CN106454431B - TV programme suggesting method and system - Google Patents
TV programme suggesting method and system Download PDFInfo
- Publication number
- CN106454431B CN106454431B CN201610900119.3A CN201610900119A CN106454431B CN 106454431 B CN106454431 B CN 106454431B CN 201610900119 A CN201610900119 A CN 201610900119A CN 106454431 B CN106454431 B CN 106454431B
- Authority
- CN
- China
- Prior art keywords
- program
- user
- real
- recommendation list
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Abstract
The present invention is provided in a kind of recommendation TV programme method and system, this method, program recommendation list can dynamically be adjusted according to program request behavior of the user in current slot, and recommend TV programme according to the program recommendation list after adjustment.In the present invention, because the viewing for combining active user is accustomed to, therefore the TV programme recommended are larger for the probability of the program to be watched of active user, and accuracy rate is higher.
Description
Technical field
The present invention relates to ntelligent television technolog field, and in particular to a kind of TV programme suggesting method and system.
Background technology
In recent years, with the continuous intensification of television set intelligently degree and interconnection networking degree, the type sum of TV programme
Amount is increased considerably, and various programs, news are flooded with the life of people.In face of so numerous and jumbled content cluster, people can not
Oneself real information interested is obtained by simply searching for, and repeats frequently way of search, people can be made to be weary of pair
The selection of program, loses the interest for viewing and admiring program.
To solve the above problems, television program recommendation system arises at the historic moment.Television program recommendation system is according to user's history
Behavioral data, sets up user interest preference model, filters out user's program interested, rapidly and accurately recommends to be liked to user
Good programme information.
During the present invention is realized, the inventors found that program recommendation system of the prior art is at least deposited
In following problem:
When generating recommendation list, traditional proposed algorithm has filtered the TV programme of targeted customer's program request, but has
A little TV programme such as serials etc., user may not finish, and exactly user may wish to;
Current television program recommendation system does not differentiate between domestic consumer, it is impossible to which good specific aim is according to the happiness of active user
Recommend corresponding program well;
Current TV programme be mainly it is live in the majority, supplemented by program request, but the fusion not yet in effect of current TV programme
The electric program menu of each channel of the same day, causes some programs to be recommended, and is not broadcast on the day of the program that some are recommended
Go out;
These above-mentioned problems cause the accuracy for the program that current program recommendation system recommended relatively low.
The content of the invention
(1) technical problem solved
It is an object of the present invention to the accuracy that at least part of raising program is recommended.
(2) technical scheme
To reach above-mentioned purpose, the first aspect of the invention provides a kind of TV programme suggesting method, including:
User is recorded as according to user's history program request record and program base attribute and generates offline program recommendation list;
Mobile state adjustment is entered to the offline program recommendation list according to current influence factor;The current influence factor bag
Include program request behavior of the active user in current slot;
It is that active user recommends TV programme according to the real time programme recommendation list after adjustment.
Further, the current influence factor is also including multiple channels in the preset time period after current slot
Real-time electronic program guide B.
Further, the current influence factor of the basis enters Mobile state adjustment to the offline program recommendation list, including:
Real-time Candidate Set E is generated according to program set A and real-time electronic program guide B;
Real-time Candidate Set D is generated according to offline program recommendation list and real-time electronic program guide B;
Real-time Candidate Set E and real-time Candidate Set D are merged, is the real time programme recommendation list List after user's generation adjustment;
The program set A is the set of active user's request program in current slot.
Further, it is described that real-time Candidate Set E is generated according to program set A and real-time electronic program guide B, including:
Preference pref of the user to program in program set A is calculated according to user interest modeling method;And using based on section
The proposed algorithm of mesh content, is calculated in program set A and real-time electronic program guide B between programme attribute according to program base attribute
Similitude sim, and the product of the preference pref of program in program set A is given birth to according to programme attribute similitude sim and user
Into preference w of the user to program in real-time electronic program guide B, according to preference w size to being saved in real-time electronic program guide B
Mesh is ranked up, and generates real-time Candidate Set E.
Further, it is described that the offline program of user's generation is recorded as according to user's history program request record and program base attribute
Recommendation list, including:
User's history program request record and program base attribute record are handled using user interest modeling method, with life
Into user preference matrix;
According to user preference matrix, using the Collaborative Filtering Recommendation Algorithm based on user, the first initial recommendation list is generated
Ulist;And/or the Collaborative Filtering Recommendation Algorithm based on program is utilized, generate the second initial recommendation list Vlist;
The series performance that whole collection/phases broadcasting is not completed in being recorded according to user's history program request generates the 3rd initial recommendation row
Table Plist;
Initially pushed away according to the first initial recommendation list Ulist of generation and the second initial recommendation list Vlist generations are middle
Recommend list UVlist;
Offline program is generated according to middle initial recommendation list UVlist and the 3rd initial recommendation list Plist and recommends row
Table.
Second aspect, the invention provides a kind of television program recommendation system, including:
Offline list recommending module, for being recorded as user's generation according to user's history program request record and program base attribute
Offline program recommendation list;
Adjusting module, for entering Mobile state adjustment to the offline program recommendation list according to current influence factor;It is described
Current influence factor includes active user the program request behavior in current slot;
Real-time list recommending module, for being that active user recommends TV Festival according to the real time programme recommendation list after adjustment
Mesh.
Further, the current influence factor is also including multiple channels in the preset time period after current slot
Real-time electronic program guide B.
Further, the adjusting module, for being carried out according to current influence factor to the offline program recommendation list
Dynamic adjustment, including:
Real-time Candidate Set E is generated according to program set A and real-time electronic program guide B;
Real-time Candidate Set D is generated according to offline program recommendation list and real-time electronic program guide B;
Real-time Candidate Set E and real-time Candidate Set D are merged, is the real time programme recommendation list List after user's generation adjustment.
Further, the adjusting module, for being waited according to program set A and real-time electronic program guide B generations are real-time
Selected works E, including:
Preference pref of the user to program in program set A is calculated according to user interest modeling method;And use base
In the proposed algorithm of programme content, program in program set A and real-time electronic program guide B is calculated according to program base attribute and belonged to
Similitude sim between property, and according to the preference pref of programme attribute similitude sim and user to program in program set A
Product generation user to the preference w of program in real-time electronic program guide B, according to preference w size to real-time electronic program
Program is ranked up in menu B, generates real-time Candidate Set E.
Further, the offline list recommending module, for according to user's history program request record and program base attribute
It is recorded as user and generates offline program recommendation list, including:
User's history program request record and program base attribute record are handled using user interest modeling method, with life
Into user preference matrix;
According to user preference matrix, using the Collaborative Filtering Recommendation Algorithm based on user, the first initial recommendation list is generated
Ulist;And/or the Collaborative Filtering Recommendation Algorithm based on program is utilized, generate the second initial recommendation list Vlist;
The series performance that whole collection/phases broadcasting is not completed in being recorded according to user's history program request generates the 3rd initial recommendation row
Table Plist;
Initially pushed away according to the first initial recommendation list Ulist of generation and the second initial recommendation list Vlist generations are middle
Recommend list UVlist;
Offline program is generated according to middle initial recommendation list UVlist and the 3rd initial recommendation list Plist and recommends row
Table.
(3) beneficial effect
The TV programme suggesting method that the present invention is provided, can be according to program request behavior of the user in current slot to section
Mesh recommendation list is dynamically adjusted, and recommends TV programme according to the program recommendation list after adjustment.In the present invention, due to
Combine active user viewing custom, therefore the TV programme recommended for the program to be watched of active user probability compared with
Greatly, accuracy rate is higher.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
The flow chart for the TV programme suggesting method that Fig. 1 provides for one embodiment of the invention;
The flow chart for the TV programme suggesting method that Fig. 2 provides for yet another embodiment of the invention;
Fig. 3 be Fig. 2 in TV programme suggesting method in the middle part of split flow schematic diagram;
Fig. 4 be Fig. 2 in TV programme suggesting method in the middle part of split flow schematic diagram;
The structural representation for the television program recommendation system that Fig. 5 one embodiment of the invention is provided.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
In a first aspect, the basic embodiment of the present invention provides a kind of TV programme suggesting method, referring to Fig. 1, this method
Including:
Step S11, is recorded as user according to user's history program request record and program base attribute and generates offline program recommendation
List;
Step S12, Mobile state adjustment is entered to the offline program recommendation list according to current influence factor;The current shadow
The factor of sound includes active user the program request behavior in current slot;
Step S13, is that active user recommends TV programme according to the real time programme recommendation list after adjustment.
The recommendation method of TV programme provided in an embodiment of the present invention, can be according to program request of the user in current slot
Behavior is dynamically adjusted to program recommendation list, and recommends TV programme according to the program recommendation list after adjustment.This hair
In bright, because the viewing for combining active user is accustomed to, therefore the TV programme recommended are the section to be watched of active user
Purpose probability is larger, and accuracy rate is higher.
In the specific implementation, it can also implement according to following one or several kinds of modes, further to improve program recommendation
Accuracy:
Mode one, the current influence factor also include the reality of multiple channels in the preset time period after current slot
When electric program menu.
So in the specific implementation, the program for recommending those currently never to play, such as variety show can be avoided
Deng the accuracy that further raising program is recommended.
Further, now step S12 can be specifically included:
Step S121, real-time Candidate Set E is generated according to program set A and real-time electronic program guide B;
Step S122, real-time Candidate Set D is generated according to offline program recommendation list and real-time electronic program guide B;
Step S123, merges real-time Candidate Set E and real-time Candidate Set D, is that the real time programme after user's generation adjustment is recommended
List List.
Specifically, when implementing, above-mentioned step S121 can be specifically included:Calculated according to user interest modeling method
Preference pref of the user to program in program set A;And the proposed algorithm based on programme content is used, according to program base attribute
The similitude sim between programme attribute in program set A and real-time electronic program guide B is calculated, and according to programme attribute similitude
Sim and user generate user to program in real-time electronic program guide B to the product of the preference pref of program in program set A
Preference w, is ranked up according to preference w size to program in real-time electronic program guide B, generates real-time Candidate Set E.
Here program set A is the set of active user's request program in current slot.
Mode three:It is described that offline program recommendation row are generated according to user's history program request record and program base attribute record
Table, including:
User's history program request record and program base attribute record are handled using user interest modeling method, with life
Into user preference matrix;
According to user preference matrix, using the Collaborative Filtering Recommendation Algorithm based on user, the first initial recommendation list is generated
Ulist;And/or the Collaborative Filtering Recommendation Algorithm based on program is utilized, generate the second initial recommendation list Vlist;
The series performance that whole collection/phases broadcasting is not completed in being recorded according to user's history program request generates the 3rd initial recommendation row
Table Plist;
Initially pushed away according to the first initial recommendation list Ulist of generation and the second initial recommendation list Vlist generations are middle
Recommend list UVlist;
Offline program is generated according to middle initial recommendation list UVlist and the 3rd initial recommendation list Plist and recommends row
Table.
In this way, user's program interested more can be effectively filtered out, removes user less interested
Program, improve recommend accuracy.
Further, it is described according to the first initial recommendation list Ulist of generation and the second initial recommendation in mode three
Initial recommendation list UVlist in the middle of list Vlist generations, can implement according to following preferred embodiment, be saved with further improve
The accuracy that mesh is recommended.Specifically, it can include:
According to preference of the user to the program in the first initial recommendation list Ulist and the second initial recommendation list Vlist
Initial recommendation list UVlist in the middle of degree generation;Wherein, in the first initial recommendation list Ulist and the second initial recommendation list
When Vlist includes same program, the preference for taking the program is program correspondence in the first initial recommendation list Ulist
Preference and in the second initial recommendation list Vlist corresponding preference average value.
In order to make it easy to understand, one kind of the method for the recommendation TV programme provided below the present invention is preferred embodiment
It is described in more detail:
Referring to Fig. 2, the overall flow of this method may include steps of:
1, using set top box harvester, collect user's history program request record;Using EPG data harvester, collect each
Electric program menu and program the base attribute record that individual channel is played;Above-mentioned real-time electronic program guide can so be obtained
B;
2, recorded, do not completed in generation user's history program request record according to program base attribute record and user's history program request
The series performance that whole collection/phase plays generates the 3rd initial recommendation list Plist;User interest modeling method is utilized simultaneously, it is raw
Into user preference matrix;
3, according to user preference matrix, the Collaborative Filtering Recommendation Algorithm based on user and based on program is utilized respectively, is mesh
Mark user and generate the first initial recommendation list Ulist;It is targeted customer's generation using the Collaborative Filtering Recommendation Algorithm based on program
Second initial recommendation list Vlist;
4, the 3rd initial recommendation list Plist of fusion, the first initial recommendation list Ulist and the second initial recommendation list
Vlist, generates offline program recommendation list UVPlist;
5, using set top box harvester, user's real-time VOD behavior is collected, active user is in current slot for generation
The program set A of program request
6, based on program set A, offline program recommendation list UVPlist and real-time electronic program guide B, using based on interior
The proposed algorithm of appearance, generation real time programme recommendation list List.
Wherein, based on user Collaborative Filtering Recommendation Algorithm and the Collaborative Filtering Recommendation Algorithm recommended user based on program
The similitude program of program request, again will not recommend the TV programme of user's program request for it, and actually TV programme have
Repeated and successional feature, user can largely watch the different collection numbers of same TV programme, therefore in generation
Need to consider not complete series performance that whole collection/phases play i.e. the when consequently recommended list in user's history program request record
Three initial recommendation list Plist, generate offline program recommendation list UVPlist.
Wherein, in above-mentioned step 4, when each algorithm generates respective recommendation list and merged, referring to
Fig. 3, concrete operation step can be as follows:
(1) if program is variety column news etc., total collection number FjValue do not know, it is now inclined to the program according to user
Good size is ranked up the 3rd initial recommendation list Plist of generation;If program is TV series, total collection number FjFor fixation
It is worth, then counting user uuProgram v is crossed in program requestjThe collection number of nearest timeWith total collection number FjRelation, ifThen according to
Family uuTo program vjPreference size be ranked up, generate the 3rd initial recommendation list Plist;IfThen not the program
Include the 3rd initial recommendation list Plist.
(2) according to size of the user to program preferences, at the beginning of fusion the first initial recommendation list Ulist recommendation lists and second
Initial recommendation list UVlist in the middle of program generation in beginning recommendation list Vlist, if same program is initially pushed away in centre respectively
Recommend in list UVlist and the second initial recommendation list Vlist, then take the average value of its preference, arranged further according to preference size
Sequence;
(3) program in the middle of merging in initial recommendation list UVlist and the 3rd initial recommendation list Plist, according to preference
Size is ranked up, and generates offline program recommendation list UVPlist.
In above-mentioned step 6, referring to Fig. 4, generation real time programme recommendation list List process can include:
(1) according to current time T, the user institute program request in the interval (i.e. [T-t1, T] time interval) of t1 minutes is taken forward
Program set A;
(2) utilize EPG data harvester, according to current time T, take backward t2 minutes interval (i.e. [T, T+t2] when
Between it is interval) in each channel the program set B that is included of electric program menu;Here program set B is current influence
Factor also includes the real-time electronic program guide B of multiple channels in the preset time period after current slot;
(3) all section destination aggregation (mda)s in offline program recommendation list UVPlist are designated as C;
(4) real-time Candidate Set D=C ∩ B are generated;
(5) proposed algorithm based on programme content is used, program set A and program set are calculated according to program base attribute
The attribute similarity sim of program in B;
(6) according to user interest preference model, preference pref of the user to program in program set A is calculated;
(7) preference w=pref*sim of the user to program in program set B is calculated;
(8) according to preference w size, real-time Candidate Set E is generated;
(9) according to preference size of the user to program in real-time Candidate Set D and real-time Candidate Set E, to real-time Candidate Set D and
Program in real-time Candidate Set E is ranked up, and is active user's generation real time programme recommendation list List.
On the other hand, the embodiment of the present invention additionally provides a kind of system of recommendation TV programme, and referring to 5, the system includes:
Offline list recommending module 51, for being recorded as user's life according to user's history program request record and program base attribute
Into offline program recommendation list;
Adjusting module 52, for entering Mobile state adjustment to the program recommendation list according to current influence factor;It is described to work as
Preceding influence factor includes active user the program request behavior in current slot;
Real-time list recommending module 53, for being that active user recommends TV according to the real time programme recommendation list after adjustment
Program.
Further, the current influence factor is also including multiple channels in the preset time period after current slot
Real-time electronic program guide B.
Further, the system also includes:The adjusting module 52, for being pushed away according to current influence factor to the program
Recommend list and enter Mobile state adjustment, including:
Real-time Candidate Set E is generated according to program set A and real-time electronic program guide B;
Real-time Candidate Set D is generated according to offline program recommendation list and real-time electronic program guide B;
Real-time Candidate Set E and real-time Candidate Set D are merged, is the real time programme recommendation list List after user's generation adjustment;
The program set A is the set of active user's request program in current slot.
Further, the adjusting module 52, it is real for being generated according to program set A and real-time electronic program guide B
When Candidate Set E, can specifically include:
Preference pref of the user to program in program set A is calculated according to user interest modeling method;And using based on section
The proposed algorithm of mesh content, is calculated in program set A and real-time electronic program guide B between programme attribute according to program base attribute
Similitude sim, and the product of the preference pref of program in program set A is given birth to according to programme attribute similitude sim and user
Into preference w of the user to program in real-time electronic program guide B, according to preference w size to being saved in real-time electronic program guide B
Mesh is ranked up, and generates real-time Candidate Set E.
Accordingly, adjusting module 52 is used to merge real-time Candidate Set E and real-time Candidate Set D, is after user's generation is adjusted
Real time programme recommendation list List.
Further, the offline list recommending module 51 is used for according to user's history program request record and program base attribute
It is recorded as user and generates offline program recommendation list, including:
User's history program request record and program base attribute record are handled using user interest modeling method, with life
Into user preference matrix;
According to user preference matrix, using the Collaborative Filtering Recommendation Algorithm based on user, the first initial recommendation list is generated
Ulist;And/or the Collaborative Filtering Recommendation Algorithm based on program is utilized, generate the second initial recommendation list Vlist;
The series performance that whole collection/phases broadcasting is not completed in being recorded according to user's history program request generates the 3rd initial recommendation row
Table Plist;
Initially pushed away according to the first initial recommendation list Ulist of generation and the second initial recommendation list Vlist generations are middle
Recommend list UVlist;
Offline program recommendation list is generated according to middle initial recommendation list UVlist and the 3rd initial recommendation list Plist
UVPlist。
It is understandable to be, because the system of the recommendation TV programme of above-mentioned second aspect introduction is that can perform the present invention
The device of the method for recommendation TV programme in embodiment, so based on the recommendation TV programme described in the embodiment of the present invention
Method, those skilled in the art can understand the embodiment of the system of the recommendation TV programme of the present embodiment with
And its various change form, so how the system at this for the recommendation TV programme realizes recommendation in the embodiment of the present invention
The method of TV programme is no longer discussed in detail.As long as those skilled in the art implement to recommend TV Festival in the embodiment of the present invention
The device that purpose method is used, belongs to the scope to be protected of the application.
The third aspect, the invention provides a kind of electronic equipment, including processor and storage medium;The processor by with
The instruction stored in the execution storage medium;
Be stored with instruction in the storage medium, the instruction be used to perform described in first aspect and any one method
Instruction.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Understood based on such, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Order is to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
In the specification that this place is provided, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect, exist
Above in the description of the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:It is i.e. required to protect
The application claims of shield features more more than the feature being expressly recited in each claim.More precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
All as the separate embodiments of the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit is required, summary and accompanying drawing) disclosed in each feature can or similar purpose identical, equivalent by offer alternative features come generation
Replace.
Although in addition, it will be appreciated by those of skill in the art that some embodiments in this include institute in other embodiments
Including some features rather than further feature, but not the combination of the feature of be the same as Example mean be in the scope of the present invention
Within and form different embodiments.For example, in the following claims, embodiment claimed it is any it
One mode can use in any combination.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and coming real by means of properly programmed computer
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Finally it should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that:It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic;
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (8)
1. a kind of TV programme suggesting method, it is characterised in that including:
User is recorded as according to user's history program request record and program base attribute and generates offline program recommendation list;
Mobile state adjustment is entered to the offline program recommendation list according to current influence factor;The current influence factor includes working as
Program request behavior of the preceding user in current slot;
It is that active user recommends TV programme according to the real time programme recommendation list after adjustment;
Wherein,
It is described that the offline program recommendation list of user's generation, bag are recorded as according to user's history program request record and program base attribute
Include:
User's history program request record and program base attribute record are handled using user interest modeling method, to generate use
Family preference matrix;
According to user preference matrix, using the Collaborative Filtering Recommendation Algorithm based on user, the first initial recommendation list is generated
Ulist;And/or the Collaborative Filtering Recommendation Algorithm based on program is utilized, generate the second initial recommendation list Vlist;
The series performance that whole collection/phases broadcasting is not completed in being recorded according to user's history program request generates the 3rd initial recommendation list
Plist;
According to initial recommendation row in the middle of the first initial recommendation list Ulist of generation and the second initial recommendation list Vlist generations
Table UVlist;
Offline program recommendation list is generated according to middle initial recommendation list UVlist and the 3rd initial recommendation list Plist.
2. according to the method described in claim 1, it is characterised in that the current influence factor is also included after current slot
Preset time period in multiple channels real-time electronic program guide B.
3. method according to claim 2, it is characterised in that the current influence factor of basis is pushed away to the offline program
Recommend list and enter Mobile state adjustment, including:
Real-time Candidate Set E is generated according to program set A and real-time electronic program guide B;
Real-time Candidate Set D is generated according to offline program recommendation list and real-time electronic program guide B;
Real-time Candidate Set E and real-time Candidate Set D are merged, is the real time programme recommendation list List after user's generation adjustment;It is described
Program set A is the set of active user's request program in current slot.
4. method according to claim 3, it is characterised in that described according to program set A and real-time electronic program guide B
Real-time Candidate Set E is generated, including:
Preference pref of the user to program in program set A is calculated according to user interest modeling method;And using based in program
The proposed algorithm of appearance, the phase in program set A and real-time electronic program guide B between programme attribute is calculated according to program base attribute
Use is generated to the product of the preference pref of program in program set A like property sim, and according to programme attribute similitude sim and user
Family is entered to the preference w of program in real-time electronic program guide B according to preference w size to program in real-time electronic program guide B
Row sequence, generates real-time Candidate Set E.
5. a kind of television program recommendation system, it is characterised in that including:
Offline list recommending module, it is offline for being recorded as user's generation according to user's history program request record and program base attribute
Program recommendation list;
Adjusting module, for entering Mobile state adjustment to the offline program recommendation list according to current influence factor;It is described current
Influence factor includes active user the program request behavior in current slot;
Real-time list recommending module, for being that active user recommends TV programme according to the real time programme recommendation list after adjustment;
Wherein,
The offline list recommending module, for being recorded as user's generation according to user's history program request record and program base attribute
Offline program recommendation list, including:
User's history program request record and program base attribute record are handled using user interest modeling method, to generate use
Family preference matrix;
According to user preference matrix, using the Collaborative Filtering Recommendation Algorithm based on user, the first initial recommendation list is generated
Ulist;And/or the Collaborative Filtering Recommendation Algorithm based on program is utilized, generate the second initial recommendation list Vlist;
The series performance that whole collection/phases broadcasting is not completed in being recorded according to user's history program request generates the 3rd initial recommendation list
Plist;
According to initial recommendation row in the middle of the first initial recommendation list Ulist of generation and the second initial recommendation list Vlist generations
Table UVlist;
Offline program recommendation list is generated according to middle initial recommendation list UVlist and the 3rd initial recommendation list Plist.
6. system according to claim 5, it is characterised in that the current influence factor is also included after current slot
Preset time period in multiple channels real-time electronic program guide B.
7. system according to claim 6, it is characterised in that the adjusting module, for according to current influence factor pair
The offline program recommendation list enters Mobile state adjustment, including:
Real-time Candidate Set E is generated according to program set A and real-time electronic program guide B;
Real-time Candidate Set D is generated according to offline program recommendation list and real-time electronic program guide B;
Real-time Candidate Set E and real-time Candidate Set D are merged, is the real time programme recommendation list List after user's generation adjustment;It is described
Program set A is the set of active user's request program in current slot.
8. system according to claim 7, it is characterised in that the adjusting module, for according to program set A and in real time
Electric program menu B generates real-time Candidate Set E, including:
Preference pref of the user to program in program set A is calculated according to user interest modeling method;And using based in program
The proposed algorithm of appearance, the phase in program set A and real-time electronic program guide B between programme attribute is calculated according to program base attribute
Use is generated to the product of the preference pref of program in program set A like property sim, and according to programme attribute similitude sim and user
Family is entered to the preference w of program in real-time electronic program guide B according to preference w size to program in real-time electronic program guide B
Row sequence, generates real-time Candidate Set E.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610900119.3A CN106454431B (en) | 2016-10-14 | 2016-10-14 | TV programme suggesting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610900119.3A CN106454431B (en) | 2016-10-14 | 2016-10-14 | TV programme suggesting method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106454431A CN106454431A (en) | 2017-02-22 |
CN106454431B true CN106454431B (en) | 2017-09-05 |
Family
ID=58174457
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610900119.3A Active CN106454431B (en) | 2016-10-14 | 2016-10-14 | TV programme suggesting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106454431B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106878772B (en) * | 2017-02-27 | 2020-04-07 | 优地网络有限公司 | Program recommendation method and device |
CN107659849A (en) * | 2017-11-03 | 2018-02-02 | 中广热点云科技有限公司 | A kind of method and system for recommending program |
CN107958668B (en) * | 2017-12-15 | 2022-04-19 | 中广热点云科技有限公司 | Voice control broadcasting method and voice control broadcasting system of smart television |
CN108243357A (en) * | 2018-01-25 | 2018-07-03 | 北京搜狐新媒体信息技术有限公司 | A kind of video recommendation method and device |
CN108419088B (en) * | 2018-02-08 | 2020-06-19 | 华南理工大学 | Channel recommendation method facing high-burstiness user request |
CN108737856B (en) * | 2018-04-26 | 2020-03-20 | 西北大学 | Social relation perception IPTV user behavior modeling and program recommendation method |
CN112052378B (en) * | 2019-10-15 | 2021-09-21 | 河南紫联物联网技术有限公司 | Intelligent terminal, and recommendation method and system for intelligent home application |
CN114915844B (en) * | 2021-11-08 | 2023-02-28 | 海看网络科技(山东)股份有限公司 | Method and system for realizing real-time intelligent recommendation on IPTV |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104168510A (en) * | 2014-05-14 | 2014-11-26 | 录可系统公司 | Preference program dynamic recommendation method and system |
CN104735477A (en) * | 2013-12-18 | 2015-06-24 | 三星电子株式会社 | Apparatus And Method For Recommending Content |
CN105915949A (en) * | 2015-12-23 | 2016-08-31 | 乐视网信息技术(北京)股份有限公司 | Video content recommending method, device and system |
CN106028071A (en) * | 2016-05-17 | 2016-10-12 | Tcl集团股份有限公司 | Video recommendation method and system |
-
2016
- 2016-10-14 CN CN201610900119.3A patent/CN106454431B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104735477A (en) * | 2013-12-18 | 2015-06-24 | 三星电子株式会社 | Apparatus And Method For Recommending Content |
CN104168510A (en) * | 2014-05-14 | 2014-11-26 | 录可系统公司 | Preference program dynamic recommendation method and system |
CN105915949A (en) * | 2015-12-23 | 2016-08-31 | 乐视网信息技术(北京)股份有限公司 | Video content recommending method, device and system |
CN106028071A (en) * | 2016-05-17 | 2016-10-12 | Tcl集团股份有限公司 | Video recommendation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN106454431A (en) | 2017-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106454431B (en) | TV programme suggesting method and system | |
US10356462B1 (en) | Recommending a composite channel | |
CN104822074B (en) | A kind of recommendation method and device of TV programme | |
JP6104154B2 (en) | Presentation of media consumption summary | |
US8869205B2 (en) | Method and system for video collection management, invalid video replacement and continuous video replay | |
US11023100B2 (en) | Methods, systems, and media for creating and updating a group of media content items | |
CN103634687B (en) | The method and system of video search result are provided in intelligent television | |
CN107172452A (en) | Direct broadcasting room recommends method and device | |
CN104065981A (en) | Method and device for recommending videos | |
CN104053023B (en) | A kind of method and device of determining video similarity | |
CN104504059A (en) | Multimedia resource recommending method | |
CN104768073A (en) | Displaying method and device for channel menu | |
CN109429103B (en) | Method and device for recommending information, computer readable storage medium and terminal equipment | |
JPWO2013118198A1 (en) | Recommended content providing apparatus, recommended content providing program, and recommended content providing method | |
US20230008928A1 (en) | Systems and methods for media content navigation and filtering | |
CN104902292A (en) | Television report-based public opinion analysis method and system | |
US20140229828A1 (en) | Creating playlists | |
CN108307239A (en) | A kind of video content recommendation method and apparatus | |
CN109151488A (en) | According to the method and system of user behavior real-time recommendation direct broadcasting room | |
CN104699696A (en) | File recommendation method and device | |
CN103731737B (en) | A kind of video information update method and electronic equipment | |
CN106713985A (en) | Method and device for recommending network video | |
CN105100840A (en) | Method and device for inter-cut of recommended media information | |
CN105898433B (en) | TV programme suggesting method and device | |
CN107613323A (en) | A kind of intelligent EPG recommended engines implementation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |