CN107613323A - A kind of intelligent EPG recommended engines implementation method - Google Patents
A kind of intelligent EPG recommended engines implementation method Download PDFInfo
- Publication number
- CN107613323A CN107613323A CN201610545855.1A CN201610545855A CN107613323A CN 107613323 A CN107613323 A CN 107613323A CN 201610545855 A CN201610545855 A CN 201610545855A CN 107613323 A CN107613323 A CN 107613323A
- Authority
- CN
- China
- Prior art keywords
- epg
- data
- live
- depth
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses a kind of intelligent EPG recommended engines implementation method, including:The whole network gathers EPG library of programmes and generates depth EPG data;According to the live Hot Contents of social data real-time recommendation and incorporate in depth EPG data;Merge live, program request and review data, based on unified metadata and clustering algorithm, the similar programme content of correlation recommendation is simultaneously incorporated in depth EPG data;The live of behavioral data recommendation personalization, program request are watched according to user and reviews programme content and incorporates in depth EPG data;By, by cross validation, information filtering, rule match, relevant matches then being carried out with the metadatabase of enhancing again, generation depth EPG data carrys out expansion EPG data to original EPG information.On this basis based on intelligent recommendation engine and social discovery engine, live correlation recommendation, live association program request, live current hot broadcast, live personalized recommendation etc. are realized.
Description
Technical field
The present invention relates to television video field, more particularly to a kind of intelligent EPG recommended engines implementation method.
Background technology
Since live telecast starts, TV is just enjoyed along with people or so, people in live telecast always
The vision viewing experience of high definition, live telecast and program request are the rigid demands of televiewer.Traditional EPG (Electronic
Program Guide electronic program guides) centered on channel, user toggles channel, but can not find the content for wanting to see.Point
Broadcasting storehouse has many contents, but only above several pages of a small amount of contents are presented to user and watched, on-demand assets utilization rate less than
20%-30%.In addition, live and program request (including reviewing) is often what is separated, every on-demand content provider has respective
Program request entrance, live and auto-associating and seamless switching of program request can not be realized.Scene 1:User watch live telecast when
Time is wanted to watch the programme content oneself liked, and if 100 channels, user wants switching channels to go for content 100 times, entirely
Process extreme influence Consumer's Experience.Scene 2:User is watching the program seeing when live telecast and oneself liking, when this
Program finishes user and still wants to watch the collection number above missed or the program of same type, is also just at a loss.
User needs a unified entrance, and by the entrance, user can be able to conveniently find the content for oneself wanting to see, can
With the seamless switching realized live, program request and review content.
The content of the invention
In view of the above-mentioned deficiency that presently, there are, the present invention provides a kind of intelligent EPG recommended engines implementation method, can realize
Live, program request and the seamless switching for reviewing content.
To reach above-mentioned purpose, embodiments of the invention adopt the following technical scheme that:
A kind of intelligent EPG recommended engines implementation method, the intelligent EPG recommended engines implementation method comprise the following steps:
The whole network gathers EPG library of programmes and generates depth EPG data;
According to the live Hot Contents of social data real-time recommendation and incorporate in depth EPG data;
Merge live, program request and review data, based on unified metadata and clustering algorithm, in the similar program of correlation recommendation
Hold and incorporate in depth EPG data;
The live of behavioral data recommendation personalization, program request are watched according to user and reviews programme content and incorporates depth EPG
In data.
According to one aspect of the present invention, described the whole network, which gathers EPG library of programmes and generates depth EPG data, to be included:The whole network
EPG library of programmes is gathered, matched rule is filtered based on EPG, live telecast EPG programs and the whole network program request storehouse program are matched, it is raw
Into depth EPG data.
According to one aspect of the present invention, described the whole network, which gathers EPG library of programmes and generates depth EPG data, to be included:To adopting
The original EPG information of collection is then related to the metadatabase progress of enhancing again by cross validation, information filtering, rule match
Matching, generate depth EPG data.
According to one aspect of the present invention, the intelligent EPG recommended engines implementation method includes:According to depth EPG data
Show that the video display list of recommendation is watched for selection by the user on broadcast interface.
According to one aspect of the present invention, the intelligent EPG recommended engines implementation method includes:Acquisition internet data,
Third party's depth EPG data and live EPG data, are managed with the metadata for forming unified.
According to one aspect of the present invention, it is described according to user watch behavioral data recommend personalized live, program request and
Reviewing programme content and incorporating depth EPG data includes:By gathering behavior hobby and evaluation, real-time receipts of the user to program
Collect the historical information of related context information and passing user, analysis and excavate user under the conditions of the scene being presently in
Demand carries out the recommendation of programme content with extraction kinsfolk's interest characteristics.
The advantages of present invention is implemented:Intelligent EPG recommended engines implementation method of the present invention, including:The whole network gathers EPG
Library of programmes simultaneously generates depth EPG data;According to the live Hot Contents of social data real-time recommendation and incorporate in depth EPG data;
Merge live, program request and review data, based on unified metadata and clustering algorithm, the similar programme content of correlation recommendation simultaneously incorporates
In depth EPG data;The live of behavioral data recommendation personalization, program request are watched according to user and reviews programme content and incorporates depth
Spend in EPG data;With program and user-center, user does not have to switching channels it is seen that just in the programme televised live of hot broadcast
(the real-time seniority among brothers and sisters and personalized recommendation of programme televised live), live auto-associating program request and reviews content (same program and similar section
Mesh), realize live and program request seamless switching.By passing through cross validation, information filtering, rule match to original EPG information,
Then relevant matches are carried out with the metadatabase of enhancing again, generation depth EPG data carrys out expansion EPG data.Base on this basis
In intelligent recommendation engine and it is social find engine, realize live correlation recommendation, live association program request, live current hot broadcast, live
Personalized recommendation.Effectively lifting content operation value and TV feed amount cashability, improve the live and resource utilization of program request,
Pay content conversion ratio and ARPU values, live and program request seamless switching is realized, Perfect Experience is brought for user.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, it will use below required in embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for ability
For the those of ordinary skill of domain, on the premise of not paying creative work, it can also be obtained according to these accompanying drawings other attached
Figure.
Fig. 1 is a kind of intelligent EPG recommended engines implementation method schematic diagram of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
As shown in figure 1, a kind of intelligent EPG recommended engines implementation method, the intelligent EPG recommended engines implementation method includes
Following steps:
Step S1:The whole network gathers EPG library of programmes and generates depth EPG data;
In actual applications, described the whole network gathers EPG library of programmes and generates depth EPG data and may include:The whole network gathers EPG
Library of programmes, matched rule is filtered based on EPG, live telecast EPG programs and the whole network program request storehouse program are matched, generates depth
EPG data.
In actual applications, described the whole network gathers EPG library of programmes and generates depth EPG data and may include:To the original of collection
Then beginning EPG information carries out relevant matches, life with the metadatabase of enhancing again by cross validation, information filtering, rule match
Into depth EPG data.
Step S2:According to the live Hot Contents of social data real-time recommendation and incorporate in depth EPG data;
According to microblogging wechat social data, the live Hot Contents of engine real-time recommendation are found by social activity.
In actual applications, the intelligent EPG recommended engines implementation method includes:Obtain internet data, third party's depth
EPG data and live EPG data are spent, is managed with the metadata for forming unified.
In actual applications, the metadata includes:Type label, programme content respective labels, director, performer, brief introduction,
Region, age, click volume etc..
Step S3:Merge live, program request and review data, it is same based on unified metadata and clustering algorithm, correlation recommendation
Class programme content is simultaneously incorporated in depth EPG data;
Step S4:The live of behavioral data recommendation personalization, program request are watched according to user and reviews programme content and incorporates
In depth EPG data.
In actual applications, it is described that the live of behavioral data recommendation personalization, program request are watched according to user and review program
Content simultaneously incorporates depth EPG data and included:It is related by gathering behavior hobby and evaluation, real-time collecting of the user to program
Context information and the historical information of passing user, analysis are simultaneously excavated demand of the user under the conditions of the scene being presently in and carried
Kinsfolk's interest characteristics is taken to carry out the recommendation of programme content.
In actual applications, the intelligent EPG recommended engines implementation method may include:Played according to depth EPG data
Show that the video display list of recommendation is watched for selection by the user on interface.
In actual applications, there can be following implementation result:
Current live:The real-time seniority among brothers and sisters and personalized recommendation of current live program, live program request and visualization are realized,
User does not have to switching channels it is seen which program of other channel hot broadcasts, the program play in which TV station, including save
Mesh playing progress rate.User sees that channel is no longer limited to a few channel, averagely watches channel quantity from less than 10 liftings
To 30-50.Its audience ratings can be improved with the program (bid ranking) of preferential recommendation cooperation TV station.Program request is recommended:It is based on
The programme televised live currently seen, the same program request of auto-associating recommendation/review program, or similar request program.By live
Auto-associating program request, the program in nearly all program request storehouse have the opportunity to be presented to user, on-demand assets utilization rate can from less than
30% is lifted to more than 90%.With preferential recommendation pay content, the buying rate and ARPU value of pay content can be improved.
The advantages of present invention is implemented:Intelligent EPG recommended engines implementation method of the present invention, including:The whole network gathers EPG
Library of programmes simultaneously generates depth EPG data;According to the live Hot Contents of social data real-time recommendation and incorporate in depth EPG data;
Merge live, program request and review data, based on unified metadata and clustering algorithm, the similar programme content of correlation recommendation simultaneously incorporates
In depth EPG data;The live of behavioral data recommendation personalization, program request are watched according to user and reviews programme content and incorporates depth
Spend in EPG data;With program and user-center, user does not have to switching channels it is seen that just in the programme televised live of hot broadcast
(the real-time seniority among brothers and sisters and personalized recommendation of programme televised live), live auto-associating program request and reviews content (same program and similar section
Mesh), realize live and program request seamless switching.By passing through cross validation, information filtering, rule match to original EPG information,
Then relevant matches are carried out with the metadatabase of enhancing again, generation depth EPG data carrys out expansion EPG data.Base on this basis
In intelligent recommendation engine and it is social find engine, realize live correlation recommendation, live association program request, live current hot broadcast, live
Personalized recommendation.Effectively lifting content operation value and TV feed amount cashability, improve the live and resource utilization of program request,
Pay content conversion ratio and ARPU values, live and program request seamless switching is realized, Perfect Experience is brought for user.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those skilled in the art is in technical scope disclosed by the invention, the change or replacement that can readily occur in, all should
It is included within the scope of the present invention.Therefore, protection scope of the present invention should using the scope of the claims as
It is accurate.
Claims (6)
1. a kind of intelligent EPG recommended engines implementation method, it is characterised in that the intelligent EPG recommended engines implementation method includes
Following steps:
The whole network gathers EPG library of programmes and generates depth EPG data;
According to the live Hot Contents of social data real-time recommendation and incorporate in depth EPG data;
Merge live, program request and review data, based on unified metadata and clustering algorithm, the similar programme content of correlation recommendation is simultaneously
Incorporate in depth EPG data;
The live of behavioral data recommendation personalization, program request are watched according to user and reviews programme content and incorporates depth EPG data
In.
2. intelligent EPG recommended engines implementation method according to claim 1, it is characterised in that the whole network collection EPG sections
Mesh storehouse simultaneously generates depth EPG data and included:The whole network gathers EPG library of programmes, matched rule is filtered based on EPG, by live telecast EPG
Program and the whole network program request storehouse program match, and generate depth EPG data.
3. intelligent EPG recommended engines implementation method according to claim 2, it is characterised in that the whole network collection EPG sections
Mesh storehouse simultaneously generates depth EPG data and included:Cross validation, information filtering, rule match are passed through to the original EPG information of collection,
Then the metadatabase again with enhancing carries out relevant matches, generates depth EPG data.
4. intelligent EPG recommended engines implementation method according to claim 1, it is characterised in that the intelligent EPG recommends to draw
Holding up implementation method includes:The video display list that recommendation is shown on broadcast interface according to depth EPG data is watched for selection by the user.
5. the intelligent EPG recommended engines implementation method according to one of claim 1 to 5, it is characterised in that the intelligence
EPG recommended engine implementation methods include:Internet data, third party's depth EPG data and live EPG data are obtained, to be formed
Unified metadata is managed.
6. intelligent EPG recommended engines implementation method according to claim 5, it is characterised in that described to be watched according to user
Behavioral data recommends the live of personalization, program request and reviews programme content and incorporate depth EPG data to include:Used by gathering
The related context information of behavior hobby and evaluation, real-time collecting of the family to program and the historical information of passing user, analysis are simultaneously
Demand of the user under the conditions of the scene being presently in is excavated with extraction kinsfolk's interest characteristics to carry out pushing away for programme content
Recommend.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610545855.1A CN107613323A (en) | 2016-07-12 | 2016-07-12 | A kind of intelligent EPG recommended engines implementation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610545855.1A CN107613323A (en) | 2016-07-12 | 2016-07-12 | A kind of intelligent EPG recommended engines implementation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107613323A true CN107613323A (en) | 2018-01-19 |
Family
ID=61055503
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610545855.1A Pending CN107613323A (en) | 2016-07-12 | 2016-07-12 | A kind of intelligent EPG recommended engines implementation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107613323A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111770358A (en) * | 2020-06-28 | 2020-10-13 | 山东云缦智能科技有限公司 | Method for live broadcasting or watching program selection based on smart television |
CN113449205A (en) * | 2021-08-30 | 2021-09-28 | 四川省人工智能研究院(宜宾) | Recommendation method and system based on metadata enhancement |
CN113505291A (en) * | 2021-05-27 | 2021-10-15 | 成都数博视科技有限公司 | Intelligent content recommendation system based on user behavior data |
CN114339441A (en) * | 2022-03-16 | 2022-04-12 | 海看网络科技(山东)股份有限公司 | Method for realizing direct point intercommunication function in IPTV |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101690181A (en) * | 2007-04-30 | 2010-03-31 | 谷歌公司 | Momentary electronic program guide |
CN102404612A (en) * | 2011-12-21 | 2012-04-04 | 江苏省广电有线信息网络股份有限公司南京分公司 | EPG (Electronic Program Guide) system based on depth program information and realizing method therefor |
CN105224576A (en) * | 2014-07-01 | 2016-01-06 | 上海视畅信息科技有限公司 | A kind of video display intelligent recommendation method |
CN105323625A (en) * | 2014-07-01 | 2016-02-10 | 上海视畅信息科技有限公司 | Method and system for achieving integration of live broadcast and broadcast on demand |
US20160165316A1 (en) * | 2012-08-17 | 2016-06-09 | Flextronics Ap, Llc | Systems and methods for providing user interfaces in an intelligent television |
-
2016
- 2016-07-12 CN CN201610545855.1A patent/CN107613323A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101690181A (en) * | 2007-04-30 | 2010-03-31 | 谷歌公司 | Momentary electronic program guide |
CN102404612A (en) * | 2011-12-21 | 2012-04-04 | 江苏省广电有线信息网络股份有限公司南京分公司 | EPG (Electronic Program Guide) system based on depth program information and realizing method therefor |
US20160165316A1 (en) * | 2012-08-17 | 2016-06-09 | Flextronics Ap, Llc | Systems and methods for providing user interfaces in an intelligent television |
CN105224576A (en) * | 2014-07-01 | 2016-01-06 | 上海视畅信息科技有限公司 | A kind of video display intelligent recommendation method |
CN105323625A (en) * | 2014-07-01 | 2016-02-10 | 上海视畅信息科技有限公司 | Method and system for achieving integration of live broadcast and broadcast on demand |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111770358A (en) * | 2020-06-28 | 2020-10-13 | 山东云缦智能科技有限公司 | Method for live broadcasting or watching program selection based on smart television |
CN113505291A (en) * | 2021-05-27 | 2021-10-15 | 成都数博视科技有限公司 | Intelligent content recommendation system based on user behavior data |
CN113449205A (en) * | 2021-08-30 | 2021-09-28 | 四川省人工智能研究院(宜宾) | Recommendation method and system based on metadata enhancement |
CN114339441A (en) * | 2022-03-16 | 2022-04-12 | 海看网络科技(山东)股份有限公司 | Method for realizing direct point intercommunication function in IPTV |
CN114339441B (en) * | 2022-03-16 | 2022-06-07 | 海看网络科技(山东)股份有限公司 | Method for realizing direct point intercommunication function in IPTV |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103491441B (en) | Recommendation method and system of live television programs | |
US9077857B2 (en) | Graphical electronic programming guide | |
CN106851368B (en) | Television controlled by remote controller | |
US20230328318A1 (en) | Methods and systems for determining user engagement based on user interactions during different time intervals | |
AU2011299234B2 (en) | Collecting data from different sources | |
US9900656B2 (en) | Method and system for customer management | |
US20140052696A1 (en) | Systems and methods for visual categorization of multimedia data | |
CN102843586A (en) | Video recommendation method and terminal | |
US20130347033A1 (en) | Methods and systems for user-induced content insertion | |
EP3340612B1 (en) | Systems and methods for indicating media asset access conflicts using a time bar | |
EP2645732A2 (en) | Method for receiving enhanced service and display apparatus thereof | |
CA2731054A1 (en) | Method and system to request audiovisual content items matched to programs identified in a program grid | |
WO2015089400A1 (en) | Systems and methods for combining media recommendations from multiple recommendation engines | |
KR101774397B1 (en) | Method and apparatus for providing preferred information about broadcasting | |
CN103562848A (en) | Multi-source and destination media discovery and management platform | |
CN104079996A (en) | Television program push method and equipment | |
CN102244811A (en) | System and method for recommending television channels | |
CN107613323A (en) | A kind of intelligent EPG recommended engines implementation method | |
CN104115504A (en) | Targeted advertising | |
KR20190037270A (en) | System and method for clarifying terms based on static and temporal knowledge graphs | |
CN106454431A (en) | Method and system for recommending television programs | |
CA2731051A1 (en) | Management and delivery of audiovisual content items that correspond to scheduled programs | |
CN104219576A (en) | Smart television based play program recommendation method | |
CN104219577A (en) | Hybrid real-time television program and network video recommending method based on intelligent televisions | |
CN105791912A (en) | Cloud-based data processing method, system and set top box |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180119 |
|
RJ01 | Rejection of invention patent application after publication |