CN103686237B - Recommend the method and system of video resource - Google Patents
Recommend the method and system of video resource Download PDFInfo
- Publication number
- CN103686237B CN103686237B CN201310578787.5A CN201310578787A CN103686237B CN 103686237 B CN103686237 B CN 103686237B CN 201310578787 A CN201310578787 A CN 201310578787A CN 103686237 B CN103686237 B CN 103686237B
- Authority
- CN
- China
- Prior art keywords
- user
- group
- video
- types
- dimensions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000000694 effects Effects 0.000 abstract description 2
- 230000009471 action Effects 0.000 description 20
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses recommending the method and system of video resource, including：Collect the historical record during each user watches video；The historical record of each user collecting is counted, the quantity of all types of videos according to each user viewing calculates it and watches the quantity accounting of all types of videos, generate the corresponding user's group including typical user of each particular video frequency type；Obtain data characteristicses in other dimensions for the typical user in each certain types of user's group respectively, determine stack features in other dimensions for each certain types of user；Judge other users outside the typical user data characteristicses in other dimensions, if meet the stack features of certain particular type group, if it is, this user is added this certain types of user's group；Particular type of information according to corresponding to each user's group, recommends corresponding video resource to the user in user's group.By the present invention, can targetedly carry out commending contents in user's viewing video, improve recommendation effect.
Description
Technical field
The present invention relates to ntelligent television technolog field, more particularly to recommend the method and system of video resource.
Background technology
Large area with mobile phone and panel computer is intelligent, and intelligent television is also just stepping into our life.Intelligence
TV, as smart mobile phone, has full open model platform, is equipped with operating system, voluntarily can be installed and uninstalled soft by user
The programs such as part, game, this class method is probably that intelligent television manufacturer provides it is also possible to the third party service provider provides,
Constantly the function of intelligent television can be expanded by this class method.Furthermore it is also possible to by netting twine, wireless network Lai real
Now surf the web.That is, real intelligent television can obtain programme content from multiple channels such as network, AV equipment, PC, by letter
Single easy-to-use integrated operation interface, the content that consumer needs most can clearly be represented on giant-screen by ease of Use.
At present, user obtains general only two kinds of the mode of resource from intelligent television.A kind of is mode the most traditional, namely
User oneself passes through the various access entrances providing in interface of intelligent television, carries out clicking on viewing after actively selecting information source.
For example, user can select to watch the section in traditional TV signal source, or the carousel channel of intelligent television server offer
Mesh, etc..Another kind is that server pushes some recommendation informations to user, such as by nearest popular video push to user,
User carries out passive reception.
So that user can obtain more rich letter by intelligent television by way of pushing some videos to user
Breath.But, prior art, when carrying out the push of video information, primary concern is that the information such as the popular degree of video, pushes
After user, most users to it and may be lost interest in, and then is ignored by user, waste and spent by push process be
System and Internet resources.
Therefore, the technical problem solving in the urgent need to those skilled in the art is that, to user's pushing video information
During, how so that the effectiveness recommended is improved.
Content of the invention
For defect present in prior art, the present invention provides a kind of method and system recommending video resource.
A kind of method recommending video resource, including：
Collect the historical record during each user watches video；Described historical record includes each video class watched
Data in type, and other dimensions at least one；
The historical record of each user collecting is counted, the quantity of all types of videos according to each user viewing
Calculate it and watch the quantity accounting of all types of videos, and this user is included into the particular type video that quantity accounting is more than group threshold value
Corresponding user's group, this user is defined as typical user, generates the corresponding use including typical user of each particular video frequency type
Family group；
Obtain data characteristicses in other dimensions for the typical user in each certain types of user's group respectively, determine each specific
Stack features in other dimensions for the user of type；
Judge other users outside the typical user data characteristicses in other dimensions, if meet certain certain types of use
The stack features of family group, if it is, this user is added this certain types of user's group；
Particular type of information according to corresponding to each user's group, recommends corresponding video resource to the user in user's group.
Alternatively：Data in described other dimensions at least one includes, the viewing duration of user's all types of videos of viewing,
The time period distribution of user's viewing video, the number of times that user watches the number of times of same video, user scans for and search content,
User's number of clicks to the message recommending class using the number of times applied and user.
Alternatively：The described historical record collected during each user watches video includes：When user's viewing video
When length is more than the first lower limit, record its historical record.
Alternatively：The described historical record collected during each user watches video is included, to the historical record collected
It is normalized, deleting duplicated data.
Alternatively：Second lower limit of the quantity accounting of all types of videos that described group of threshold value is watched for user.
Alternatively, also include：The quantity calculating calculating all types of videos that the other users outside typical user are watched is all kinds of
Whether the quantity accounting of type, judge this quantity accounting more than or equal to the corresponding group threshold value organized, if more than or equal to group threshold value, by it
Put this group under；If accounting is less than the group threshold value of each packet, obtain data characteristicses in other dimensions for this user.
Alternatively, also include：For historical record article number be more than the 3rd lower limit user carry out statistical packet, for point
User after group carries out statistical packet to this user after every record increasing certain bar number again.
Alternatively：The described user into user's group recommends corresponding video to include same video is carried out recommending across group.
A kind of system recommending video resource, including：
Historical record acquisition module, for collecting the historical record during each user watches video, described historical record
Including the data in each video type watched, and other dimensions at least one；
Typical user chooses division module, the historical record of each user collecting is counted, according to each user
The quantity of all types of videos of viewing calculates it and watches the quantity accounting of all types of videos, and it is big that this user is included into quantity accounting
In the user's group corresponding to the particular type video of group threshold value, this user is defined as typical user, generates each particular video frequency type
The corresponding user's group including typical user；
Model training module, for obtaining number in other dimensions for the typical user in each certain types of user's group respectively
According to feature, determine stack features in other dimensions for this group；
User grouping module, for judging data characteristicses in other dimensions for the other users outside typical user, if
Meet the stack features of certain certain types of user's group, if it is, this user is added this certain types of user's group；
Video recommendations module, for the particular type of information according to corresponding to each user's group, pushes away to the user in user's group
Recommend corresponding video resource.
Alternatively：Data in described other dimensions at least one includes, the viewing duration of user's all types of videos of viewing,
The time period distribution of user's viewing video, the number of times that user watches the number of times of same video, user scans for and search content,
User's number of clicks to the message recommending class using the number of times applied and user.
Compared with prior art, one of technique scheme technical scheme has advantages below or beneficial effect：
The historical data of video is watched it is possible to determine which kind of viewing classification type this user belongs to by counting user, leads to
Cross data distribution in different angles for the counting user data, can accurately realize the packet to user's generic,
So just targetedly can carry out commending contents in user's viewing video, improve recommendation effect.
Brief description
By reading the detailed description of hereafter preferred implementation, various other advantages and benefit are common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and is not considered as to the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical part.In the accompanying drawings：
Fig. 1 is the method flow diagram recommending video resource provided in an embodiment of the present invention；
Fig. 2 is the apparatus structure schematic diagram recommending video resource provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings, the present invention is expanded on further.It should be understood that these embodiments be merely to illustrate the present invention and not
For limiting the scope of the present invention.In addition, it is to be understood that after having read the content of present invention instruction, those skilled in the art
The present invention can be made various changes or modifications, these equivalent form of values equally fall within the application appended claims and limited
Scope.
The intelligent television system of the present invention includes client and server, and user can after client logs in particular account number
With the various video resources in access server, client can be to operate in the application program of Intelligent television terminal, by end
End equipment user can watch the video resource on server.Server preserves the viewing historical record of each account, by right
The analysis of viewing historical record recommends its video resource interested to different user.Below by specific embodiment to this
Bright it is described further.
Embodiment 1
As shown in figure 1, a kind of present invention firstly provides method recommending video resource.Video resource can be drawn by its type
It is divided into action movie, literary film, documentary film, animation piece etc., due to everyone viewing custom, personal happiness during video-see
Good difference, the quantity accounting that each user watches all types of videos is different, if can in the history viewing record of user
Significantly embody, user is significantly higher than other types to the viewing quantity accounting of certain type video, then can will be somebody's turn to do accordingly
User is divided in the user's group of the type.Such as user can be divided into action group, performing arts class, documentary film group, animation group etc..When
So, also have in the viewing record of some users and may embody certain directly in terms of the video type quantity accounting of viewing
How the significance of one type, now, determine the user's group belonging to these users, then become the problem needing to solve for emphasis.Under
Mask body introduces the process of user's division.
S101：Collect the historical record during each user watches video；What described historical record included watching respectively regards
Data in frequency type, and other dimensions at least one；
In order to be able to be divided to numerous users it is necessary first to be recorded the viewing historical record of user.When implementing,
After user signs in server using its account number, server can receive account information, judges the legitimacy of account information, when
The history note of each video type watched during the user corresponding to this account watches video is collected when account information is legal
Record.Wherein, when implementing, user can be by scanning Quick Response Code, and input ID, password, etc. mode game server.Close
In the viewing historical record of user, can be to be collected by client, then upload onto the server, so, server can
Record is watched with the history getting each client.Wherein, client can be in the way of using real-time upload, or using fixed
Phase uploads（For example, upload weekly once）, or quantitative upload（For example, often the data of record 10M uploads once）, etc..
Wherein, historical record can include user viewing all types of videos quantity, the viewing duration of all types of videos,
User watches the time period distribution of video；User watches the number of times of same video；The number of times that user scans for and search content
Type distribution；User is using the type distribution of the number of times applied and application；User to recommend class message number of clicks and
Ratio etc..
Server can watch the duration of video come judging whether to need to record this viewing behavior according to user, specifically
For can be：Server to be divided into unit record user's viewing time, when user certain video time of staying be less than threshold value when,
Such as 1 minute, then this time behavior is invalid, not records.So both reduced data record amount, the content of record is also more accurate.
After server receives each user's viewing historical record, data can be normalized first, delete weight
Complex data.Then just the accounting that user watches all types of videos can be calculated according to the historical record after having processed.For example, go through
There are 100 viewing records, the record that user watches action movie in this 100 viewing records is 70, viewing in Records of the Historian record
The record of literary film is 10 etc., then the accounting being calculated user's viewing action class video is 70%, the accounting of literature and art class video
For 10% etc..
S102：The historical record of each user collecting is counted, according to all types of videos of each user viewing
Quantity calculate its watch all types of videos quantity accounting, and by this user be included into quantity accounting be more than group threshold value certain kinds
User's group corresponding to type video, this user is defined as typical user, generates each particular video frequency type corresponding inclusion typical case and uses
The user's group at family；
In the user of history of existence record, some users have obvious characteristic of division, and such as certain user's viewing is dynamic
The ratio making class video is more than 60%, and the ratio that certain user watches literature and art class video is more than 70%, and certain user watches animation class
The ratio of video is more than 80% etc., then these users corresponding can be divided into action group, performing arts class, animation group etc..And other
User does not have obvious characteristic, and the historical record of such as some users is imperfect, wherein there may be the data of disappearance, for example,
The type of some videos is difficult to divide, then system just cannot obtain the record of the video type in current viewing historical record, or
In person's watching process, network interrupts leading to not situations such as obtain viewing duration etc., or some users viewing classification of type is failed to understand
Really, as all types of accountings in some users viewing is essentially identical, and the accounting of such as viewing action class is 30%, viewing literature and art class
Accounting is 31%, the accounting of viewing animation class is 28% etc., is difficult to recommend video to it for these users.
In order to solve this problem, the present invention chooses a part of user with obvious characteristic of division and carries out group division, really
Surely the quantity accounting of viewing particular type video is more than the typical user of group threshold value, prepares for model training hereafter.For example
Choose 1000 users, the accounting that this 1000 users watch corresponding types videos is all higher than corresponding group of threshold value, such as 1000
The accounting belonging to user's viewing action class video of action group in individual user is more than 60%, belongs to user's viewing literary composition of literature and art class group
The accounting of skill class video is more than 65% etc..This user is referred to as typical user, 60%, 65% referred to as organizes threshold value, the groups of different groups here
Threshold value both can be the same or different, and its group threshold value can dynamically adjust.
S103：Obtain data characteristicses in other dimensions for the typical user in each certain types of user's group respectively, determine
Stack features in other dimensions for each certain types of user；
After completing typical user is grouped, carry out model training, obtain corresponding packet Nei Ge typical user and tie up at other
Data characteristicses on degree.Taking action class as a example it is described below, the user belonging to action group in such as 1000 users is
100 people, the accounting of this 100 people viewing action class video is all higher than 60%, except viewing video type accounting is more than 60% this number
According to being characterized as, also there are the data characteristicses in some other dimensions in this group, and such as such user is more than 60 minutes the average viewing time,
And the viewing period often see at night, to recommend class message click on ratio averagely be more than 70%, the average viewing of user in this embodiment
Time, viewing period, the message of recommendation class are clicked on ratio and are referred to as the data in other dimensions.
The user belonging to performing arts class for another example in 1000 users is 200 people, and this 200 people watches the accounting of literature and art class video
It is all higher than 65%, except viewing video type accounting is that this group also exists in some other dimensions more than 65% this data characteristics
Data characteristicses, such as user watches the number of times of same video more than 10 times, searches often at noon such user's viewing period
In the type distribution of rope content, literature and art class accounting is more than 40% etc., and user's viewing period, user watch same video in this embodiment
Number of times, the type distribution of search content are referred to as the data in other dimensions.
Data characteristicses in other dimensions for each group user, those skilled in the art can be obtained by this model training
It should be understood that in the history viewing record collected, any data different from the accounting watching each video type, all can claim
The content being comprised for the data in other dimensions, the data that the embodiment of the present invention is not intended to limit in other dimensions.
S104：Judge other users outside the typical user data characteristicses in other dimensions, if meet certain certain kinds
The stack features of type user's group, if it is, this user is added this certain types of user's group；
After obtaining the data characteristicses in other dimensions, can be with these data characteristicses to other use outside typical user
Family is grouped.Be equivalent to using the model training, user is classified.
Can be specifically to first determine whether whether watch the record of video type with regard to it in acquired historical record
Completely, if record is complete, it is calculated with it and watches the accounting of each video type, judge this accounting whether more than corresponding group
Group threshold value, if more than group threshold value, put under this group.Watching the record of video type with regard to it in judging historical record is
When no complete, a lower limit can be set, the user being more than lower limit for missing data is just carried out in other dimensions further
Judgement, the judgement that for example user more than 10% is just carried out in other dimensions further for disappearance record, this lower limit
Value can dynamically adjust.
If recording the group threshold value that imperfect or its accounting is less than each packet, the data obtaining in other dimensions of this user is special
Levy, judge whether it meets the data characteristicses in other dimensions counting by model training in certain particular type, meet then
It is divided into this group, if finding after judging to be not present in the corresponding packet of this user, that is, this user can not put any one class under
The group of type, then by non-for this user grouping grouping user.
For example for a certain user, there are 500 records in historical record, then system first determines whether this 500 historical record
In whether watch the record of video type with regard to it complete, if record is complete, it calculated with it watches each video type and account for
If there being 400 records being viewing action class in this 500 records, quantity accounting is 80% to ratio, and it is more than the group of action group
Threshold value 60%, then put under action group；If there being 100 records being viewing action class in this 500 records, or 500 go through
It is imperfect for watching the record of video type with regard to it in Records of the Historian record, then judge in described other dimensions of at least one of this user
Data whether meet in certain particular type and count described feature, such as judge user's average viewing time whether more than 60 points
To the message recommending class, clock, if often see at night, clicking on whether ratio is more than 70%, if meeting these conditions, this being used
Family puts action group under；If finding after judging to be not present in the corresponding packet of this user, that is, this user can not put any one class under
The group of type, then by this user grouping to non-grouping user.
It should be appreciated that the same user of the present invention can be grouped different groups, such as same user, in other dimensions
Data may meet the data characteristicses counting in multiple corresponding grouping models in other dimensions described, then by this user simultaneously
It is divided into this two groups simultaneously.
In the present invention, with the increase of user's viewing time, the information of its historical record is more and more abundanter, in order to more accurate
The true packet realized to user, system carries out statistical only for the historical record bar number of user more than the user of lower limit
Group, this lower limit can be for example 10.After packet, system can be again to user after every record increasing certain bar number
Carry out statistical packet, such as record strip number increases 10 newly afterwards, system can record again to original record and newly-increased this 10
Carry out statistical packet.
S105：Particular type of information according to corresponding to each user's group, recommends corresponding video to the user in user's group
Resource.
After the completion of user grouping, user is after account login system it is possible to enter historical record with user account
Row association, the viewing custom such as love of analysis user sees TV play, and love is seen a film, and TV play love sees domestic or American series, film
Love sees science fiction film, horror film or romance movie etc., according to the corresponding group information of each user, recommends certain types of regarding to user
Frequency resource.The a certain account of such as server record belongs to action group, then, after user is logged in by this account, system is from trend
Its recommendation action class video.Same video can carry out recommending across group, such as the video with action and comedy feature,
Then this video is recommended combination of actions comedy group simultaneously, preferably recommend the common factor user of two groups.
Video can be recommended to user in the way of using poster or message, poster picture can show when client is started shooting,
If for example client is TV, television startup picture shows the associated video recommended to user, picture comprises to link, and uses
Family click picture can be directly linked to associated video and be watched；Or pass through Pop-up message during user's viewing video
To recommend to user, in message, comprise video name, video address, thumbnail etc..
When user logs in not over account or user is that new registration user or user belong to non-grouping user group, then
System can recommend other videos of the type according to his currently watched video type to it, so facilitates user to watch
Similar video, or recommended at random.
Embodiment 2
As shown in Fig. 2 the present invention also provides a kind of system recommending video resource.System includes client and server,
User can be to operate in intelligence with the various video resources in access server, client after client logs in particular account number
The application program of television terminal, can watch the video resource on server by terminal user.Server is preserved respectively
The viewing historical record of account, by recommending its video resource interested to the analysis watching historical record to different user.
Historical record acquisition module 201, for collecting the historical record during each user watches video, described history note
Record includes each video type watched, and the data in other dimensions at least one；
Typical user chooses division module 202, the historical record of each user collecting is counted, according to each use
The quantity of all types of videos of family viewing calculates it and watches the quantity accounting of all types of videos, and this user is included into quantity accounting
More than the user's group corresponding to particular type video of group threshold value, this user is defined as typical user, generates each particular video frequency class
The corresponding user's group including typical user of type；
Model training module 203, for obtaining in each certain types of user's group typical user respectively in other dimensions
Data characteristicses, determine stack features in other dimensions for this group；
User grouping module 204, for judging data characteristicses in other dimensions for the other users outside typical user, be
The no stack features meeting certain particular type of user group, if it is, this user is added this certain types of user's group；
Video recommendations module 205, for the particular type of information according to corresponding to each user's group, to the user in user's group
Recommend corresponding video resource.
Wherein, the data in described other dimensions at least one includes, and user watches the viewing duration of all types of videos, use
The time period that video is watched at family is distributed, user watches the number of times of same video, user scans for number of times and search content, use
Family number of clicks to the message recommending class using the number of times applied and user.
When implementing, described historical record acquisition module specifically for：When the duration that user watches video is more than first
During lower limit, record its historical record.Second lower limit of the quantity accounting of all types of videos that described group of threshold value is watched for user
Value.
In order to reduce amount of calculation, this system can also include：
Normalized module, for being normalized to the historical record collected, deleting duplicated data.
First judge module, the quantity for calculating all types of videos of the viewing of the other users outside typical user calculates each
Whether the quantity accounting of type, judge this quantity accounting more than or equal to the corresponding group threshold value organized, if more than or equal to group threshold value, will
It puts this group under；If accounting is less than the group threshold value of each packet, trigger the described judgement of described user grouping module execution at other
The operation of the data characteristicses in dimension.
Again grouping module, the user for being more than the 3rd lower limit for historical record article number carries out statistical packet, right
Again statistical packet is carried out to this user in the user after packet after every record increasing certain bar number.
For aforesaid each device embodiment, in order to be briefly described, therefore it is all expressed as a series of block combiner, but
It is that those skilled in the art should know, the present invention is not limited by described block combiner, because according to the present invention,
Certain module can be using the execution of other modules；Secondly, those skilled in the art also should know, said apparatus embodiment all belongs to
In preferred embodiment, necessary to the involved module not necessarily present invention.
Each embodiment in this specification is all described by the way of going forward one by one, what each embodiment stressed be with
The difference of other embodiment, between each embodiment identical similar partly mutually referring to.For system embodiment
For, due to itself and embodiment of the method basic simlarity, so description is fairly simple, referring to the portion of embodiment of the method in place of correlation
Defend oneself bright.
Above to the method and system recommending video resource provided by the present invention, it is described in detail, herein should
With specific case, the principle of the present invention and embodiment are set forth, the explanation of above example is only intended to help reason
The solution method of the present invention and its core concept；Simultaneously for one of ordinary skill in the art, according to the thought of the present invention,
All will change in specific embodiment and range of application, in sum, this specification content should not be construed as to this
Bright restriction.
Claims (10)
1. a kind of method recommending video resource is it is characterised in that include：
Collect the historical record during each user watches video；Described historical record includes each video type watched, with
And the data at least one other dimensions；
The historical record of each user collecting is counted, the quantity of all types of videos according to each user viewing calculates
It watches the quantity accounting of all types of videos, and it is right more than the particular type video institute of group threshold value that this user is included into quantity accounting
The user's group answered, this user is defined as typical user, generates the corresponding user's group including typical user of each particular video frequency type；
Obtain data characteristicses in other dimensions for the typical user in each certain types of user's group respectively, determine each particular type
Stack features in other dimensions for the user；
Judge other users outside the typical user data characteristicses in other dimensions, if meet certain certain types of user's group
Stack features, if it is, this user is added this certain types of user's group；
Particular type of information according to corresponding to each user's group, recommends corresponding video resource to the user in user's group.
2. method according to claim 1 it is characterised in that：Data in described other dimensions at least one includes, and uses
The viewing duration of all types of videos is watched at family, user watches the time period distribution of video, user watches the number of times of same video, use
The number of times that family scans for and the number of clicks of search content, user's message to recommendation class using the number of times applied and user.
3. method according to claim 1 it is characterised in that：The described history note collected during each user watches video
Record includes：When the duration that user watches video is more than the first lower limit, record its historical record.
4. method according to claim 1 it is characterised in that：The described history note collected during each user watches video
Record includes, and the historical record collected is normalized, deleting duplicated data.
5. method according to claim 1 it is characterised in that：The number of all types of videos that described group of threshold value is watched for user
Second lower limit of amount accounting.
6. method according to claim 1 is it is characterised in that also include：Calculate the other users viewing outside typical user
The quantity of all types of videos calculate all types of quantity accountings, judge this quantity accounting whether more than or equal to the group threshold of corresponding group
Value, if more than or equal to group threshold value, put under this group；If accounting is less than the group threshold value of each packet, obtain this user at other
Data characteristicses in dimension.
7. method according to claim 1 is it is characterised in that also include：3rd lower limit is more than for historical record article number
The user of value carries out statistical packet, again this user is carried out after every record increasing certain bar number for the user after packet
Statistical packet.
8. method according to claim 1 it is characterised in that：The described user into user's group recommends corresponding video to include
Same video is carried out recommend across group.
9. a kind of system recommending video resource is it is characterised in that include：
Historical record acquisition module, for collecting the historical record during each user watches video, described historical record includes
Data in each video type watched, and other dimensions at least one；
Typical user chooses division module, and the historical record of each user collecting is counted, and is watched according to each user
All types of videos quantity calculate its watch all types of videos quantity accounting, and by this user be included into quantity accounting be more than group
The user's group corresponding to particular type video of threshold value, this user is defined as typical user, generates each particular video frequency type and corresponds to
Inclusion typical user user's group；
Model training module, special for obtaining data in other dimensions for the typical user in each certain types of user's group respectively
Levy, determine stack features in other dimensions for this group；
User grouping module, for judging data characteristicses in other dimensions for the other users outside typical user, if meets
The stack features of certain certain types of user's group, if it is, this user is added this certain types of user's group；
Video recommendations module, for the particular type of information according to corresponding to each user's group, it is right to recommend to the user in user's group
The video resource answered.
10. system according to claim 9 it is characterised in that：Data in described other dimensions at least one includes, and uses
The viewing duration of all types of videos is watched at family, user watches the time period distribution of video, user watches the number of times of same video, use
The number of times that family scans for and the number of clicks of search content, user's message to recommendation class using the number of times applied and user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310578787.5A CN103686237B (en) | 2013-11-19 | 2013-11-19 | Recommend the method and system of video resource |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310578787.5A CN103686237B (en) | 2013-11-19 | 2013-11-19 | Recommend the method and system of video resource |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103686237A CN103686237A (en) | 2014-03-26 |
| CN103686237B true CN103686237B (en) | 2017-03-08 |
Family
ID=50322315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310578787.5A Active CN103686237B (en) | 2013-11-19 | 2013-11-19 | Recommend the method and system of video resource |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103686237B (en) |
Families Citing this family (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104469430A (en) * | 2014-12-24 | 2015-03-25 | 武汉泰迪智慧科技有限公司 | Video recommending method and system based on context and group combination |
| CN104469432B (en) * | 2014-12-31 | 2017-12-05 | 合一网络技术(北京)有限公司 | A kind of audience ratings modification method and device based on user |
| CN106303591B (en) * | 2015-06-03 | 2019-05-28 | 中移(苏州)软件技术有限公司 | A kind of video recommendation method and device |
| US10268748B2 (en) * | 2015-06-07 | 2019-04-23 | Apple Inc. | Reader application with a personalized feed and method of providing recommendations while maintaining user privacy |
| CN104954877B (en) * | 2015-06-29 | 2019-02-12 | 深圳市微浦技术有限公司 | The data load method and system of set-top box |
| CN105163142B (en) * | 2015-09-09 | 2018-10-26 | 聚好看科技股份有限公司 | A kind of user preference determines method, video recommendation method and system |
| CN105516279B (en) * | 2015-11-30 | 2019-06-28 | 海信集团有限公司 | A kind of user account creation method and device |
| CN105426688B (en) * | 2015-12-07 | 2018-12-21 | 杭州聪宝科技有限公司 | Individualized video content push system based on user's tcm constitution data |
| CN105912544A (en) * | 2015-12-14 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Method and device for matching video content, server, and video playing system |
| CN105550334B (en) * | 2015-12-22 | 2019-01-22 | 海信集团有限公司 | A kind of video recommendation method and device |
| CN105898433B (en) * | 2016-05-27 | 2019-08-06 | 青岛海信电器股份有限公司 | TV programme suggesting method and device |
| CN106131632A (en) * | 2016-06-29 | 2016-11-16 | 乐视控股（北京）有限公司 | Opening video playing method, device and terminal |
| CN106231379A (en) * | 2016-07-29 | 2016-12-14 | 广州酷狗计算机科技有限公司 | A kind of methods, devices and systems playing live video |
| CN106604068B (en) * | 2016-12-30 | 2019-11-05 | 中广热点云科技有限公司 | A kind of method and its system of more new media program |
| CN107153907A (en) * | 2017-03-22 | 2017-09-12 | 华为技术有限公司 | The method and relevant apparatus of a kind of potential user for assessing video traffic |
| CN108304525B (en) * | 2018-01-25 | 2022-02-11 | 创新先进技术有限公司 | Condition data determination method and device |
| CN108614856B (en) * | 2018-03-21 | 2021-01-05 | 北京奇艺世纪科技有限公司 | Video sequencing calibration method and device |
| CN111125498B (en) * | 2018-10-30 | 2023-06-06 | 百度在线网络技术（北京）有限公司 | User attribute distinguishing method, device, equipment and computer readable medium |
| CN109769145A (en) * | 2018-11-28 | 2019-05-17 | 北京达佳互联信息技术有限公司 | Access control method, device, terminal and the storage medium of short-sighted frequency |
| CN109547814B (en) * | 2018-12-13 | 2021-07-16 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
| CN109934748A (en) * | 2019-03-25 | 2019-06-25 | 京工博创（北京）科技有限公司 | A kind of personalized course method for customizing based under the conditions of big data |
| CN110213660B (en) * | 2019-05-27 | 2021-08-20 | 广州荔支网络技术有限公司 | Program distribution method, system, computer device and storage medium |
| CN112417263B (en) * | 2019-08-23 | 2024-01-09 | 北京达佳互联信息技术有限公司 | Data recommendation method, device and storage medium |
| CN110784531A (en) * | 2019-10-24 | 2020-02-11 | 北京联卓信息技术有限公司 | Advertisement display method and system for mobile phone video software |
| CN110971973A (en) * | 2019-12-03 | 2020-04-07 | 北京奇艺世纪科技有限公司 | Video pushing method and device and electronic equipment |
| CN111028572A (en) * | 2019-12-31 | 2020-04-17 | 浙江正元智慧科技股份有限公司 | Online education platform |
| CN114598932A (en) * | 2020-12-04 | 2022-06-07 | 深圳Tcl新技术有限公司 | Program recommendation method, terminal and storage medium |
| CN113014938B (en) * | 2021-02-24 | 2022-06-14 | 北京金和网络股份有限公司 | Multi-dimensional live video recommendation method and device |
| CN113378020A (en) * | 2021-06-08 | 2021-09-10 | 深圳Tcl新技术有限公司 | Acquisition method, device and computer readable storage medium for similar film watching users |
| CN116233498B (en) * | 2023-03-09 | 2023-10-10 | 联通沃音乐文化有限公司 | Audio-video playing control method based on AI artificial intelligence |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1756336A (en) * | 2004-09-29 | 2006-04-05 | 松下电器产业株式会社 | Television channel commending system and commending method |
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
| CN102236669A (en) * | 2010-04-30 | 2011-11-09 | 腾讯科技（深圳）有限公司 | Recommendation list generation method, device, media server, client and method |
| CN102306178A (en) * | 2011-08-25 | 2012-01-04 | 盛乐信息技术（上海）有限公司 | Video recommendation method and device |
| CN102421025A (en) * | 2011-11-22 | 2012-04-18 | 康佳集团股份有限公司 | Television program guide method and system based on program content attributes |
| CN102843586A (en) * | 2011-06-21 | 2012-12-26 | 华为软件技术有限公司 | Video recommendation method and terminal |
| CN102946566A (en) * | 2012-10-24 | 2013-02-27 | 北京奇虎科技有限公司 | Video recommending method and device based on historical information |
| CN102968446A (en) * | 2012-10-24 | 2013-03-13 | 北京奇虎科技有限公司 | Video recommendation method and video recommendation device |
| CN103020161A (en) * | 2012-11-26 | 2013-04-03 | 北京奇虎科技有限公司 | On-line video recommending method recommending system, and processing system |
| US8418205B2 (en) * | 2008-11-18 | 2013-04-09 | Electronics And Telecommunications Research Institute | Method and apparatus for recommending personalized content |
| CN103167330A (en) * | 2011-12-15 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Method and system for audio/video recommendation |
-
2013
- 2013-11-19 CN CN201310578787.5A patent/CN103686237B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1756336A (en) * | 2004-09-29 | 2006-04-05 | 松下电器产业株式会社 | Television channel commending system and commending method |
| US8418205B2 (en) * | 2008-11-18 | 2013-04-09 | Electronics And Telecommunications Research Institute | Method and apparatus for recommending personalized content |
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
| CN102236669A (en) * | 2010-04-30 | 2011-11-09 | 腾讯科技（深圳）有限公司 | Recommendation list generation method, device, media server, client and method |
| CN102843586A (en) * | 2011-06-21 | 2012-12-26 | 华为软件技术有限公司 | Video recommendation method and terminal |
| CN102306178A (en) * | 2011-08-25 | 2012-01-04 | 盛乐信息技术（上海）有限公司 | Video recommendation method and device |
| CN102421025A (en) * | 2011-11-22 | 2012-04-18 | 康佳集团股份有限公司 | Television program guide method and system based on program content attributes |
| CN103167330A (en) * | 2011-12-15 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Method and system for audio/video recommendation |
| CN102946566A (en) * | 2012-10-24 | 2013-02-27 | 北京奇虎科技有限公司 | Video recommending method and device based on historical information |
| CN102968446A (en) * | 2012-10-24 | 2013-03-13 | 北京奇虎科技有限公司 | Video recommendation method and video recommendation device |
| CN103020161A (en) * | 2012-11-26 | 2013-04-03 | 北京奇虎科技有限公司 | On-line video recommending method recommending system, and processing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103686237A (en) | 2014-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103686237B (en) | Recommend the method and system of video resource | |
| CN103686375B (en) | Video sharing method and device | |
| CN103686396B (en) | Video sharing method and device | |
| CN104935970B (en) | Carry out the method and Television clients of television content recommendation | |
| CN103686236A (en) | Method and system for recommending video resource | |
| US20200012654A1 (en) | System and methods for generating optimal post times for social networking sites | |
| US11770569B2 (en) | Providing risk based subscriber enhancements | |
| CN103647800B (en) | Recommend the method and system of application resource | |
| CN105095480B (en) | To the real-time offer of the link of portion of media object in social networks update | |
| CN103377242B (en) | User behavior analysis method, analyzing and predicting method and television program push system | |
| US8151194B1 (en) | Visual presentation of video usage statistics | |
| US8843463B2 (en) | Providing content by using a social network | |
| CN107087235A (en) | Media content recommendations method, server and client | |
| DE202014011625U1 (en) | Apparatus and system for compensating impression data for misattribution and/or non-coverage by a database owner | |
| EP1971075A1 (en) | An information issuing system, a public media information issuing system and an issuing method | |
| US8386601B1 (en) | Detecting and reporting on consumption rate changes | |
| JP2007241982A (en) | Method and system for accurate issuance of data information | |
| US9009298B2 (en) | Methods and apparatus to determine audience engagement indices associated with media presentations | |
| CN103747343A (en) | Method and device for resource day parting recommendation | |
| CN101764661A (en) | Data fusion based video program recommendation system | |
| CN106604137B (en) | Method and device for predicting video watching duration | |
| CN103997662A (en) | Program pushing method and system | |
| CN114747227A (en) | Method, system, and apparatus for estimating census-level audience size and total impression duration across demographic groups | |
| CN105956061B (en) | Method and device for determining similarity between users | |
| CN106303591A (en) | A kind of video recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20170721 Granted publication date: 20170308 |
|
| PP01 | Preservation of patent right | ||
| PD01 | Discharge of preservation of patent | ||
| PD01 | Discharge of preservation of patent |
Date of cancellation: 20200721 Granted publication date: 20170308 |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 300453 Tianjin Binhai New Area, Tianjin Eco-city, No. 126 Animation and Animation Center Road, Area B1, Second Floor 201-427 Patentee after: Xinle Visual Intelligent Electronic Technology (Tianjin) Co.,Ltd. Address before: 300467 Tianjin Binhai New Area, ecological city, animation Middle Road, building, No. two, B1 District, 201-427 Patentee before: LE SHI ZHI XIN ELECTRONIC TECHNOLOGY (TIANJIN) Ltd. Address after: Room 301-1, Room 301-3, Area B2, Animation Building, No. 126 Animation Road, Zhongxin Eco-city, Tianjin Binhai New Area, Tianjin Patentee after: LE SHI ZHI XIN ELECTRONIC TECHNOLOGY (TIANJIN) Ltd. Address before: 300453 Tianjin Binhai New Area, Tianjin Eco-city, No. 126 Animation and Animation Center Road, Area B1, Second Floor 201-427 Patentee before: Xinle Visual Intelligent Electronic Technology (Tianjin) Co.,Ltd. |
|
| PP01 | Preservation of patent right | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20210201 Granted publication date: 20170308 |