CN102572543A - Digital television program recommending system and method thereof - Google Patents
Digital television program recommending system and method thereof Download PDFInfo
- Publication number
- CN102572543A CN102572543A CN2012100505878A CN201210050587A CN102572543A CN 102572543 A CN102572543 A CN 102572543A CN 2012100505878 A CN2012100505878 A CN 2012100505878A CN 201210050587 A CN201210050587 A CN 201210050587A CN 102572543 A CN102572543 A CN 102572543A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- program
- digital television
- user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000013523 data management Methods 0.000 claims description 8
- 238000007418 data mining Methods 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 4
- 101000622430 Homo sapiens Vang-like protein 2 Proteins 0.000 claims 2
- 102100023520 Vang-like protein 2 Human genes 0.000 claims 2
- 238000005065 mining Methods 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 14
- 230000007246 mechanism Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 230000008713 feedback mechanism Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 230000000366 juvenile effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000009227 behaviour therapy Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013440 design planning Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention discloses a digital television program recommending system, which comprises a set top box module (STBM) access control module, a user behavior analysis (UBA) service module, a recommender system (RES) service module and a profile manager (PMS) module, wherein the STBM module is used for conducting Bluetooth communication between a set top box and mobile equipment and using an obtained Bluetooth address as a user mark; the UBA module is used for updating or registering user data according to the user mark and recording programs which a user watches presently and historically; the RES module is used for comparing the transmitted data with an electronic program menu, finding out the programs of which the watching frequency is high in personal information and simultaneously transmitting the information into the PMS module; the PMS module is used for collecting data and information of the UBA module and the RES module, mining the data through a K-mean clustering method and a K adjacent method, finding out a recommending result and transmitting the recommending result to the mobile equipment through a Bluetooth protocol. The invention simultaneously discloses a digital television program recommending method. Through using the digital television program recommending system and the digital television program recommending method, programs preferred by all family members can be calculably recommended.
Description
Technical field
The present invention relates to the digital television techniques field, relate in particular to a kind of digital television program recommending system and method.
Background technology
Along with global various countries DTV is promoted acceleration, top box of digital machine STB (set top box) has entered into increasing family; Top box of digital machine is not only user terminal; Or the network terminal; It can make simulated television turn to interactive digital TV (like video request program etc.) from passive reception simulated television, and can enter the Internet, and makes the user enjoy omnibearing information services such as TV, data, language.STB has wide development space as the significant product of DTV.Along with the development of digital television application, chip technology and software engineering, the function of STB also will be from strength to strength, can carry out more service for operator and user, satisfies the demand of different levels.
Fast development along with digital television techniques; The cable digital TV system can reach the transmission capacity of 500～600 programs under current encoder and modulation classification, in so numerous programs, can't select the problem of their interested content with TV user occurring.For thoroughly solving this TV information " overload " problem; Electronic program guides must have intelligent; It can be according to user's interest, hobby and rule automatically in advance to user's recommending television; Simultaneously it can also adjust the TV programme of being recommended from the variation of motion tracking user interest, and the digital television program recommending system therefore has been born.
Mainly be made up of main control module and controlled module two sub-systems in the existing commending system, main control module mainly contains program system is provided, Content Management System, and formations such as center media service system, controlled module mainly contains some terminals and comes connecting system.There is following shortcoming in said commending system: at first said commending system can only carry out distinctive single program commending to unique user; Secondly, the system design of said commending system is very high for the resource and the environmental quality requirement of network; Once more, conveniently moving property in terminal is good inadequately in the said commending system.Therefore; Be necessary family's program recommendation system of providing a kind of convenience easy-to-use; Through setting up individual digital television-viewing program related data; Convenient individual seeks favorite program, and carries out all favorite program of related data method for digging calculated recommendation through the data to the kinsfolk, makes the program of broadcast more can satisfy everybody demand.
Summary of the invention
The objective of the invention is to overcome the deficiency of prior art; The invention provides the easy-to-use digital television program recommending system and method for a kind of convenience; Data to the kinsfolk carries out all favorite program of related data method for digging calculated recommendation, makes the program of broadcast more can satisfy everybody demand.。
In order to address the above problem; The present invention proposes a kind of digital television program recommending system; Comprise: STBM access control module, UBA user behavior analysis service module, RES recommendation service module and PMS data management module; Said STBM access control module is used for the Bluetooth communication between STB and the mobile device, with the Bluetooth address that obtains as ID; Said UBA user behavior analysis service module obtains to import data into UBA user behavior analysis service module after bluetooth inserts in STBM access control module; UBA user behavior analysis service module upgrades or registered user's data according to ID, and the program of watching with history watched of recording user; The electric program menu that RES recommendation service module passes UBA user behavior analysis service module the data come and DTV contrasts, and finds out the program of in personal information, watching frequency ratio higher, simultaneously data is sent into PMS data management module; PMS data management module is collected the data and the data of UBA user behavior analysis service module and RES recommendation service module; And carry out data mining through K mean cluster method and k nearest neighbor method and handle; Find out recommendation results, send mobile device to through Bluetooth protocol.
Correspondingly, the present invention has also provided a kind of digital television program recommending method based on STB, it is characterized in that, may further comprise the steps: through bluetooth mobile device is inserted in the digital television program recommending system; Read the information that mobile device transmits, upgrade or registered user's data, and recording user is being watched and the historical program of watching; With the electric program menu contrast of DTV, find out the program of in personal information, watching frequency ratio higher; Data and data after collection receives and analyzes are carried out data mining through K mean cluster method and k nearest neighbor method and are handled, and find out recommendation results and send mobile device to through Bluetooth protocol.
The digital television program recommending system and method for the embodiment of the invention; Can set up individual digital television-viewing program related data through said digital television program recommending system; Convenient individual seeks favorite program; And carry out all favorite program of related data method for digging calculated recommendation through data, make the program of broadcast more can satisfy everybody demand the kinsfolk.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art; To do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below; Obviously, the accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills; Under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the structured flowchart of the digital television program recommending system of the embodiment of the invention;
Fig. 2 is the flow chart of the digital television program recommending method of the embodiment of the invention;
Fig. 3-the 4th, the digital television program recommending system principle sketch map of the embodiment of the invention.
Embodiment
To combine the accompanying drawing in the embodiment of the invention below, the technical scheme in the embodiment of the invention is carried out clear, intactly description, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills are not making the every other embodiment that is obtained under the creative work prerequisite, all belong to the scope of the present invention's protection.As stated; The present invention has set up family's program recommendation system that convenience is easy-to-use; Can set up individual digital television-viewing program related data through native system; Convenient individual seeks favorite program, and carries out all favorite program of related data method for digging calculated recommendation through the data to the kinsfolk, makes the program of broadcast more can satisfy everybody demand.
Particularly; With reference to figure 1; The digital television program recommending system of the embodiment of the invention is based on the Bluetooth of mobile phone technology; Comprise STBM (Set Top Box Module) access control module, UBA (User Behavior Analysis) user behavior analysis service module, RES (Recommender System) recommendation service module and PMS (Profile Manager) data management module; Said STBM access control module is used for the Bluetooth communication between STB and the mobile device, with the Bluetooth address that obtains as ID; Said UBA user behavior analysis service module obtains to import data into UBA user behavior analysis service module after bluetooth inserts in STBM access control module; UBA user behavior analysis service module upgrades or registered user's data according to ID, and the program of watching with history watched of recording user; The electric program menu that RES recommendation service module passes UBA user behavior analysis service module the data come and DTV contrasts, and finds out the program of in personal information, watching frequency ratio higher, simultaneously data is sent into PMS data management module; PMS data management module is collected the data and the data of UBA user behavior analysis service module and RES recommendation service module; And carry out data mining through K mean cluster method and k nearest neighbor method and handle; Find out recommendation results, send mobile device to through Bluetooth protocol.
Wherein, STBM AM access module is a STB middleware, and this middleware makes STB to communicate with near bluetooth equipment, and obtains Bluetooth address as unique identification equipment or the user; Obtain bluetooth access back UBA customer analysis service module at STBM and import relevant information into UBA customer analysis service module, said UBA customer analysis service module internal memory includes the N dimensional vector, is used for writing down different types of program; Picture action class; The comedy class, science fiction class, emotion class ...
With reference to figure 2, the present invention has announced a kind of digital television program recommending method simultaneously, may further comprise the steps:
S101: mobile device is inserted in the digital television program recommending system through bluetooth;
S102: read the information that mobile device transmits, upgrade or registered user's data, and recording user is being watched and the historical program of watching;
S103:, find out the program of in personal information, watching frequency ratio higher with the electric program menu contrast of DTV;
S104: collect data and data after receiving and analyzing, carry out data mining through K mean cluster method and k nearest neighbor method and handle, find out recommendation results and send mobile device to through Bluetooth protocol.
Digital television program recommending method of the present invention adopts the recommendation mechanisms of content-based similarity coupling and adopts the recommendation mechanisms of filtering based on cooperation.Content-based recommendation mechanisms is through calculating the similarity between user characteristics vector and the programs feature vector, and then that similarity is high program commending is given the user.When calculating the process of similarity, also must consider the weight of component characteristics in similarity is calculated, content-based recommend method also can adopt the Bayes sorting technique except utilizing above-mentioned similarity matching process.The cooperation strobe utility also recommends this user for the program that has upper frequency in this k neighbour's the TV programme system recommendation through seeking k the neighbour that similar hobby is arranged with the specific user.The key that cooperation is filtered is choosing of neighbour; But choosing of neighbour requires this user to have the rating record of long period; Therefore, for the new registration user, system also must rely on content-based recommendation mechanisms; For the unexpected variation of user interest, cooperation filtered recommendation mechanism also can't be made reaction timely simultaneously.So perfect personal TV program recommendation system must organically combine content-based recommendation mechanisms and the recommendation mechanisms of filtering based on cooperation.In recommendation mechanisms, mainly use improve one's methods K-Means-based clustering algorithm mean cluster method and K-NNK near neighbor method.
The K-means method mainly is to be divided into k type to n object.Wherein, input parameter k is a clusters number, through the iteration of not stopping carrying out cluster, when method converges to given termination condition, with regard to the termination of iterations process, the output result.The method course of work: at first, from n data object, choose at random k object initial cluster center, other objects then are respectively allocated to the most similar (the cluster centre representative) cluster according to them with the similarity (distance) of these cluster centres.Then, calculate the cluster centre (average of all objects in this cluster) of each new cluster that obtains, and constantly repeat this process, till the canonical measure function begins convergence, generally adopt mean square deviation as the canonical measure function.K cluster has following characteristics: each cluster itself is compact as far as possible, separates as far as possible between each cluster.
Above method still has weak point: at first, method is responsive to the input sequence of initial cluster center and sample, different initial cluster centers and different sample input sequences, and the cluster result of generation has a long way to go; Secondly, when utilizing distance between sample to weigh the similarity between data, this method is not suitable for the data set that big value attribute exists; Once more, with the average of all objects of same type data centralization as cluster centre, its effect receives the influence of isolated point very big.
In the present invention,, some improvement are proposed the K-means method to above problem: the one, the data preliminary treatment, the 2nd, initial cluster center is selected, and the 3rd, the selection of cluster seed in the iterative process.
At first sample data is carried out normalization process, so just can prevent the distance between the data left and right sides sample of some big value attribute.Given one group of data set that contains n data, each data contains m attribute, utilizes formula (1), (2) to calculate average, the standard deviation of each attribute respectively, in conjunction with formula (3) every data is carried out standardization.
Secondly; The selection of initial cluster center has very big influence to last cluster effect; Former K-means method is that a picked at random k data are as cluster centre; And if similar of clustering result is similar as far as possible, different as far as possible between inhomogeneity, so choosing of initial cluster center will be accomplished this point as far as possible.Conventional method adopt based on distance and isolated point define the screening in advance of carrying out isolated point; And utilize in twos the ultimate range between the data in the remaining data set, to seek initial cluster center; For real data; The isolated point number is often unpredictable, if the isolated point number of forcing sieve to fall to estimate possibly have certain influence to cluster result.When selecting initial cluster center; Earlier include isolated point in scope of statistics; Calculating object distance between any two in sample; Then from remaining sample object, finding out all distances of clustering centers of having elected was another cluster centre with maximum point, up to selecting k cluster centre as two inhomogeneous cluster centres in two o'clock that select the distance maximum.Do like this and just reduced the influence that the sample input sequence is selected initial cluster center.After cluster centre is chosen, will carry out continuous iterative computation, in the K-means method; It is the cluster calculation of cluster average point (geometric center point of all data in type) being carried out a new round as new cluster seed; In this case, new cluster seed possibly depart from real data-intensive district, thereby causes deviation; Particularly under the situation that has isolated point to exist, significant limitation is arranged.When selecting initial center point, because isolated point is counted, so in iterative process, will avoid the influence of isolated point.Here select the cluster seed of a new round according to the cluster seed similarity.When carrying out the calculating of k wheel cluster seed; Those take turns the bigger data of cluster seed similarity with k-1 in adopting bunch; Calculate the seed of their average o'clock as k wheel cluster; Be equivalent to isolated point is foreclosed, isolated point is not participated in the calculating of cluster centre, and cluster centre just can be because of the concentrated place of the former thereby obvious bias data of isolated point like this.When calculating cluster centre, use certain method that isolated point is got rid of outside those data of computation of mean values point.Here with the sub-set of cluster seed similarity greater than each type of data composition of a certain threshold value, the average point in the subset of computations is as the cluster seed of next round cluster in the main employing class.Go in order to let more data participate in the calculating of cluster centre, threshold range will comprise most data.Class in the acquisition of k-1 wheel cluster; Calculate the average distance S of all data and such cluster centre in such; Form the sub-set of each type with the cluster seed similarity greater than the data of 2S in selecting type, take turns the cluster seed of cluster with the average point of this subclass as k.Whether no matter have tangible isolated point to exist in data centralization, the average distance of twice can both comprise most data.
The basic thought of k-NN method is: when the query text that remains to be classified arrives; In training set, find a most approaching with it k training text according to the Euclidean distance formula; And then the method through " majority voting "; In this k training text, the text categories that occupies the majority decides the classification of query text.Adopt the programs recommended system interaction of k-NN method as shown in Figure 3.
For a specific program, its characteristic file is made up of following key element: channel, program the 1st and the 2nd grade of classification, performer or host's information, director or producer's information, programme content brief introduction, program stage photo or film clips etc. that time that programm name, program broadcast and duration, program broadcast.In schedule programs characteristic file process; We are divided into two kinds of multidate information and static informations with it again; Multidate information mainly refers to the title and the broadcast time of each channel program, other corresponding information of the main dactylus order of static information, and adopt the XML form that program characteristics is defined.
On DVB classification and country classification standard; In conjunction with actual situation of China; The present invention adjusts program classification; Film, TV play, news, finance and economics, entertainment, physical fitness, opera, juvenile, science and education, animation, documentary film, travel life, interview, military affairs, legal system, 16 1 grade of classifications of special topic and 124 2 grades of classifications have been defined.For example 2 of TV play grades of classifications have Hong Kong and Taiwan, Japan and Korea S, foreign country, political subject matter, historical subject matter, city life emotion subject matter, the case-involving subject matter of public security organs, rural area subject matter, juvenile's subject matter, army life's subject matter, imperial palace to joke with 15 of subject matter, the mythical subject matter of swordsman, indoor sitcom, video art sheet and cartoons.
Therefore according to standard, the N dimensional vector of UBA user behavior analysis service module has also just been confirmed so, and this just makes things convenient for us to carry out the internal memory design planning.
The situation sketch map that returns client's mobile phone end for the data after analyzing is as shown in Figure 4.Said system can realize the demonstration and the inquiry of whole channels broadcast items in one week; The current period that meets user watched demand and the program commending of whole day period can be provided according to the rating characteristic that user registration provides; The whole day period meets the program of user preferences, also through the More button TOP50 is provided except providing TOP20 to be 20 at the recommendation page most; In addition, system can provide the user feedback mechanism to recommendation results, system design enjoy a lot, like, generally like, dislike and dislike very much 5 grades of feedback mechanisms.
The advantage of the digital television program recommending system of the embodiment of the invention comprises:
1) through general general Bluetooth technology and light and handy portable terminal easily, convenient for users, bring different service experience to the user;
2) realized many people are watched the suggested design of TV, popular hobby program is provided, helped to reach the result that the public watches the more satisfied harmony of TV through information excavating.
3) realized application, for other designers and client bring new intention to the small-sized convenient network that is free of charge.
Compared with prior art; The digital television program recommending system of embodiment of the present invention embodiment; Can realize the looking of CATV set-top-box, audio-frequency index parameter are tested automatically and assessed; Be converted into machine to behavioral test and carry out, save manpower, time and hardware resource greatly, improved testing efficiency with artificial driving.
More than the digital television program recommending system and method that the embodiment of the invention provided is described in detail; Used specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, the part that all can change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (2)
1. the digital television program recommending system based on STB is characterized in that, comprises being arranged in the STB
STBM access control module is used for the Bluetooth communication between STB and the mobile device, with the Bluetooth address that obtains as ID;
UBA user behavior analysis service module; Obtain to import data into UBA user behavior analysis service module after bluetooth inserts in STBM access control module; UBA user behavior analysis service module upgrades or registered user's data according to ID, and the program of watching with history watched of recording user;
RES recommendation service module, the electric program menu that UBA user behavior analysis service module is passed the data come and DTV contrasts, and finds out the program of in personal information, watching frequency ratio higher, simultaneously data is sent into PMS data management module;
PMS data management module; Collect the data and the data of UBA user behavior analysis service module and RES recommendation service module; And carry out data mining through K mean cluster method and k nearest neighbor method and handle, find out recommendation results, send mobile device to through Bluetooth protocol.
2. the digital television program recommending method based on STB is characterized in that, may further comprise the steps:
Through bluetooth mobile device is inserted in the digital television program recommending system;
Read the information that mobile device transmits, upgrade or registered user's data, and recording user is being watched and the historical program of watching;
With the electric program menu contrast of DTV, find out the program of in personal information, watching frequency ratio higher;
Data and data after collection receives and analyzes are carried out data mining through K mean cluster method and k nearest neighbor method and are handled, and find out recommendation results and send mobile device to through Bluetooth protocol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100505878A CN102572543A (en) | 2012-02-29 | 2012-02-29 | Digital television program recommending system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100505878A CN102572543A (en) | 2012-02-29 | 2012-02-29 | Digital television program recommending system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102572543A true CN102572543A (en) | 2012-07-11 |
Family
ID=46416814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012100505878A Pending CN102572543A (en) | 2012-02-29 | 2012-02-29 | Digital television program recommending system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102572543A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458275A (en) * | 2013-09-02 | 2013-12-18 | 深圳市茁壮网络股份有限公司 | Real-time interaction digital television information recommendation system and method |
| WO2014180224A1 (en) * | 2013-11-21 | 2014-11-13 | 中兴通讯股份有限公司 | Method and device for service recommendation |
| CN105163182A (en) * | 2015-08-24 | 2015-12-16 | Tcl集团股份有限公司 | Smart TV user behavior obtaining method and system based on exceptional mining algorithm |
| CN105681835A (en) * | 2016-02-26 | 2016-06-15 | 腾讯科技（深圳）有限公司 | Information pushing method and server |
| CN105744302A (en) * | 2016-01-29 | 2016-07-06 | 四川长虹电器股份有限公司 | Method and system for collecting television user information based on Bluetooth peripheral |
| CN106331109A (en) * | 2016-08-26 | 2017-01-11 | 天津通信广播集团有限公司 | Method for realizing intelligent recommendation system of visual information in digital television |
| CN106658078A (en) * | 2016-12-23 | 2017-05-10 | 北京小米移动软件有限公司 | Ordering method and device through television terminal |
| CN108810655A (en) * | 2018-06-29 | 2018-11-13 | 北京比利信息技术有限公司 | The implementation method of real-time recommendation scheme is broadcast live in IP-based |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101682733A (en) * | 2007-05-31 | 2010-03-24 | 索尼爱立信移动通讯有限公司 | System and method for personalized television viewing triggered by a portable communication device |
| CN101951481A (en) * | 2009-07-09 | 2011-01-19 | 索尼公司 | TV programme selective system, recommend method and method for recording |
| CN102184235A (en) * | 2011-05-13 | 2011-09-14 | 广州星海传媒有限公司 | Set top box-based digital television program recommending method and system |
-
2012
- 2012-02-29 CN CN2012100505878A patent/CN102572543A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101682733A (en) * | 2007-05-31 | 2010-03-24 | 索尼爱立信移动通讯有限公司 | System and method for personalized television viewing triggered by a portable communication device |
| CN101951481A (en) * | 2009-07-09 | 2011-01-19 | 索尼公司 | TV programme selective system, recommend method and method for recording |
| CN102184235A (en) * | 2011-05-13 | 2011-09-14 | 广州星海传媒有限公司 | Set top box-based digital television program recommending method and system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458275A (en) * | 2013-09-02 | 2013-12-18 | 深圳市茁壮网络股份有限公司 | Real-time interaction digital television information recommendation system and method |
| WO2014180224A1 (en) * | 2013-11-21 | 2014-11-13 | 中兴通讯股份有限公司 | Method and device for service recommendation |
| CN105163182A (en) * | 2015-08-24 | 2015-12-16 | Tcl集团股份有限公司 | Smart TV user behavior obtaining method and system based on exceptional mining algorithm |
| CN105163182B (en) * | 2015-08-24 | 2019-06-11 | Tcl集团股份有限公司 | Smart television user behavior acquisition methods and system based on exception mining algorithm |
| CN105744302A (en) * | 2016-01-29 | 2016-07-06 | 四川长虹电器股份有限公司 | Method and system for collecting television user information based on Bluetooth peripheral |
| CN105681835A (en) * | 2016-02-26 | 2016-06-15 | 腾讯科技（深圳）有限公司 | Information pushing method and server |
| CN105681835B (en) * | 2016-02-26 | 2019-11-19 | 腾讯科技（深圳）有限公司 | A kind of method and server of information push |
| CN106331109A (en) * | 2016-08-26 | 2017-01-11 | 天津通信广播集团有限公司 | Method for realizing intelligent recommendation system of visual information in digital television |
| CN106658078A (en) * | 2016-12-23 | 2017-05-10 | 北京小米移动软件有限公司 | Ordering method and device through television terminal |
| CN108810655A (en) * | 2018-06-29 | 2018-11-13 | 北京比利信息技术有限公司 | The implementation method of real-time recommendation scheme is broadcast live in IP-based |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102572543A (en) | Digital television program recommending system and method thereof | |
| CN110574387B (en) | Recommending live streaming content using machine learning | |
| CN104182449B (en) | Individualized video commending system and method based on user interest modeling | |
| CN101047826B (en) | Electronic apparatus, information browsing method thereof | |
| CN108737856B (en) | Social relation perception IPTV user behavior modeling and program recommendation method | |
| US20170188102A1 (en) | Method and electronic device for video content recommendation | |
| CN101888527B (en) | A method of recommending local and remote content | |
| CN102184235A (en) | Set top box-based digital television program recommending method and system | |
| CN103533393B (en) | The family's analysis noted down based on home audience and program commending method | |
| CN110430471A (en) | It is a kind of based on the television recommendations method and system instantaneously calculated | |
| CN105975472A (en) | Method and device for recommendation | |
| CN101383942B (en) | Hidden customer characteristic extracting method and television program recommendation method and system | |
| CN106407418A (en) | A face identification-based personalized video recommendation method and recommendation system | |
| CN109429103B (en) | Method and device for recommending information, computer readable storage medium and terminal equipment | |
| CN102523511A (en) | Network program aggregation and recommendation system and network program aggregation and recommendation method | |
| CN103139616A (en) | Personalization cloud recommendation method and system based on multi-user digital television program | |
| US20070288965A1 (en) | Recommended program information providing method and apparatus | |
| CN103052954A (en) | Profile based content retrieval for recommender systems | |
| CN101431694B (en) | Digital television program recommending method and system based on Bayesian algorithm | |
| CN101482884A (en) | Cooperation recommending system based on user predilection grade distribution | |
| CN103686403A (en) | Television desktop display method and device | |
| CN111767430B (en) | Video resource pushing method, video resource pushing device and storage medium | |
| CN111062527B (en) | Video traffic collection prediction method and device | |
| CN104639957A (en) | Mobile multimedia terminal, video program recommendation method and server | |
| CN105376649A (en) | Set top box blind operation method and system for realizing accurate combination recommendation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120711 |