CN105915956A - Video content recommendation method, device, server and system - Google Patents
Video content recommendation method, device, server and system Download PDFInfo
- Publication number
- CN105915956A CN105915956A CN201510940029.2A CN201510940029A CN105915956A CN 105915956 A CN105915956 A CN 105915956A CN 201510940029 A CN201510940029 A CN 201510940029A CN 105915956 A CN105915956 A CN 105915956A
- Authority
- CN
- China
- Prior art keywords
- video content
- show
- type
- dissimilar
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—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
- H04N21/45—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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a video content recommendation method, device, server and system. The method comprises the steps that the type of video content of historical watching records and the conversion rate of different types of video content are determined; the type of new video content to be released is acquired and the recommendable values of different types of new video content to be released are calculated; and the recommendable video content is selected from the new video content to be released according to the type of video content of the historical watching records and the conversion rate of different types of video content and the type of new video content to be released and the corresponding recommendable values. The problems in the prior art that the focus of user interest cannot be accurately positioned due to the face that video classification is extensive and the search result depends on search experience and skills can be solved by the video content recommendation method, device, server and system.
Description
Technical field
The present embodiments relate to video technique field, particularly relate to recommendation method, device, server and the system of a kind of video content.
Background technology
The development pole the earth of network technology and video compression technology has promoted the development of Video Applications.And the development of video traffic derives from the promotion of abundant video content, the increase of number of videos and the variation of content also will certainly be caused.
For a user, on the one hand abundant substance film enriches the selection of user, but on the other hand but adds the difficulty that film selects.
To this end, existing Video Applications is in order to solve the problems referred to above, most of existing operation systems provide " collection " function, but it can only be to user it has been determined that film interested be collected；Still further aspect is classified the most in advance, such as, video content is divided into action movie, romance movie etc., or video content is divided into continent film, American film etc., thus assist user to select film.When " search " function that user uses on network, the key word that it provides according to user carries out relevant matches, retrieves the content that user may be interested.
But, the mode of above-mentioned this retrieval needs user oneself to provide key word, when search in order to precisely mate Search Results, usually search experience and skill to user there are certain requirements, and due to when video content classification, the classification divided is the most extensive, it is impossible to navigate to the interest focus of user accurately.
Summary of the invention
The purpose of the embodiment of the present invention is to provide the matching process of a kind of video content, device, server and system, in order to solve in prior art due to visual classification is extensive and Search Results depends on that search experience and skill etc. cause cannot the problem of precise positioning user interest focus.
The technical scheme that the embodiment of the present invention uses is as follows:
The embodiment of the present invention provides a kind of recommendation method of video content, comprising:
Determine type and the conversion ratio of dissimilar video content of video content in described history viewing record；
The type of the new video content that acquisition will be shown calculating and the dissimilar new video content that will show can recommendation；
According to the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
Preferably, in arbitrary embodiment of the present invention, described determine in described history viewing record also include before the type of video content and the conversion ratio of dissimilar video content: the history viewing record obtaining in predetermined amount of time, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record.
Preferably, in arbitrary embodiment of the present invention, described determine in described history viewing record also include before the type of video content and the conversion ratio of dissimilar video content: obtain the history viewing record of predetermined quantity size, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record.
Preferably, in arbitrary embodiment of the present invention, determine that in described history viewing record, the type of video content and the conversion ratio of dissimilar video content include:
Determine in described history viewing record the type of video content and the hits of dissimilar video content and exposure frequency；
The conversion ratio of dissimilar video content in described history viewing record is determined according to hits and the exposure frequency of video content in described history viewing record.
Preferably, in arbitrary embodiment of the present invention, the described type determining video content in described history viewing record and the hits of dissimilar video content and exposure frequency include:
Determine in described history viewing record the type of video content and the hits of dissimilar video content and and the video content number of times by user's ken, described exposure frequency includes that video content passes through the number of times of user's ken.
Preferably, in arbitrary embodiment of the present invention, can recommendation including of the type of the new video content that described acquisition will be shown calculating and the dissimilar new video content that will show:
The type of the new video content that acquisition will be shown and the on-line time of dissimilar new video content that will show, according to described on-line time generate described can recommendation.
Preferably, in arbitrary embodiment of the present invention, the type of the new video content that described acquisition will be shown and the on-line time of dissimilar new video content that will show include:
The type of the new video content that acquisition will be shown and the on-line time of dissimilar new video content that will show, described on-line time is the on-line time of user location.
Preferably, in arbitrary embodiment of the present invention, can recommendation including of the type of the new video content that described acquisition will be shown calculating and the dissimilar new video content that will show:
The type of the new video content that acquisition will be shown and the on-line time of dissimilar new video content that will show and put on show the time；
What on-line time according to the dissimilar new video content that will show and the time of putting on show determined the described dissimilar new video content that will show can recommendation.
Preferably, in arbitrary embodiment of the present invention, the type of the new video content that described acquisition will be shown and the on-line time of dissimilar new video content and the time of putting on show that will show include: the type obtaining the new video content that will show and the on-line time of the dissimilar new video content that will show and put on show the time, described on-line time is included in the on-site on-line time of user, described in the time of putting on show be included in the whole world put on show the time.
The embodiment of the present invention also provides for the recommendation apparatus of a kind of video content, comprising:
Conversion ratio determines unit, for determining type and the conversion ratio of dissimilar video content of video content in described history viewing record；
Can recommendation computing unit, can recommendation for obtain the type of new video content calculating that will show and the dissimilar new video content that will show；
Recommendation unit, for watching type and the conversion ratio of dissimilar video content of video content in record according to described history, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
The embodiment of the present invention also provides for a kind of video recommendations server, it includes memorizer and processor, described processor is for determining the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and obtain the type of the new video content that will show calculating and the dissimilar new video content that will show can recommendation；And for watching type and the conversion ratio of dissimilar video content of video content in record according to described history, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show；Described memorizer for storing the type of video content and the conversion ratio of dissimilar video content in described history viewing record, described history viewing record, and the type of the new video content that will show and correspondence can recommendation.
The embodiment of the present invention also provides for a kind of video recommendation system, it includes video recommendations server and video playing terminal, video recommendations server includes memorizer and processor, processor is for determining the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and obtain the type of the new video content that will show calculating and the dissimilar new video content that will show can recommendation；And for watching type and the conversion ratio of dissimilar video content of video content in record according to described history, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show；Described memorizer for storing the type of video content and the conversion ratio of dissimilar video content in described history viewing record, described history viewing record, and the type of the new video content that will show and correspondence can recommendation.
The technical scheme of the embodiment of the present invention has the advantage that the embodiment of the present invention watches type and the conversion ratio of dissimilar video content of video content in record according to described history, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show, thus solve in prior art due to visual classification is extensive and Search Results depends on that search experience and skill etc. cause cannot the problem of precise positioning user interest focus.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in describing below is some embodiments of the present invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the recommendation method flow schematic diagram of the embodiment of the present invention one video content；
Fig. 2 is the schematic flow sheet of the embodiment of the present invention two step S102；
Fig. 3 is the recommendation method flow schematic diagram of the embodiment of the present invention three video content；
Fig. 4 is the recommendation method flow schematic diagram of the embodiment of the present invention four video content；
Fig. 5 is the recommendation method flow schematic diagram of the embodiment of the present invention five video content；
Fig. 6 is the recommendation method flow schematic diagram of the embodiment of the present invention six video content；
Fig. 7 is the recommendation apparatus structural representation of the embodiment of the present invention seven video content；
Fig. 8 is the recommendation apparatus structural representation of the embodiment of the present invention eight video content；
Fig. 9 is the structural representation of the embodiment of the present invention nine video recommendations server；
Figure 10 is the structural representation of the embodiment of the present invention ten video recommendation system.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art are obtained under not making creative work premise, broadly fall into the scope of protection of the invention.
Video content described in the following embodiment of the present invention includes the video content pushed by convention video web-site, also includes the video content pushed by third party application.
Fig. 1 is the recommendation method flow schematic diagram of the embodiment of the present invention one video content；As it is shown in figure 1, comprising:
S101, the type determining video content in described history viewing record and the conversion ratio of dissimilar video content；
In the present embodiment, the type of video content includes film, documentary film or TV play etc., it is also possible to include the regional information such as continent, Europe, Hong Kong, TaiWan, China etc. of film.
In the present embodiment, label or its breadcrumb that in history viewing record, the type of video content can be carried by video content determine, it includes all information relevant to the video content of browsed video content, viewing, including browsing time, viewing time, the integrity etc. of viewing.The information that history viewing record includes can be set up with indexed mode and preserve.
In the present embodiment, history viewing record can be saved in this locality, it is also possible to is saved on background server.By data-interface, obtain history viewing record from local or background server.
In the present embodiment, when step S102 determines the conversion ratio of the type of video content and dissimilar video content in described history viewing record, following step S112 and S122 can be specifically included.Fig. 2 is the schematic flow sheet of the embodiment of the present invention two step S102；As in figure 2 it is shown, it specifically may include that
S112, the type determining video content in described history viewing record and the hits of dissimilar video content and exposure frequency；
S122, the hits watching video content in record according to described history and exposure frequency determine the conversion ratio of dissimilar video content in described history viewing record.
In the present embodiment, specifically, step S112 can specifically include: determine in described history viewing record the type of video content and the hits of dissimilar video content and and the video content number of times by user's ken, described exposure frequency includes that video content passes through the number of times of user's ken.If by webpage viewing video, then exposure frequency can be determined by the number of times in the visible scope of user in browser.
In the present embodiment, the hits of video content is reflected the point of interest that user is possible, combining corresponding exposure frequency, the conversion ratio of correspondence can be learnt.
S102, obtain the type of new video content calculating that will show and the dissimilar new video content that will show can recommendation；
In the present embodiment, carry out adaptation, to recommend most probable to meet the video content of user interest focus to user by recommendation and conversion ratio.
This recommendation can calculate in conjunction with the on-line time of video content and/or the time of putting on show, refers to aftermentioned embodiment in detail and records, does not repeats them here.
S103, according to the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
In the present embodiment, by being analyzed obtaining conversion ratio to history viewing record, estimate the point of interest of user；From the point of interest of user, estimate with user interest point matching degree by new video content is carried out again, generating one can recommendation, can will can give the user that this type of video with higher conversion is corresponding by the biggest new video commending contents of recommendation, when specifically recommending, can sort according to the size of recommendation, it is recommended that what value was the biggest shows the highest with the interest points matching degree of user.
In the present embodiment, can the calculating of recommendation can judge according to the on-line time of video content, on-line time is the most late, can recommendation less, the most then can recommend bigger.
Fig. 3 is the recommendation method flow schematic diagram of the embodiment of the present invention three video content；As it is shown on figure 3, comprising:
S301, the history viewing record obtained in predetermined amount of time；
In the present embodiment, in order to improve the speed that data process, only choose the history viewing record in predetermined amount of time.Predetermined amount of time can be configured according to the preference of the custom of user, viewing video content.
S302, the type determining video content in described history viewing record and the conversion ratio of dissimilar video content；
In the present embodiment, the determination of conversion ratio can be achieved by the steps of: first, determines in described history viewing record the type of video content and the hits of dissimilar video content and exposure frequency；Secondly the conversion ratio of dissimilar video content in described history viewing record is determined according to hits and the exposure frequency of video content in described history viewing record.
S303, obtain the type of new video content calculating that will show and the dissimilar new video content that will show can recommendation；
In the present embodiment, carry out adaptation, to recommend most probable to meet the video content of user interest focus to user by follow-up with conversion ratio.
This recommendation can calculate in conjunction with the on-line time of video content and/or the time of putting on show, refers to aftermentioned embodiment in detail and records, does not repeats them here.
S304, according to the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
In the present embodiment, by being analyzed obtaining conversion ratio to history viewing record, estimate the point of interest of user；From the point of interest of user, estimate with user interest point matching degree by new video content is carried out again, generating one can recommendation, can will can give the user that this type of video with higher conversion is corresponding by the biggest new video commending contents of recommendation, when specifically recommending, can sort according to the size of recommendation, it is recommended that what value was the biggest shows the highest with the interest points matching degree of user.
Fig. 4 is the recommendation method flow schematic diagram of the embodiment of the present invention four video content；As shown in Figure 4, comprising:
S401, the history viewing record of acquisition predetermined quantity size；
In the present embodiment, in order to improve the speed that data process, only choose the history viewing record of predetermined amount of data size.Predetermined amount of data size can be configured according to the preference of the custom of user, viewing video content.
S402, the type determining video content in described history viewing record and the conversion ratio of dissimilar video content；
In the present embodiment, the determination of conversion ratio can be achieved by the steps of: first, determines in described history viewing record the type of video content and the hits of dissimilar video content and exposure frequency；Secondly the conversion ratio of dissimilar video content in described history viewing record is determined according to hits and the exposure frequency of video content in described history viewing record.
S403, obtain the type of new video content calculating that will show and the dissimilar new video content that will show can recommendation；
In the present embodiment, carry out adaptation, to recommend most probable to meet the video content of user interest focus to user by follow-up with conversion ratio.
This recommendation can calculate in conjunction with the on-line time of video content and/or the time of putting on show, refers to aftermentioned embodiment in detail and records, does not repeats them here.
S404, according to the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
In the present embodiment, by being analyzed obtaining conversion ratio to history viewing record, estimate the point of interest of user；From the point of interest of user, estimate with user interest point matching degree by new video content is carried out again, generating one can recommendation, can will can give the user that this type of video with higher conversion is corresponding by the biggest new video commending contents of recommendation, when specifically recommending, can sort according to the size of recommendation, it is recommended that what value was the biggest shows the highest with the interest points matching degree of user.
Fig. 5 is the recommendation method flow schematic diagram of the embodiment of the present invention five video content；As it is shown in figure 5, comprising:
S501, the type determining video content in described history viewing record and the conversion ratio of dissimilar video content；
In the present embodiment, the type of video content includes film, documentary film or TV play etc., it is also possible to include the regional information such as continent, Europe, Hong Kong, TaiWan, China etc. of film.
In the present embodiment, label or its breadcrumb that in history viewing record, the type of video content can be carried by video content determine, it includes all information relevant to the video content of browsed video content, viewing, including browsing time, viewing time, the integrity etc. of viewing.The information that history viewing record includes can be set up with indexed mode and preserve.
In the present embodiment, history viewing record can be saved in this locality, it is also possible to is saved on background server.By data-interface, obtain history viewing record from local or background server.
S502, obtain the type of new video content that will show and the on-line time of the dissimilar new video content that will show, according to described on-line time generate described can recommendation.
In the present embodiment, for the video content of only on-line time, on-line time is the most late, and its recommendation is the least, it is possible to less with the point of interest dependency of user, does not recommends or be positioned at can recommend after video content queue as far as possible.
In the present embodiment, the type obtaining the new video content that will show and the on-line time of the dissimilar new video content that will show, described on-line time is the on-line time of user location.
S503, according to the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
In the present embodiment, by being analyzed obtaining conversion ratio to history viewing record, estimate the point of interest of user；From the point of interest of user, estimate with user interest point matching degree by new video content is carried out again, generating one can recommendation, can will can give the user that this type of video with higher conversion is corresponding by the biggest new video commending contents of recommendation, when specifically recommending, can sort according to the size of recommendation, it is recommended that what value was the biggest shows the highest with the interest points matching degree of user.
In the present embodiment, can the calculating of recommendation can judge according to the on-line time of video content, on-line time is the most late, can recommendation less, the most then can recommend bigger.
Fig. 6 is the recommendation method flow schematic diagram of the embodiment of the present invention six video content；As shown in Figure 6, comprising:
S601, the type determining video content in described history viewing record and the conversion ratio of dissimilar video content；
Step S601 is same as the previously described embodiments, does not repeats them here.
S602, obtain the type of new video content that will show and the on-line time of the dissimilar new video content that will show and put on show the time；
In the present embodiment, the type of the new video content that described acquisition will be shown and the on-line time of dissimilar new video content and the time of putting on show that will show include: the type obtaining the new video content that will show and the on-line time of the dissimilar new video content that will show and put on show the time, described on-line time is included in the on-site on-line time of user, described in the time of putting on show be included in the whole world put on show the time.
S603, determine the described dissimilar new video content that will show according to the on-line time of dissimilar new video content that will show and the time of putting on show can recommendation；
In the present embodiment, have again the video content of time requirement of putting on show for the requirement of existing on-line time for, such as film, for the user in particular country or area, on-line time is there is in the publishing point such as web-site of video content or the server site of the 3rd application program, meanwhile, this film has the most again one to put on show the time.Specifically, can by the weighted calculation of the two time is obtained a fractional value, by this fractional value generate can recommendation, or directly using this fractional value as can recommendation.
S604, according to the type of video content and the conversion ratio of dissimilar video content in described history viewing record, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
Step S604 is same as the previously described embodiments, does not repeats them here.
Fig. 7 is the recommendation apparatus structural representation of the embodiment of the present invention seven video content；As it is shown in fig. 7, comprising:
Conversion ratio determines that unit 701 is for determining type and the conversion ratio of dissimilar video content of video content in described history viewing record；
Can recommendation computing unit 702 can recommendation for obtain the type of the new video content that will show calculating and the dissimilar new video content that will show；
The type of recommendation unit 703 video content in recording according to the viewing of described history and the conversion ratio of dissimilar video content, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
In the present embodiment, described conversion ratio determines that unit 701 is further used for the history viewing record obtaining in predetermined amount of time, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record.
In the present embodiment, described conversion ratio determines that unit 701 is further used for obtaining the history viewing record of predetermined quantity size, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record.
In the present embodiment, described conversion ratio determines that unit 701 is further used for determining the type of video content in described history viewing record and the hits of dissimilar video content and exposure frequency；And determine the conversion ratio of dissimilar video content in described history viewing record according to hits and the exposure frequency of video content in described history viewing record.
In the present embodiment, described conversion ratio determine unit 701 be further used for determining the type of video content in described history viewing record and the hits of dissimilar video content and and the video content number of times by user's ken, described exposure frequency includes that video content passes through the number of times of user's ken.
In the present embodiment, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show by recommendation computing unit 702, according to described on-line time generate described can recommendation.Specifically, in the present embodiment, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show by recommendation computing unit 702, described on-line time is the on-line time of user location.
Or, in the present embodiment, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show and putting on show the time by recommendation computing unit 702；And according to the on-line time of the dissimilar new video content that will show and the time of putting on show determine the described dissimilar new video content that will show can recommendation.Specifically, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show and putting on show the time by recommendation computing unit 702, described on-line time is included in the on-site on-line time of user, described in the time of putting on show be included in the whole world put on show the time.
Fig. 8 is the recommendation apparatus structural representation of the embodiment of the present invention eight video content；As shown in Figure 8, comprising:
Conversion ratio determines that unit 801 is for determining type and the conversion ratio of dissimilar video content of video content in described history viewing record；
Can recommendation computing unit 802 can recommendation for obtain the type of the new video content that will show calculating and the dissimilar new video content that will show；
The type of recommendation unit 803 video content in recording according to the viewing of described history and the conversion ratio of dissimilar video content, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show.
In the present embodiment, also include: history viewing record acquiring unit 804, for obtaining the history viewing record in predetermined amount of time, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record；Or, obtain the history viewing record of predetermined quantity size, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record.
In the present embodiment, described conversion ratio determines that unit 801 includes:
Click/exposure frequency obtains subelement 811, is used for determining the type of video content in described history viewing record and the hits of dissimilar video content and exposure frequency；
Conversion ratio determines subelement 821, for determining the conversion ratio of dissimilar video content in described history viewing record according to hits and the exposure frequency of video content in described history viewing record.
In the present embodiment, described click/exposure frequency obtain subelement 811 be further used for determining the type of video content in described history viewing record and the hits of dissimilar video content and and the video content number of times by user's ken, described exposure frequency includes that video content passes through the number of times of user's ken.
In the present embodiment, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show by recommendation computing unit 802, according to described on-line time generate described can recommendation.Specifically, in the present embodiment, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show by recommendation computing unit 802, described on-line time is the on-line time of user location.
Or, in the present embodiment, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show and putting on show the time by recommendation computing unit 801；And according to the on-line time of the dissimilar new video content that will show and the time of putting on show determine the described dissimilar new video content that will show can recommendation.Specifically, described can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show and putting on show the time by recommendation computing unit 801, described on-line time is included in the on-site on-line time of user, described in the time of putting on show be included in the whole world put on show the time.
Fig. 9 is the structural representation of the embodiment of the present invention nine video recommendations server；As shown in Figure 9, comprising: memorizer 901 and processor 902, processor 902 is for determining type and the conversion ratio of dissimilar video content of video content in described history viewing record, and obtain the type of the new video content that will show calculating and the dissimilar new video content that will show can recommendation；And for watching type and the conversion ratio of dissimilar video content of video content in record according to described history, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show；Described memorizer 901 for storing type and the conversion ratio of dissimilar video content of video content in described history viewing record, described history viewing record, and the type of the new video content that will show and correspondence can recommendation.
Figure 10 is the structural representation of the embodiment of the present invention ten video recommendation system；As shown in Figure 10, it includes video recommendations server 900 and video playing terminal 100, video recommendations server 900 includes memorizer 901 and processor 902, processor 902 is for determining type and the conversion ratio of dissimilar video content of video content in described history viewing record, and obtain the type of the new video content that will show calculating and the dissimilar new video content that will show can recommendation；And for watching type and the conversion ratio of dissimilar video content of video content in record according to described history, and the type of the new video content that will show and correspondence can recommendation, select to recommend video content from the new video content that will show；Described memorizer for storing the type of video content and the conversion ratio of dissimilar video content in described history viewing record, described history viewing record, and the type of the new video content that will show and correspondence can recommendation.
Video playing terminal 100 can with PC, can also be intelligent terminal, intelligent terminal includes that smart mobile phone, intelligent television, panel computer etc. possess browser and log in the electronic equipment of video website website, or can install any electronic equipment of third party's video plug-in unit.
In the embodiment of Fig. 9 and Figure 10, it is also possible to:
Described processor can be further used for the history viewing record obtaining in predetermined amount of time, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record.
Described processor can determine that unit is further used for obtaining the history viewing record of predetermined quantity size by described conversion ratio, to determine type and the conversion ratio of dissimilar video content of video content in described history viewing record.
Described processor can be further used for determining the type of video content in described history viewing record and the hits of dissimilar video content and exposure frequency；And determine the conversion ratio of dissimilar video content in described history viewing record according to hits and the exposure frequency of video content in described history viewing record.
Described processor can be further used for determining the type of video content in described history viewing record and the hits of dissimilar video content and and the video content number of times by user's ken, described exposure frequency includes that video content passes through the number of times of user's ken.
Described processor can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show, according to described on-line time generate described can recommendation.
Described processor can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show, and described on-line time is the on-line time of user location.
Described processor can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show and putting on show the time；And according to the on-line time of the dissimilar new video content that will show and the time of putting on show determine the described dissimilar new video content that will show can recommendation.
Described processor can be further used for obtaining the type of new video content that will show and the on-line time of the dissimilar new video content that will show and putting on show the time, described on-line time is included in the on-site on-line time of user, described in the time of putting on show be included in the whole world put on show the time.
Device embodiment described above is only schematically, the wherein said unit illustrated as separating component can be or may not be physically separate, the parts shown as unit can be or may not be physical location, i.e. may be located at a place, or can also be distributed on multiple NE.Some or all of module therein can be selected according to the actual needs to realize the purpose of the present embodiment scheme.Those of ordinary skill in the art, in the case of not paying performing creative labour, are i.e. appreciated that and implement.
Through the above description of the embodiments, those skilled in the art is it can be understood that can add the mode of required general hardware platform by software to each embodiment and realize, naturally it is also possible to pass through hardware.Based on such understanding, the part that prior art is contributed by technique scheme the most in other words can embody with the form of software product, this computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that a computer equipment (can be personal computer, video recommendations server, or the network equipment etc.) perform the method described in some part of each embodiment or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, it is not intended to limit；Although the present invention being described in detail with reference to previous embodiment, it will be understood by those within the art that: the technical scheme described in foregoing embodiments still can be modified by it, or wherein portion of techniques feature is carried out equivalent；And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (22)
1. the recommendation method of a video content, it is characterised in that including:
Determine type and the conversion of dissimilar video content of video content in described history viewing record
Rate；
The type of the new video content that acquisition will be shown calculating and the dissimilar new video that will show
Content can recommendation；
Type and the conversion of dissimilar video content of video content in record is watched according to described history
Rate, and the type of the new video content that will show and correspondence can recommendation, new from will show
Video content selects to recommend video content.
Recommendation method the most according to claim 1, it is characterised in that described determine the described conception of history
Also include before seeing the type of video content in record and the conversion ratio of dissimilar video content: obtain pre-
In the section of fixing time history viewing record, with determine described history viewing record in video content type and
The conversion ratio of dissimilar video content.
Recommendation method the most according to claim 1, it is characterised in that described determine the described conception of history
Also include before seeing the type of video content in record and the conversion ratio of dissimilar video content: obtain pre-
Determined number size history viewing record, with determine described history viewing record in video content type and
The conversion ratio of dissimilar video content.
Recommendation method the most according to claim 1, it is characterised in that determine described history viewing note
In record, the type of video content and the conversion ratio of dissimilar video content include:
Determine type and the click of dissimilar video content of video content in described history viewing record
Number and exposure frequency；
Described history is determined according to hits and the exposure frequency of video content in described history viewing record
The conversion ratio of dissimilar video content in viewing record.
Recommendation method the most according to claim 4, it is characterised in that described determine the described conception of history
See the type of video content in record and the hits of dissimilar video content and exposure frequency bag
Include:
Determine type and the click of dissimilar video content of video content in described history viewing record
Number and and video content by the number of times of user's ken, described exposure frequency includes that video content passes through
The number of times of user's ken.
Recommendation method the most according to claim 1, it is characterised in that described acquisition will be shown
The type of new video content and calculate and the dissimilar new video content that will show can recommendation bag
Include:
The type of the new video content that acquisition will be shown and the dissimilar new video content that will show
On-line time, according to described on-line time generate described can recommendation.
Recommendation method the most according to claim 6, it is characterised in that described acquisition will be shown
The type of new video content and the on-line time of dissimilar new video content that will show include:
The type of the new video content that acquisition will be shown and the dissimilar new video content that will show
On-line time, described on-line time is the on-line time of user location.
Recommendation method the most according to claim 1, it is characterised in that described acquisition will be shown
The type of new video content and calculate and the dissimilar new video content that will show can recommendation bag
Include:
The type of the new video content that acquisition will be shown and the dissimilar new video content that will show
On-line time and putting on show the time；
On-line time and the time of putting on show according to the dissimilar new video content that will show determine described
The dissimilar new video content that will show can recommendation.
Recommendation method the most according to claim 8, it is characterised in that described acquisition will be shown
The type of new video content and the on-line time of dissimilar new video content that will show and when putting on show
Between include: obtain in the type of new video content that will show and the dissimilar new video that will show
Hold on-line time and put on show the time, described on-line time is included in the on-site on-line time of user,
The described time of putting on show is included in putting on show the time of the whole world.
10. the recommendation apparatus of a video content, it is characterised in that including:
Conversion ratio determines unit, for determining type and the difference of video content in described history viewing record
The conversion ratio of type video content；
Can recommendation computing unit, for obtaining the type of new video content that will show and calculating and be
By the dissimilar new video content shown can recommendation；
Recommendation unit, for according to the type of video content in described history viewing record and dissimilar regard
Frequently the conversion ratio of content, and the type of the new video content that will show and correspondence can recommendation, from
The new video content that will show selects can recommend video content.
11. devices according to claim 10, it is characterised in that described conversion ratio determines that unit enters
One step, for obtaining the history viewing record in predetermined amount of time, regards to determine in described history viewing record
Frequently the type of content and the conversion ratio of dissimilar video content.
12. devices according to claim 10, it is characterised in that described conversion ratio determines that unit enters
One step, for obtaining the history viewing record of predetermined quantity size, regards to determine in described history viewing record
Frequently the type of content and the conversion ratio of dissimilar video content.
13. devices according to claim 10, it is characterised in that described conversion ratio determines that unit enters
One step is for determining the type of video content in described history viewing record and dissimilar video content
Hits and exposure frequency；And according to described history viewing record in video content hits and
Exposure frequency determines the conversion ratio of dissimilar video content in described history viewing record.
14. devices according to claim 13, it is characterised in that described conversion ratio determines that unit enters
One step is for determining the type of video content in described history viewing record and dissimilar video content
Hits and and video content by the number of times of user's ken, described exposure frequency includes video content
Number of times by user's ken.
15. devices according to claim 10, it is characterised in that described can recommendation computing unit
It is further used for the type obtaining the new video content that will show and the dissimilar new video that will show
The on-line time of content, according to described on-line time generate described can recommendation.
16. devices according to claim 10, it is characterised in that described can recommendation computing unit
It is further used for the type obtaining the new video content that will show and the dissimilar new video that will show
The on-line time of content, described on-line time is the on-line time of user location.
17. devices according to claim 10, it is characterised in that described can recommendation computing unit
It is further used for the type obtaining the new video content that will show and the dissimilar new video that will show
The on-line time of content and putting on show the time；And according to the dissimilar new video content that will show
On-line time and the time of putting on show determine recommending of the described dissimilar new video content that will show
Value.
18. devices according to claim 17, it is characterised in that described can recommendation computing unit
It is further used for the type obtaining the new video content that will show and the dissimilar new video that will show
The on-line time of content and putting on show the time, described on-line time is included in the on-site on-line time of user,
The described time of putting on show is included in putting on show the time of the whole world.
19. devices according to claim 10, it is characterised in that also include: history viewing record
Acquiring unit, for obtaining the history viewing record in predetermined amount of time, to determine described history viewing note
The type of video content and the conversion ratio of dissimilar video content in record；Or, obtain predetermined quantity big
Little history viewing record, to determine the type of video content in described history viewing record and dissimilar
The conversion ratio of video content.
20. devices according to claim 10, it is characterised in that described conversion ratio determines unit bag
Include:
Click/exposure frequency obtains subelement, for determining the class of video content in described history viewing record
Type and the hits of dissimilar video content and exposure frequency；
Conversion ratio determines subelement, for according to described history viewing record in video content hits with
And exposure frequency determines the conversion ratio of dissimilar video content in described history viewing record.
21. 1 kinds of video recommendations servers, it is characterised in that include memorizer and processor, process
Device is for determining type and the conversion of dissimilar video content of video content in described history viewing record
Rate, the type of the new video content that acquisition will be shown calculating and the dissimilar new video that will show
Content can recommendation；And for watching type and the difference of video content in record according to described history
The conversion ratio of type video content, and the type of new video content that will show and recommending of correspondence
Value, selects to recommend video content from the new video content that will show；Described memorizer is used for storing
Described history viewing record, described history are watched in type and the dissimilar video of video content in record
The conversion ratio held, and the type of the new video content that will show and correspondence can recommendation.
22. 1 kinds of video recommendation system, it is characterised in that include that video recommendations server and video are broadcast
Putting terminal, video recommendations server includes memorizer and processor, and processor is used for determining described history
Watching type and the conversion ratio of dissimilar video content of video content in record, acquisition will be shown
The type of new video content and calculate and the dissimilar new video content that will show can recommendation；With
And for watching type and the conversion of dissimilar video content of video content in record according to described history
Rate, and the type of the new video content that will show and correspondence can recommendation, new from will show
Video content selects to recommend video content；Described memorizer be used for storing described history viewing record,
Described history watches type and the conversion ratio of dissimilar video content of video content in record, and is
By the type of new video content shown and correspondence can recommendation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510940029.2A CN105915956A (en) | 2015-12-15 | 2015-12-15 | Video content recommendation method, device, server and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510940029.2A CN105915956A (en) | 2015-12-15 | 2015-12-15 | Video content recommendation method, device, server and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105915956A true CN105915956A (en) | 2016-08-31 |
Family
ID=56744284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510940029.2A Pending CN105915956A (en) | 2015-12-15 | 2015-12-15 | Video content recommendation method, device, server and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105915956A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106488267A (en) * | 2016-11-21 | 2017-03-08 | 武汉斗鱼网络科技有限公司 | A kind of appraisal procedure of direct broadcasting room Generalization bounds, user equipment server system |
| CN106604044A (en) * | 2016-11-21 | 2017-04-26 | 武汉斗鱼网络科技有限公司 | Direct broadcast room recommendation strategy assessment method, user equipment, and server system |
| CN106897398A (en) * | 2017-02-08 | 2017-06-27 | 北京奇艺世纪科技有限公司 | A kind of video display method and device |
| CN107197333A (en) * | 2017-05-05 | 2017-09-22 | 中广热点云科技有限公司 | A kind of method according to watching record of user recommendation video |
| CN108228795A (en) * | 2017-12-29 | 2018-06-29 | 北京奇虎科技有限公司 | Add the method and device of business object |
| CN108304429A (en) * | 2017-05-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information recommendation method, device and computer equipment |
| CN108875022A (en) * | 2018-06-20 | 2018-11-23 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and device |
| CN108900876A (en) * | 2018-06-22 | 2018-11-27 | 上海合志信息技术有限公司 | A kind of mobile video content miniaturation method and its system |
| CN109040795A (en) * | 2018-07-31 | 2018-12-18 | 上海斐讯数据通信技术有限公司 | A kind of video recommendation method and system |
| CN109120955A (en) * | 2018-09-30 | 2019-01-01 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of direct broadcasting room |
| CN111754253A (en) * | 2019-06-20 | 2020-10-09 | 北京沃东天骏信息技术有限公司 | User authentication method, device, computer equipment and storage medium |
| CN112042205A (en) * | 2018-10-15 | 2020-12-04 | 海信视像科技股份有限公司 | Information processing system and information processing apparatus |
| CN112612921A (en) * | 2020-12-31 | 2021-04-06 | 湖南快乐阳光互动娱乐传媒有限公司 | Video label determination method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101047831A (en) * | 2006-03-30 | 2007-10-03 | 株式会社东芝 | Recommendation program information method and device |
| CN101127624A (en) * | 2007-09-27 | 2008-02-20 | 腾讯科技（深圳）有限公司 | Demonstration method and system for advertisement server, advertisement originality |
| US20120054679A1 (en) * | 2010-08-31 | 2012-03-01 | Apple Inc. | Menuing Structure for Favorite Media Content |
| CN102999498A (en) * | 2011-09-08 | 2013-03-27 | 中兴通讯股份有限公司 | Method and device for searching multi-media programs |
| CN103237264A (en) * | 2013-04-12 | 2013-08-07 | 深圳创维－Rgb电子有限公司 | Network video playing method and network video playing device |
| CN104168510A (en) * | 2014-05-14 | 2014-11-26 | 录可系统公司 | Preference program dynamic recommendation method and system |
| US20150256892A1 (en) * | 2003-12-02 | 2015-09-10 | Sony Corporation | Information processor, information processing method and computer program |
-
2015
- 2015-12-15 CN CN201510940029.2A patent/CN105915956A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150256892A1 (en) * | 2003-12-02 | 2015-09-10 | Sony Corporation | Information processor, information processing method and computer program |
| CN101047831A (en) * | 2006-03-30 | 2007-10-03 | 株式会社东芝 | Recommendation program information method and device |
| CN101127624A (en) * | 2007-09-27 | 2008-02-20 | 腾讯科技（深圳）有限公司 | Demonstration method and system for advertisement server, advertisement originality |
| US20120054679A1 (en) * | 2010-08-31 | 2012-03-01 | Apple Inc. | Menuing Structure for Favorite Media Content |
| CN102999498A (en) * | 2011-09-08 | 2013-03-27 | 中兴通讯股份有限公司 | Method and device for searching multi-media programs |
| CN103237264A (en) * | 2013-04-12 | 2013-08-07 | 深圳创维－Rgb电子有限公司 | Network video playing method and network video playing device |
| CN104168510A (en) * | 2014-05-14 | 2014-11-26 | 录可系统公司 | Preference program dynamic recommendation method and system |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604044A (en) * | 2016-11-21 | 2017-04-26 | 武汉斗鱼网络科技有限公司 | Direct broadcast room recommendation strategy assessment method, user equipment, and server system |
| CN106488267A (en) * | 2016-11-21 | 2017-03-08 | 武汉斗鱼网络科技有限公司 | A kind of appraisal procedure of direct broadcasting room Generalization bounds, user equipment server system |
| CN106897398A (en) * | 2017-02-08 | 2017-06-27 | 北京奇艺世纪科技有限公司 | A kind of video display method and device |
| CN106897398B (en) * | 2017-02-08 | 2020-07-10 | 北京奇艺世纪科技有限公司 | Video display method and device |
| CN107197333B (en) * | 2017-05-05 | 2019-07-12 | 中广热点云科技有限公司 | A method of video is recommended according to watching record of user |
| CN107197333A (en) * | 2017-05-05 | 2017-09-22 | 中广热点云科技有限公司 | A kind of method according to watching record of user recommendation video |
| CN108304429A (en) * | 2017-05-16 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information recommendation method, device and computer equipment |
| CN108304429B (en) * | 2017-05-16 | 2021-12-14 | 腾讯科技（深圳）有限公司 | Information recommendation method and device and computer equipment |
| CN108228795A (en) * | 2017-12-29 | 2018-06-29 | 北京奇虎科技有限公司 | Add the method and device of business object |
| CN108875022A (en) * | 2018-06-20 | 2018-11-23 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method and device |
| CN108900876B (en) * | 2018-06-22 | 2021-05-28 | 上海合志信息技术有限公司 | Mobile video content granulation method and system thereof |
| CN108900876A (en) * | 2018-06-22 | 2018-11-27 | 上海合志信息技术有限公司 | A kind of mobile video content miniaturation method and its system |
| CN109040795A (en) * | 2018-07-31 | 2018-12-18 | 上海斐讯数据通信技术有限公司 | A kind of video recommendation method and system |
| CN109040795B (en) * | 2018-07-31 | 2023-12-19 | 周向红 | Video recommendation method and system |
| CN109120955A (en) * | 2018-09-30 | 2019-01-01 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of direct broadcasting room |
| CN109120955B (en) * | 2018-09-30 | 2020-12-15 | 武汉斗鱼网络科技有限公司 | Recommendation method for live broadcast room and related equipment |
| CN112042205A (en) * | 2018-10-15 | 2020-12-04 | 海信视像科技股份有限公司 | Information processing system and information processing apparatus |
| CN112042205B (en) * | 2018-10-15 | 2022-02-08 | 海信视像科技股份有限公司 | Information processing system and information processing apparatus |
| CN111754253A (en) * | 2019-06-20 | 2020-10-09 | 北京沃东天骏信息技术有限公司 | User authentication method, device, computer equipment and storage medium |
| CN112612921A (en) * | 2020-12-31 | 2021-04-06 | 湖南快乐阳光互动娱乐传媒有限公司 | Video label determination method and device |
| CN112612921B (en) * | 2020-12-31 | 2022-02-22 | 湖南快乐阳光互动娱乐传媒有限公司 | Video label determination method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105915956A (en) | Video content recommendation method, device, server and system | |
| US11880398B2 (en) | Method of presenting excluded keyword categories in keyword suggestions | |
| CN107888950B (en) | A kind of method and system for recommending video | |
| CN109819284B (en) | Short video recommendation method and device, computer equipment and storage medium | |
| US10402479B2 (en) | Method, server, browser, and system for recommending text information | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN109033149B (en) | Information recommendation method and device, server and storage medium | |
| US20160241894A1 (en) | Recommending media items based on take rate signals | |
| US8893012B1 (en) | Visual indicator based on relative rating of content item | |
| CN109753601B (en) | Method and device for determining click rate of recommended information and electronic equipment | |
| US8898150B1 (en) | Collecting image search event information | |
| JP6646931B2 (en) | Method and apparatus for providing recommendation information | |
| CN106331778A (en) | Video recommendation method and device | |
| WO2014194689A1 (en) | Method, server, browser, and system for recommending text information | |
| CN104537115A (en) | Method and device for exploring user interests | |
| CN104469508A (en) | Method, server and system for performing video positioning based on bullet screen information content | |
| CN109168047B (en) | Video recommendation method and device, server and storage medium | |
| CN103221955A (en) | Content recommending method, system and apparatus | |
| CN105550277A (en) | Intelligent movie ranking and evaluation system based on tag popularity | |
| CN111344696B (en) | System and method for evaluating advertisements | |
| CN105897847A (en) | Information push method and device | |
| CN106354867A (en) | Multimedia resource recommendation method and device | |
| CN103780625A (en) | Method and device for discovering interest of users | |
| CN110264283B (en) | Popularization resource display method and device | |
| US20130080437A1 (en) | System and method for providing statistics for user submissions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160831 |