are filtered out when the videos are recommended to the users, so that the situation that a large number of similar videos appear in a concentrated manner is avoided, the accuracy and diversity of recalling the videos are improved, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a flowchart illustrating a video recall method according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating a video recall method according to a second embodiment of the present invention.
Fig. 3 is a flowchart illustrating a recall procedure in a video recall method according to a third embodiment of the present invention.
Fig. 4 is a flowchart illustrating steps of an information updating process in a video recall method according to a third embodiment of the present invention.
Fig. 5 is a block diagram of a video recall device according to a fourth embodiment of the present invention.
Fig. 6 is a block diagram of a video recall device according to a fifth embodiment of the present invention.
Fig. 7 is a block diagram of an electronic device in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
In the embodiment of the invention, the recommendation system sets corresponding historical information for the user identification of the user, and the historical information is used for recording information such as the freezing time of the historical video label. After the recommendation system recommends a video to a user, the client uploads a user behavior log, the recommendation system determines the freezing time of a video tag of the recommended video according to the information in the behavior log and the user behavior executed by the user on the recommended video, and updates the historical information corresponding to the user identification. When the recommendation system recommends videos to the user again, the to-be-processed video tags within the freezing time can be filtered according to the historical information corresponding to the user identification, and the videos corresponding to the filtered to-be-processed video tags are recommended, so that the situation that a large number of similar videos are concentrated is avoided. Therefore, the video recall method and device in the embodiment of the invention can be applied to a recommendation system.
The client may be various video APPs (applications), and the recommendation system may be a server corresponding to the video APPs, and so on.
Example one
Fig. 1 is a flowchart illustrating a video recall method according to an embodiment of the present invention. As shown in fig. 1, the video recall method may include the steps of:
And 102, acquiring historical information corresponding to the user identification, wherein the historical information comprises the freezing time of a historical video label.
And step 104, recalling the video corresponding to the filtered video label to be processed.
In step 101, after a user performs a corresponding operation on a client, for example, clicks a recommendation entry, the client generates a video acquisition request, where the video acquisition request includes information such as a user identifier. And the client sends the video acquisition request to the recommendation system.
In step 102, the recommendation system stores history information corresponding to each user identifier, wherein the history information includes the freezing time of the history video tag. After receiving the video acquisition request, the recommendation system acquires the historical information corresponding to the user identification according to the user identification in the video acquisition request.
In step 103, the recommendation system obtains the to-be-processed video tags corresponding to the user identifier, and determines, for each to-be-processed video tag, whether the to-be-processed video tag is within the freezing time according to the freezing time of the history video tag recorded by the history information. In implementation, whether the to-be-processed video tag exists in the history information is searched, if yes, whether the to-be-processed video tag is within the freezing time is determined, and if not, the to-be-processed video tag is filtered.
In step 104, the recommendation system recalls the filtered videos corresponding to the remaining to-be-processed video tags in the video recall process.
In the embodiment of the invention, the to-be-processed video tags within the freezing time can be filtered according to the historical information corresponding to the user identification in the video recall process, so that the videos corresponding to the filtered to-be-processed video tags are not recalled within the freezing time, a large number of similar videos are avoided from being concentrated, the accuracy and diversity of video recall are improved, and the user experience is improved.
Example two
Fig. 2 is a flowchart illustrating a video recall method according to a second embodiment of the present invention. As shown in fig. 2, the video recall method may include the steps of:
And step 204, recalling the video corresponding to the filtered video label to be processed.
And step 207, when the user behavior information is that the recommended video is not clicked, determining whether the current video label meets a freezing condition according to the freezing time of the historical video label.
And 208, when the current video label meets the freezing condition, determining the freezing time of the current video label, and recording the freezing time of the current video label into the historical information.
In step 205, after the recommendation system recalls the video, the recalled video may be recommended to the user, the recommended video is displayed at the client of the user, the client may generate a corresponding user behavior log after the user performs some processing on the recommended video, and the client uploads the user behavior log to the recommendation system. The recommendation system receives a user behavior log uploaded by a client, wherein the user behavior log can include information such as a user identifier, user behavior information and a current video tag of a recommended video. Wherein the user behavior information may include videos that are recommended clicked and videos that are not recommended clicked. The user behavior of the user on the recommended video can also be used as the behavior of the user on the current video tag of the recommended video.
In step 206, the recommendation system stores history information corresponding to the user identifier, and the history information may record information such as the freezing time of each history video tag. The freezing time is set after the video is not clicked, and the non-clicked state indicates that the user is not interested in the video temporarily, namely, the video tag of the video is not interested, so that a period of freezing time can be set for the video tag.
In step 207 and step 208, considering that the video tags of the videos are real and continuous interests of the user, it is not reasonable to consider that the videos recommended to the user according to the video tags are excessively concentrated to cause poor effects and the videos are not interested by the user, so that the videos corresponding to the video tags are not recommended to the user any more subsequently if the video tags are directly deleted. Therefore, the embodiment of the invention sets a freezing mechanism for the video label, the video label is frozen in a short period of time, and the video label can be continuously used after being not frozen, so that the problem of excessive concentration of similar videos is avoided.
Therefore, when the recommendation system determines that the user behavior information included in the user behavior log is the un-clicked recommended video, whether the current video tag of the recommended video meets the freezing condition or not can be determined according to the freezing time of the historical video tag recorded in the historical information corresponding to the user identifier. And if the freezing condition is met, determining the freezing time of the current video label, and recording the freezing time of the current video label into the historical information. Here, if the freezing time of the current video tag is already recorded in the history information, the freezing time of the current video tag determined this time is recorded in the history information to update the freezing time. If the freezing condition is not satisfied, the freezing time of the current video tag does not need to be determined.
After the recalled video is recommended to the user, the historical information corresponding to the user identification can be updated according to the user behavior information of the user on the recommended video, so that the accuracy of the historical information is ensured.
EXAMPLE III
In the embodiment of the invention, the video recall method can comprise a recall process and an information updating process. The recall process corresponds to step 201 to step 204 in the second embodiment, and the information update process corresponds to step 205 to step 208 in the second embodiment. The embodiments of the present invention will respectively describe these two processes in detail.
In an implementation, the pending video tags may include pending user interest tags and/or pending content tags, and the historical video tags may include historical user interest tags and/or historical content tags. Wherein "and/or" means at least one of the two. The user interest tag refers to user interest corresponding to the video. The user interest tags may include at least one of: video identification, type label, content label. For example, the user interest tag corresponding to the video a is the video identifier B, or is the genre tag "sports", or is the content tag "basketball", and so on. The difference between the content tag in the user interest tag corresponding to the video and the content tag of the video is described here: the former is for the freezing of the user interest tag, for example, when the user interest tag is the content tag "basketball" is frozen, the video related to basketball cannot be recalled through the user interest tag "basketball", but the video related to basketball still may be recalled through the user interest tag such as "sports"; the latter is for freezing of the content tag of the video itself, for example, when the content tag "basketball" of the video is frozen, the video related to basketball will not be recalled.
Fig. 3 is a flowchart illustrating a recall procedure in a video recall method according to a third embodiment of the present invention. Fig. 3 illustrates an example in which the to-be-processed video tags include to-be-processed user interest tags and to-be-processed content tags, and the historical video tags include historical user interest tags and historical content tags. As shown in fig. 3, the recall process may include the following steps:
And 305, recalling the video corresponding to the residual video tag to be processed after filtering.
In step 303, the recommendation system stores user portrait information corresponding to the user identifier, and the user portrait information stores a user interest tag corresponding to the user identifier. Therefore, the recommendation system can acquire the user interest tag corresponding to the user identification from the user portrait information according to the user identification, and select the user interest tag which can be used for recalling from the user interest tag as the user interest tag to be processed. For example, the user interest tags in the user portrait information may have corresponding scores, and the user interest tags with scores exceeding a preset score threshold may be selected as the to-be-processed user interest tags. For example, user interest tags with a negative score cannot be used for recalls. And searching whether the freezing time of the interest tag of the user to be processed exists or not from the historical information aiming at each interest tag of the user to be processed, if so, judging whether the interest tag of the user to be processed is within the freezing time or not, and if so, filtering the interest tag of the user to be processed. For example, for the to-be-processed user interest tag a, if the freezing time of the to-be-processed user interest tag a in the history information is 9:30, the current time is obtained, and if the current time is 9:30 ago, it is determined that the to-be-processed user interest tag a is within the freezing time.
In step 304, after the to-be-processed user interest tags are filtered in step 303, to-be-processed content tags corresponding to the to-be-processed user interest tags remaining after filtering are obtained. Each user interest tag corresponds to a plurality of videos, and the content tags to be processed are the content tags of the videos corresponding to the filtered residual user interest tags to be processed. And searching whether the freezing time of the content tag to be processed exists or not from the historical information aiming at each content tag to be processed, if so, judging whether the content tag to be processed is within the freezing time or not, and if so, filtering the content tag to be processed. For example, for the to-be-processed content tag B, if the freezing time of the to-be-processed content tag B in the history information is 9:30, the current time is obtained, and if the current time is 9:30 ago, it is determined that the to-be-processed content tag B is within the freezing time.
In step 305, after the above-mentioned filtering of the to-be-processed user interest tags and the to-be-processed content tags, the videos corresponding to the filtered remaining to-be-processed content tags are recalled from the videos corresponding to the filtered remaining to-be-processed user interest tags.
In the embodiment of the invention, the accuracy of video recall can be further improved by double filtering the interest tags and the content tags of the user.
Fig. 4 is a flowchart illustrating steps of an information updating process in a video recall method according to a third embodiment of the present invention. As shown in fig. 4, the information update process may include the steps of:
And step 408, recording the occurrence time of the user behavior as the last non-click time of the current video tag.
And step 409, increasing the number of times of non-clicking the current video label once.
In step 401, the user behavior log includes the user identifier, the user behavior information, the current video tag of the recommended video, and the occurrence time of the user behavior, and of course, the user behavior log may also include information such as the video identifier of the recommended video.
Wherein the current video tags of the recommended videos may include current user interest tags and/or current content tags. "and/or" means at least one of the two.
For the occurrence time of the user behavior, if the user behavior information is the video recommended by clicking, the occurrence time of the user behavior is the time of clicking the video; and if the user behavior information is the video which is not recommended by clicking, the occurrence time of the user behavior is the generation time of a user behavior log and the like.
In step 402, the history information is used to record information of the history video tags, which may specifically include a freezing time of the history video tags, a number of times of non-clicks of the history video tags, and a last non-click time of the history video tags. When the user does not click on the video, the video tag of the video is not clicked. The last non-click time of the historical video tag can be the occurrence time of the last non-click behavior of the video corresponding to the historical video tag by the user.
In step 403, it is determined whether the user behavior information is a recommended clicked video or a recommended unchecked video, and different operations are performed according to different user behavior information.
In step 404, if the user behavior information is a video recommended without being clicked, since the current video tag may already exist in the history information or may not exist in the history information, different operations are performed for two different situations, so as to further determine whether the current video tag exists in the history information.
In step 405, considering that the purpose of the embodiment of the present invention is to freeze the video tag in a short time, so that similar videos do not appear in a concentrated manner in a short time, and therefore, the history information of the early time has little influence on the current time and can be deleted. And presetting a valid time threshold value for the historical video tags recorded in the historical information. And aiming at the received user behavior log, if the current video label exists in the historical information, acquiring the time interval between the occurrence time of the user behavior and the last non-click time of the current video label.
In step 406, it is determined whether the time interval is greater than a predetermined time threshold. For the specific value of the time threshold, any suitable value may be set by those skilled in the art according to practical experience, and the embodiment of the present invention is not limited thereto. For example, the time threshold may be set to 2 days, 3 days, etc.
In step 407, if the time interval is greater than the preset time threshold, it indicates that the interval between the current user behavior and the last time non-click time of the current video tag is longer, and the current video tag recorded in the history information has little influence on the current time, so that the current video tag is deleted from the history information, thereby improving the accuracy of the history information. For example, the last time of the current video tag recorded in the history information is 1 month and 1 day, and in the user behavior log received this time, the occurrence time of the user non-click behavior for the current video tag is 1 month and 4 days, and the interval is long, so that the recorded current video tag can be deleted from the history information.
In step 408 and step 409, if it is determined in step 404 that the current video tag does not exist in the history information, the current video tag is added to the history information, the occurrence time of the user behavior is recorded as the last non-click time of the current video tag, and the non-click number of the current video tag is increased once. The related information of the current video tag in the history information at this time may be: the number of times of non-clicking of the current video label is 1, the freezing time of the current video label is empty, and the last time of non-clicking of the current video label is set as the occurrence time of the user behavior in the user behavior log.
If the time interval is less than or equal to the preset time threshold value in step 406, the current video tag does not need to be deleted, the occurrence time of the user behavior is recorded as the last non-click time of the current video tag, and the non-click times of the current video tag is increased once. The related information of the current video tag in the history information at this time may be: the number of times of non-clicking of the current video label is increased once, the freezing time of the current video label is kept unchanged, and the last time of non-clicking of the current video label is set as the occurrence time of the user behavior in the user behavior log.
If the current video tag is deleted from the history information in step 407, the current video tag may be added to the history information again, the occurrence time of the user behavior is recorded as the last time of the current video tag, and the number of times of non-clicking of the current video tag is increased once. The related information of the current video tag in the history information at this time may be: the number of times of non-clicking of the current video label is 1, the freezing time of the current video label is empty, and the last time of non-clicking of the current video label is set as the occurrence time of the user behavior in the user behavior log.
It should be noted that the execution order of step 408 and step 409 is not limited in the embodiment of the present invention.
In step 410, it may be determined whether the current video tag satisfies the freezing condition according to the number of times of non-clicks of the current video tag in the history information. If the user determines that the current video tag meets the freezing condition without clicking once, the situation is not met, and the embodiment of the invention sets that the user does not click for many times, which indicates that the video corresponding to the video tag is not interested in the period of time. Therefore, a frequency threshold value is preset, and when the number of times of non-clicking of the current video tag is larger than the preset frequency threshold value, the current video tag is determined to meet the freezing condition. For the specific value of the time threshold, a person skilled in the art may set any suitable value according to practical experience, and the embodiment of the present invention is not limited thereto. For example, the number threshold may be set to 3 times, 5 times, 6 times, and so on.
In step 411, if the current video tag satisfies the freezing condition, the freezing time of the current video tag is further determined. In the embodiment of the invention, the freezing time of the current video label can be determined according to the number of times of non-clicking the current video label and the occurrence time of the user behavior. The method specifically comprises the following steps: calculating the freezing time of the current video label according to the number of times of non-clicking of the current video label; and determining the time after the freezing duration is continued from the occurrence time of the user behavior as the freezing time of the current video label. Wherein, the freezing time length and the number of times of non-click are in positive correlation, namely the larger the number of times of non-click is, the larger the freezing time length is. For example, the freezing time is 10 minutes, the occurrence time of the user behavior is 9: 00, the freezing time is 9: 10. The freezing time refers to the freezing termination time, i.e., freezing before 9:10 and not freezing after 9: 10.
In an alternative embodiment, the freezing time may be calculated according to the following formula:
revive_time＝sizeof(window)^2*6+120+T
wherein, the fresh _ time is the freezing time, the sizeof (window) is the non-click number, and T is the occurrence time of the user behavior, then the sizeof (window) 2 + 6+120 is the freezing time, and the unit of the freezing time is second.
In step 412, if it is determined in step 403 that the user behavior information is the video recommended by the click, it indicates that the current video tag of the clicked video is interested in the user in this period of time, and therefore the current video tag is not frozen. And when the current video tag exists in the historical information, deleting the current video tag from the historical information. And when the current video label does not exist in the historical information, no processing is performed.
In the embodiment of the invention, by analyzing the user behavior in real time, the video tags which are not interested by the user in the near future are frozen in a short time instead of deleted in a whole day, the short-time freezing is equivalent to breaking up the interest, similar contents cannot be concentrated, the accuracy and diversity of videos are improved, the real-time experience of the user is concerned, the processing of historical information is more accurate and rapid, and the interactivity is stronger.
Example four
Fig. 5 is a block diagram of a video recall device according to a fourth embodiment of the present invention. As shown in fig. 5, the video recall apparatus may include the following modules:
a first receiving module 501, configured to receive a video obtaining request, where the video obtaining request includes a user identifier.
A first obtaining module 502, configured to obtain history information corresponding to the user identifier, where the history information includes a freezing time of a history video tag.
The filtering module 503 is configured to obtain a to-be-processed video tag corresponding to the user identifier, determine whether the to-be-processed video tag is within the freezing time according to the freezing time of the historical video tag, and filter the to-be-processed video tag within the freezing time.
And a recall module 504, configured to recall a video corresponding to the filtered remaining to-be-processed video tag.
In the embodiment of the invention, the to-be-processed video tags within the freezing time can be filtered according to the historical information corresponding to the user identification in the video recall process, so that the videos corresponding to the filtered to-be-processed video tags are not recalled any more, the situation that a large number of similar videos are concentrated is avoided, the accuracy and diversity of the recalled videos are improved, and the user experience is improved.
EXAMPLE five
Fig. 6 is a block diagram of a video recall device according to a fifth embodiment of the present invention. As shown in fig. 6, the video recall apparatus may include the following modules.
A first receiving module 601, configured to receive a video obtaining request, where the video obtaining request includes a user identifier.
A first obtaining module 602, configured to obtain history information corresponding to the user identifier, where the history information includes a freezing time of a history video tag.
The filtering module 603 is configured to obtain a to-be-processed video tag corresponding to the user identifier, determine whether the to-be-processed video tag is within the freezing time according to the freezing time of the historical video tag, and filter the to-be-processed video tag within the freezing time.
The recalling module 604 is configured to recall the video corresponding to the remaining to-be-processed video tag after filtering.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and/or to-be-processed content tags, and the historical video tags include historical user interest tags and/or historical content tags.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and to-be-processed content tags, and the historical video tags include historical user interest tags and historical content tags; the filtering module 603 includes: an interest filtering unit 6031, configured to obtain a to-be-processed user interest tag corresponding to the user identifier, determine whether the to-be-processed user interest tag is within the freezing time according to the freezing time of the historical user interest tag, and filter the to-be-processed user interest tag within the freezing time; a content filtering unit 6032, configured to obtain the to-be-processed content tags corresponding to the to-be-processed user interest tags remaining after filtering, determine whether the to-be-processed content tags are within the freezing time according to the freezing time of the historical content tags, and filter the to-be-processed content tags within the freezing time.
Optionally, the apparatus further comprises: a second receiving module 605, configured to receive a user behavior log after recommending a recalled video to a user; the user behavior log comprises the user identification, user behavior information and a current video tag of a recommended video; a second obtaining module 606, configured to obtain history information corresponding to the user identifier; a first determining module 607, configured to determine whether the current video tag meets a freezing condition according to the freezing time of the historical video tag when the user behavior information is that the recommended video is not clicked; a second determining module 608, configured to determine a freezing time of the current video tag when the current video tag meets a freezing condition, and record the freezing time of the current video tag into the history information.
Optionally, the user behavior log further includes occurrence time of user behavior, and the history information further includes last non-click time of a history video tag; the device further comprises: a third obtaining module 609, configured to obtain a time interval between occurrence time of the user behavior and last non-click time of the current video tag; a first deleting module 610, configured to delete the current video tag from the history information when the time interval is greater than a preset time threshold.
Optionally, the apparatus further comprises: a second deleting module 611, configured to delete the current video tag from the history information when the user behavior information is that the recommended video is clicked and the current video tag exists in the history information.
Optionally, the history information further includes the number of times of non-clicks of the history video tag; the device further comprises: an increasing module 612, configured to increase the number of times of non-clicks of the current video tag by one time.
Optionally, the user behavior log further comprises occurrence times of user behaviors; the second determining module 608 includes: a duration calculation unit 6081 configured to calculate a freezing duration of the current video tag according to the number of times of non-clicking of the current video tag; the freezing time length is positively correlated with the number of times of non-clicks; a time determining unit 6082, configured to determine a time after the duration of the freezing time from the occurrence time of the user behavior as the freezing time of the current video tag.
Optionally, the first determining module 607 is specifically configured to determine that the current video tag meets a freezing condition when the number of times of non-clicks of the current video tag is greater than a preset number threshold.
In the embodiment of the invention, the accuracy of video recall can be further improved by double filtering the interest tags and the content tags of the user. The accuracy and diversity of videos are improved, the real-time experience of users is concerned, the historical information is processed more accurately and rapidly, and the interactivity is stronger.
An embodiment of the present invention further provides an electronic device, as shown in fig. 7, including a processor 701, a communication interface 702, a memory 703 and a communication bus 704, where the processor 701, the communication interface 702, and the memory 703 complete mutual communication through the communication bus 704,
a memory 703 for storing a computer program;
the processor 701 is configured to implement the following steps when executing the program stored in the memory 703:
receiving a video acquisition request, wherein the video acquisition request comprises a user identifier;
acquiring historical information corresponding to the user identification, wherein the historical information comprises the freezing time of a historical video label;
acquiring a to-be-processed video tag corresponding to the user identifier, determining whether the to-be-processed video tag is within the freezing time according to the freezing time of the historical video tag, and filtering the to-be-processed video tag within the freezing time;
and recalling the videos corresponding to the residual video tags to be processed after filtering.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and/or to-be-processed content tags, and the historical video tags include historical user interest tags and/or historical content tags.
Optionally, the to-be-processed video tags include to-be-processed user interest tags and to-be-processed content tags, and the historical video tags include historical user interest tags and historical content tags; the step of obtaining the video tag to be processed corresponding to the user identifier, determining whether the video tag to be processed is within the freezing time according to the freezing time of the historical video tag, and filtering the video tag to be processed within the freezing time includes: acquiring a to-be-processed user interest tag corresponding to the user identifier, determining whether the to-be-processed user interest tag is within the freezing time according to the freezing time of the historical user interest tag, and filtering the to-be-processed user interest tag within the freezing time; and acquiring the to-be-processed content tags corresponding to the filtered residual to-be-processed user interest tags, determining whether the to-be-processed content tags are within the freezing time according to the freezing time of the historical content tags, and filtering the to-be-processed content tags within the freezing time.
Optionally, the method further comprises: after recommending a recalled video to a user, receiving a user behavior log; the user behavior log comprises the user identification, user behavior information and a current video tag of a recommended video; acquiring historical information corresponding to the user identification; when the user behavior information is that the recommended video is not clicked, determining whether the current video label meets a freezing condition or not according to the freezing time of the historical video label; and when the current video label meets the freezing condition, determining the freezing time of the current video label, and recording the freezing time of the current video label into the historical information.
Optionally, the user behavior log further includes occurrence time of user behavior, and the history information further includes last non-click time of a history video tag; before the step of determining whether the current video tag meets the freezing condition according to the freezing time of the historical video tag, the method further comprises the following steps: when the current video tag exists in the historical information, acquiring a time interval between occurrence time of the user behavior and last non-click time of the current video tag; and when the time interval is greater than a preset time threshold, deleting the current video tag from the historical information.
Optionally, after the step of obtaining the history information corresponding to the user identifier, the method further includes: and when the user behavior information is the video which is clicked to recommend and the current video tag exists in the historical information, deleting the current video tag from the historical information.
Optionally, the history information further includes the number of times of non-clicks of the history video tag; before the step of determining whether the current video tag meets the freezing condition according to the freezing time of the historical video tag, the method further comprises the following steps: and increasing the number of times of non-clicking of the current video label once.
Optionally, the user behavior log further comprises occurrence times of user behaviors; the step of determining the freezing time of the current video tag comprises the following steps: calculating the freezing time length of the current video label according to the number of times of non-clicking of the current video label; the freezing time length is positively correlated with the number of times of non-clicks; and determining the time after the duration of the freezing time from the occurrence time of the user behavior as the freezing time of the current video tag.
Optionally, the step of determining whether the current video tag meets a freezing condition according to the freezing time of the historical video tag includes: and when the number of times of non-clicking of the current video label is larger than a preset number threshold value, determining that the current video label meets the freezing condition.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In yet another embodiment, a computer-readable storage medium is provided, having stored thereon instructions, which, when executed on a computer, cause the computer to perform the method of any of the above embodiments.
In a further embodiment provided by the present invention, there is also provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (12)
1. A method for video recall, the method comprising:
receiving a video acquisition request, wherein the video acquisition request comprises a user identifier;
acquiring historical information corresponding to the user identification, wherein the historical information comprises freezing time of a historical video tag, and the freezing time is a period of time set for the video tag of the video after the video recommended to the user is not clicked;
acquiring a to-be-processed video tag corresponding to the user identifier, determining whether the to-be-processed video tag is within the freezing time according to the freezing time of the historical video tag, and filtering the to-be-processed video tag within the freezing time;
and recalling the videos corresponding to the residual video tags to be processed after filtering.
2. The method according to claim 1, wherein the pending video tags comprise pending user interest tags and/or pending content tags and the historical video tags comprise historical user interest tags and/or historical content tags.
3. The method of claim 1, wherein the pending video tags comprise pending user interest tags and pending content tags, and wherein the historical video tags comprise historical user interest tags and historical content tags;
the step of obtaining the video tag to be processed corresponding to the user identifier, determining whether the video tag to be processed is within the freezing time according to the freezing time of the historical video tag, and filtering the video tag to be processed within the freezing time includes:
acquiring a to-be-processed user interest tag corresponding to the user identifier, determining whether the to-be-processed user interest tag is within the freezing time according to the freezing time of the historical user interest tag, and filtering the to-be-processed user interest tag within the freezing time;
and acquiring the to-be-processed content tags corresponding to the filtered residual to-be-processed user interest tags, determining whether the to-be-processed content tags are within the freezing time according to the freezing time of the historical content tags, and filtering the to-be-processed content tags within the freezing time.
4. The method of claim 1, further comprising:
after recommending a recalled video to a user, receiving a user behavior log; the user behavior log comprises the user identification, user behavior information and a current video tag of a recommended video;
acquiring historical information corresponding to the user identification;
when the user behavior information is that the recommended video is not clicked, determining whether the current video label meets a freezing condition or not according to the freezing time of the historical video label;
and when the current video label meets the freezing condition, determining the freezing time of the current video label, and recording the freezing time of the current video label into the historical information.
5. The method of claim 4, wherein the user behavior log further comprises a time of occurrence of a user behavior, and wherein the historical information further comprises a last time unchecked time of a historical video tag; before the step of determining whether the current video tag meets the freezing condition according to the freezing time of the historical video tag, the method further comprises the following steps:
when the current video tag exists in the historical information, acquiring a time interval between occurrence time of the user behavior and last non-click time of the current video tag;
and when the time interval is greater than a preset time threshold, deleting the current video tag from the historical information.
6. A video recall apparatus, the apparatus comprising:
the system comprises a first receiving module, a second receiving module and a video acquiring module, wherein the first receiving module is used for receiving a video acquiring request which comprises a user identifier;
the first acquisition module is used for acquiring historical information corresponding to the user identifier, wherein the historical information comprises freezing time of a historical video tag, and the freezing time is a period of time set for the video tag of the video after the video recommended to the user is not clicked;
the filtering module is used for acquiring the video tag to be processed corresponding to the user identifier, determining whether the video tag to be processed is within the freezing time according to the freezing time of the historical video tag, and filtering the video tag to be processed within the freezing time;
and the recall module is used for recalling the videos corresponding to the residual video tags to be processed after filtering.
7. The apparatus of claim 6, wherein the pending video tags comprise pending user interest tags and/or pending content tags and the historical video tags comprise historical user interest tags and/or historical content tags.
8. The apparatus of claim 6, wherein the pending video tags comprise a pending user interest tag and a pending content tag, and wherein the historical video tags comprise a historical user interest tag and a historical content tag; the filtration module includes:
the interest filtering unit is used for acquiring the interest tags of the users to be processed corresponding to the user identifications, determining whether the interest tags of the users to be processed are within the freezing time according to the freezing time of the historical interest tags of the users, and filtering the interest tags of the users to be processed within the freezing time;
and the content filtering unit is used for acquiring the to-be-processed content tags corresponding to the to-be-processed user interest tags remaining after filtering, determining whether the to-be-processed content tags are within the freezing time according to the freezing time of the historical content tags, and filtering the to-be-processed content tags within the freezing time.
9. The apparatus of claim 6, further comprising:
the second receiving module is used for receiving the user behavior log after the recalled video is recommended to the user; the user behavior log comprises the user identification, user behavior information and a current video tag of a recommended video;
the second acquisition module is used for acquiring historical information corresponding to the user identification;
the first determining module is used for determining whether the current video label meets a freezing condition according to the freezing time of the historical video label when the user behavior information is that the recommended video is not clicked;
and the second determining module is used for determining the freezing time of the current video label when the current video label meets the freezing condition, and recording the freezing time of the current video label into the historical information.
10. The apparatus of claim 9, wherein the user behavior log further comprises a time of occurrence of a user behavior, and wherein the historical information further comprises a last time unchecked time of a historical video tag; the device further comprises:
a third obtaining module, configured to obtain, when the current video tag exists in the history information, a time interval between occurrence time of the user behavior and last non-click time of the current video tag;
and the first deleting module is used for deleting the current video tag from the historical information when the time interval is greater than a preset time threshold.
11. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method of any one of claims 1 to 5 when executing a program stored in the memory.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911089842.8A CN110996142B (en) | 2019-11-08 | 2019-11-08 | Video recall method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911089842.8A CN110996142B (en) | 2019-11-08 | 2019-11-08 | Video recall method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110996142A CN110996142A (en) | 2020-04-10 |
| CN110996142B true CN110996142B (en) | 2021-12-07 |
Family
ID=70083853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911089842.8A Active CN110996142B (en) | 2019-11-08 | 2019-11-08 | Video recall method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110996142B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114079826B (en) * | 2020-08-14 | 2023-11-28 | 北京达佳互联信息技术有限公司 | Video recommendation list generation method, device, server and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105163183A (en) * | 2015-08-28 | 2015-12-16 | 北京奇艺世纪科技有限公司 | Screening method and device for video pictures |
| CN105897785A (en) * | 2016-06-30 | 2016-08-24 | 宇龙计算机通信科技(深圳)有限公司 | Method for managing application in combination with cloud data and terminal |
| CN106326431A (en) * | 2016-08-25 | 2017-01-11 | 乐视控股（北京）有限公司 | Information recommendation method and device |
| CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN106407418A (en) * | 2016-09-23 | 2017-02-15 | Tcl集团股份有限公司 | A face identification-based personalized video recommendation method and recommendation system |
| CN106851328A (en) * | 2017-01-17 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Live interactive approach and device |
| CN107332905A (en) * | 2017-06-30 | 2017-11-07 | 广州优视网络科技有限公司 | Information-pushing method, device and server |
| CN108197331A (en) * | 2015-01-21 | 2018-06-22 | 北京字节跳动科技有限公司 | The heuristic approach and device of user interest |
| CN108228784A (en) * | 2017-12-28 | 2018-06-29 | 暴风集团股份有限公司 | Video recommendation method and device, electronic equipment, storage medium, program |
| CN108334536A (en) * | 2017-11-30 | 2018-07-27 | 中国电子科技集团公司电子科学研究院 | A kind of information recommendation method, equipment and storage medium |
| CN108540860A (en) * | 2018-02-28 | 2018-09-14 | 北京奇艺世纪科技有限公司 | A kind of video recalls method and apparatus |
| CN109218767A (en) * | 2018-09-03 | 2019-01-15 | 中山大学 | A kind of recommended method towards TV box order video based on Time Perception |
| CN109670077A (en) * | 2018-11-01 | 2019-04-23 | 北京达佳互联信息技术有限公司 | Video recommendation method, device and computer readable storage medium |
| CN110263244A (en) * | 2019-02-14 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, storage medium and computer equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190050876A1 (en) * | 2014-12-03 | 2019-02-14 | Eventsq Llc | Content recommendation based on user feedback of content in a networked environment captured using a single action |
| CN104869439B (en) * | 2015-05-14 | 2018-03-09 | 无锡天脉聚源传媒科技有限公司 | A kind of video pushing method and device |
| US10180968B2 (en) * | 2015-07-23 | 2019-01-15 | Netflix, Inc. | Gaussian ranking using matrix factorization |
| CN105930425A (en) * | 2016-04-18 | 2016-09-07 | 乐视控股（北京）有限公司 | Personalized video recommendation method and apparatus |
| CN106844446A (en) * | 2016-12-16 | 2017-06-13 | 飞狐信息技术（天津）有限公司 | Video methods of marking, device and video system based on user's viewing behavior |
| CN110019941A (en) * | 2017-08-22 | 2019-07-16 | 飞狐信息技术（天津）有限公司 | Video recommendation method and system |
-
2019
- 2019-11-08 CN CN201911089842.8A patent/CN110996142B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197331A (en) * | 2015-01-21 | 2018-06-22 | 北京字节跳动科技有限公司 | The heuristic approach and device of user interest |
| CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN105163183A (en) * | 2015-08-28 | 2015-12-16 | 北京奇艺世纪科技有限公司 | Screening method and device for video pictures |
| CN105897785A (en) * | 2016-06-30 | 2016-08-24 | 宇龙计算机通信科技(深圳)有限公司 | Method for managing application in combination with cloud data and terminal |
| CN106326431A (en) * | 2016-08-25 | 2017-01-11 | 乐视控股（北京）有限公司 | Information recommendation method and device |
| CN106407418A (en) * | 2016-09-23 | 2017-02-15 | Tcl集团股份有限公司 | A face identification-based personalized video recommendation method and recommendation system |
| CN106851328A (en) * | 2017-01-17 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Live interactive approach and device |
| CN107332905A (en) * | 2017-06-30 | 2017-11-07 | 广州优视网络科技有限公司 | Information-pushing method, device and server |
| CN108334536A (en) * | 2017-11-30 | 2018-07-27 | 中国电子科技集团公司电子科学研究院 | A kind of information recommendation method, equipment and storage medium |
| CN108228784A (en) * | 2017-12-28 | 2018-06-29 | 暴风集团股份有限公司 | Video recommendation method and device, electronic equipment, storage medium, program |
| CN108540860A (en) * | 2018-02-28 | 2018-09-14 | 北京奇艺世纪科技有限公司 | A kind of video recalls method and apparatus |
| CN109218767A (en) * | 2018-09-03 | 2019-01-15 | 中山大学 | A kind of recommended method towards TV box order video based on Time Perception |
| CN109670077A (en) * | 2018-11-01 | 2019-04-23 | 北京达佳互联信息技术有限公司 | Video recommendation method, device and computer readable storage medium |
| CN110263244A (en) * | 2019-02-14 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Content recommendation method, device, storage medium and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 基于ＤＮＮ算法的移动视频推荐策略;陈亮;《计算机学报》;20160831;第1626-1638页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110996142A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109451333B (en) | Bullet screen display method, device, terminal and system | |
| CN109685144B (en) | Method and device for evaluating video model and electronic equipment | |
| CN111666448B (en) | Search method, search device, electronic equipment and computer readable storage medium | |
| CN111225246B (en) | Video recommendation method and device and electronic equipment | |
| CN110856037A (en) | Video cover determination method and device, electronic equipment and readable storage medium | |
| CN112765400B (en) | Weight updating method, content recommending method, device and equipment for interest labels | |
| CN111815375B (en) | User portrayal method and device in advertisement putting | |
| CN110674345A (en) | Video searching method and device and server | |
| CN112669078A (en) | Behavior prediction model training method, device, equipment and storage medium | |
| CN110121088B (en) | User attribute information determination method and device and electronic equipment | |
| CN110996142B (en) | Video recall method and device, electronic equipment and storage medium | |
| CN111669622A (en) | Method and device for determining default play relationship of videos and electronic equipment | |
| CN111090810A (en) | Application message pushing method and device and electronic equipment | |
| CN112883275B (en) | Live broadcast room recommendation method, device, server and medium | |
| CN111597380B (en) | Recommended video determining method and device, electronic equipment and storage medium | |
| CN113743963A (en) | Abnormal recognition model training method, abnormal object recognition device and electronic equipment | |
| CN111314744B (en) | Video pushing method and server | |
| CN112995765A (en) | Network resource display method and device | |
| CN112785333A (en) | Advertisement putting method, electronic device, storage medium and device | |
| CN111314790A (en) | Video playing record sequencing method and device and electronic equipment | |
| CN110213630B (en) | Video processing method and device, electronic equipment and medium | |
| CN109740621B (en) | Video classification method, device and equipment | |
| CN109168044B (en) | Method and device for determining video characteristics | |
| CN115984734A (en) | Model training method, video recall method, model training device, video recall device, electronic equipment and storage medium | |
| CN110971973A (en) | Video pushing method and device and electronic equipment |
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 |