CN103491441A - Recommendation method and system of live television programs - Google Patents
Recommendation method and system of live television programs Download PDFInfo
- Publication number
- CN103491441A CN103491441A CN201310407292.6A CN201310407292A CN103491441A CN 103491441 A CN103491441 A CN 103491441A CN 201310407292 A CN201310407292 A CN 201310407292A CN 103491441 A CN103491441 A CN 103491441A
- Authority
- CN
- China
- Prior art keywords
- program
- user
- record
- watching
- television
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005516 engineering process Methods 0.000 claims description 9
- 230000006399 behavior Effects 0.000 description 10
- 238000001914 filtration Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
Images
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a recommendation method and system of live television programs. The recommendation method of the live television programs comprises the steps of (1) obtaining a program watching record, on a program menu, of a user according to a historical watching record of the user and the program menu of channels which are fetched by the user, (2) obtaining program metadata according to the program watching record, on the program menu, of the user, (3) obtaining a television program preference record of the user according to the historical watching record of the user and the program metadata, (4) selecting the program menu according to moving sliding windows, obtaining the preference degree of the user to each program according to the program menu and the television program preference record of the user, (5) selecting a neighbor user who has the similar interests as the user according to the moving sliding windows to obtain a statistical record of the situation that television programs are watched in the time periods corresponding to the moving sliding windows, and (6) recommending the television programs in the time periods corresponding to the moving sliding windows to the user according to the statistical record and the preference degree of the user to each program on the program menu. When the recommendation method and system of the live television programs are used, the purpose of accurate recommendation of the television programs can be achieved.
Description
Technical Field
The invention relates to the technical field of digital television program recommendation, in particular to a live television program recommendation method and system.
Background
At present, products such as smart televisions, set-top boxes, online video websites and the like which provide video content to users are very popular, and there are many recommendation solutions for multimedia videos, such as the existing television program recommendation flow diagram shown in fig. 1.
As shown in fig. 1, in the television program recommendation process, a group of users having the same interest as that of the target user is found by using a collaborative filtering algorithm, and programs that are all liked by the users are found from the group of users and then pushed to the target user.
In the prior art, similar algorithms are often effective for Video On Demand (vod) because vod does not have strong timeliness. However, for the recommendation of live broadcast content, the recommendation process described above causes great deviation in the accuracy of the recommendation result, and the deviation is mainly caused by the following three factors:
firstly, the method comprises the following steps: deviation in user interest points.
In the process of acquiring the watching record of the user, since the video-on-demand content is fixed, the record information of the watching program of the user can be directly acquired, but in the live channel, the traditional method can only acquire the channel information (such as CCTV 5) watched by the user, and cannot acquire the specific content information (such as basketball game) watched by the user. This can lead to relatively large errors in subsequent discovery of the user's points of interest. Current recommendation algorithms are mainly classified into two categories:
a) one method is to recommend based on the content, namely, according to the metadata information of the video, a text mining method is used to find a video set containing metadata information similar to the video set for recommendation. This approach is effective for video-on-demand (e.g., you are using it), but is not very useful for live channels because the metadata information of live channels is actually a whole introduction of the channel (e.g., CCTV5 is a sports table) and often does not contain specific content information, which makes the metadata information very general and the recommended video content very inaccurate.
b) The other is to make recommendations based on user behavior data, such as a collaborative filtering algorithm, making recommendations using co-browsing behaviors found in a group of users who have the same browsing preferences as the target user. This approach is often only suitable for on-demand content, since for live channel content, both people prefer CCTV5 (sports table) very well even though they are likely to prefer basketball to football, since the content is changing.
Secondly, the method comprises the following steps: deviation of channel content change.
Since the video-on-demand content is fixed, the user can directly click and watch the recommended video set, so that the recommendation algorithm does not need to consider the problem of content change, but for live content, since the content is changed, if the recommendation algorithm does not consider the time dimension, it is highly likely that the recommended content cannot be directly watched by the user (for example, a football game is played on a live channel when a basketball game in a recommended channel).
Thirdly, the method comprises the following steps: deviation of the playing time.
On-demand content often does not have high timeliness and timeliness requirements, a user can click and watch recommended content at any time, but the recommended content of a live channel is likely to be played within a certain time period in the future, and if the time interval is long, the user may lose patience and abandon watching, so that the recommendation effect is reduced.
In addition, in the recommendation process of the on-demand video, since the content of each video is fixed and can be repeatedly played again, a user or an administrator can directly add specific metadata information (such as a title, a content introduction and the like) to the video content, but in the live video, the content covered by the content of each channel is very wide (such as CCTV5 contains a plurality of sports programs such as basketball and swimming) and can change with time (such as 1 playing basketball games on demand and 2 playing football games on demand), so that the administrator needs to continuously modify the content metadata information of the video to perfect the information required by the recommendation.
In order to solve the above problems, it is necessary to provide a method for effectively recommending live channel programs in real time, so as to increase the accuracy of recommendation results and improve user experience.
Disclosure of Invention
In view of the foregoing problems, an object of the present invention is to provide a live tv program recommendation method and system, so as to solve the problem of program recommendation accuracy.
The live television program recommendation method provided by the invention comprises the following steps:
acquiring a program viewing record of a user in a program list according to the user historical viewing record and the program list of the crawled channel;
acquiring program metadata according to a program watching record of a user in a program list;
acquiring a favorite record of a user television program according to the historical watching record of the user and the program metadata;
selecting a program form according to the mobile sliding window and acquiring the preference degree of each program of the user according to the program form and the preference record of the television program of the user; and,
selecting neighbor users similar to the user interests according to the mobile sliding window so as to obtain the watched statistical record of the television programs in the time period corresponding to the mobile sliding window;
and recommending the television programs in the time period corresponding to the mobile sliding window to the user according to the statistical record and the preference degree of the user to each program in the program list.
In addition, the preferred scheme is that the user channel watching record in a period of user history is inquired from the user watching behavior database according to the user ID to obtain the user history watching record, wherein the user channel watching record in the period of user history comprises the watched channel information, the watching starting time and the watching ending time; wherein,
in the process of obtaining the program watching records of the user, matching the historical watching records of the user with the program forms of the crawled channels, and converting the watching records of the channels of the user into percentage records of the programs watched by the user.
In addition, the preferred scheme is that the program content played by the television channel is acquired from the internet website by using a web crawler technology to acquire a program list of the crawled channel; the program list includes program titles, program actors, program profiles, playing time periods of the programs, and channels on which the programs are played.
In addition, in the preferred scheme, in the process of acquiring the favorite record of the television program of the user, according to the program watching time length in a period of user history, the total time length of the watched programs is counted by combining the metadata of the corresponding program list, and the favorite degree of the user on the programs is determined according to the total time length.
In addition, in the process of selecting a program form according to the mobile sliding window, a program information list which is currently played or is about to be played in a preset future time interval from the current time is selected in a time period corresponding to the mobile sliding window, wherein the program information list comprises the program metadata.
In addition, preferably, in the process of selecting the neighbor users with similar interests to the user according to the mobile sliding window, a user group with viewing records in a preset past time interval from the selection to the current time in the time period corresponding to the mobile sliding window, and the N users with the most similar interests are determined as the neighbor users with similar interests to the user according to the preference records of the user group and the preference records of the users.
In addition, it is preferable that, in the process of recommending the television programs in the time period corresponding to the moving sliding window to the user according to the statistical record and the user's preference degree for each program in the program list,
performing reverse sequencing on the statistical records to obtain a recommendation sequence of the television programs in a time period corresponding to the mobile sliding window recommended to the user; and,
and recommending the television programs to the user when the preference degree of the user to the television programs in the recommendation sequence exceeds a preset threshold value.
In addition, it is preferable that, when each viewing behavior of the user is finished, a user channel viewing record is added to the user viewing behavior database to update the user viewing record; wherein the user channel viewing record includes a user ID, viewing channel information, a viewing start time, and a viewing end time.
On the other hand, the invention also provides a live television program recommendation system, which comprises:
the program watching record obtaining unit is used for obtaining the program watching record of the user in the program list according to the historical watching record of the user and the program list of the crawled channel;
the program metadata acquisition unit is used for acquiring program metadata according to program watching records of a user in a program list;
the favorite record acquisition unit is used for acquiring the favorite record of the television program of the user according to the historical watching record of the user and the program metadata;
the recommendation basis acquisition unit is used for selecting the program list according to the mobile sliding window and acquiring the preference degree of each program in the program list by the user according to the program list and the preference record of the television programs of the user; selecting neighbor users similar to the user interests according to the mobile sliding window so as to obtain the statistical record of the watched television programs in the time period corresponding to the mobile sliding window;
and the program recommending unit is used for recommending the television programs in the time period corresponding to the mobile sliding window to the user according to the statistical record and the preference degree of the user to each program in the program list.
In addition, it is preferable that, in the recommendation basis acquiring unit, a program information list that is currently played or is to be played in a preset future time interval from the current time is selected in a time period corresponding to the moving sliding window, where the program information list includes program metadata.
According to the technical scheme, the live television program recommendation method and system provided by the invention can obtain the following beneficial effects:
1) metadata of the television program is automatically acquired through a web crawler technology, so that the burden of managers and users on manually editing the metadata of the television program can be reduced;
2) by combining behavior data of a user watching a channel and metadata of a channel program, counting and converting the watching time of the user to the program, and more accurately acquiring the interest point of the user;
3) by the mobile sliding window technology, the program list information which is being played and is to be played in a certain time period is selected to be matched with the preference of the user, so that the effect of reminding the user of the program in advance can be achieved, and the user is prevented from missing the probably preferred program;
4) the conventional collaborative filtering method is improved, the time dimension is added, and when similar neighbors of a user are obtained, only the user in a moving sliding window time period is considered, so that a recommendation result can be focused on a hot program which is currently played, and the problem that the recommendation result cannot be viewed can be avoided;
5) the threshold value is used for controlling the showing times of the recommendation result, so that the accuracy of the recommendation result can be improved.
To the accomplishment of the foregoing and related ends, one or more aspects of the invention comprise the features hereinafter fully described and particularly pointed out in the claims. The following description and the annexed drawings set forth in detail certain illustrative aspects of the invention. These aspects are indicative, however, of but a few of the various ways in which the principles of the invention may be employed. Further, the present invention is intended to include all such aspects and their equivalents.
Drawings
Other objects and results of the present invention will become more apparent and more readily appreciated as the same becomes better understood by reference to the following description and appended claims, taken in conjunction with the accompanying drawings. In the drawings:
FIG. 1 is a flow chart of a prior art television program recommendation method;
fig. 2 is a flowchart of a live tv program recommendation method according to an embodiment of the present invention;
fig. 3 is a flow chart of a live tv program recommendation method according to an embodiment of the present invention;
fig. 4 is a block diagram of a live tv program recommendation system according to an embodiment of the present invention.
The same reference numbers in all figures indicate similar or corresponding features or functions.
Detailed Description
In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident, however, that such embodiment(s) may be practiced without these specific details. Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Fig. 2 is a flowchart of a live tv program recommendation method according to an embodiment of the present invention.
As shown in fig. 2, the live tv program recommendation method provided by the present invention includes the following steps:
s201: acquiring a program viewing record of a user in a program list according to the user historical viewing record and the program list of the crawled channel;
s202: acquiring program metadata according to a program watching record of a user in a program list;
s203: acquiring a favorite record of a user television program according to the historical watching record of the user and the program metadata;
s204: selecting a program form according to the mobile sliding window and acquiring the preference degree of each user program of the user according to the program form and the preference record of the television program of the user; selecting neighbor users similar to the user interests according to the mobile sliding window so as to obtain the watched statistical record of the television programs in the time period corresponding to the mobile sliding window;
s205: and recommending the television programs in the time period corresponding to the mobile sliding window to the user according to the statistical record and the preference degree of the user to each program in the program list.
Fig. 3 is a flowchart of a live tv program recommendation method according to an embodiment of the present invention.
As shown in fig. 3, a specific flow of the live tv program recommendation method includes:
s1: carrying out personalized recommendation on live television programs in time;
s2: the user opens the television to watch the program;
s3: updating the watching records of the user; specifically, adding a user watching channel record into a user watching behavior database;
s4: a user channel viewing record; the information to be recorded includes user ID, channel information of viewing (such as CCTV 5), start time of viewing and end time of viewing (changing channels or turning off the television);
s5: acquiring a historical watching record of a user; specifically, according to the user ID, the user viewing behavior database is queried for the user channel viewing record in a period of time of the user history, including the viewing channel information (such as CCTV 5), the viewing start time, and the viewing end time (changing or turning off the television);
s6: inquiring internet information;
s7: a program list of the crawled channels; the specific method comprises the steps of acquiring program contents played by a television channel from an internet website by using a web crawler technology, wherein the program contents comprise program titles, program actors, program profiles, playing time periods (starting and ending times) of the programs and channels (such as CCTV 5) played by the programs;
s8: channel program playing information;
s9: acquiring the user program watching record means that the user program watching record is matched with a program form of a crawled channel by using the user historical watching record, and the starting time and the ending time of the user channel watching and the starting time and the ending time of the program playing in the channel are mainly used, so that the step S4 of converting the user watching channel record into the percentage record of the user watching program.
The specific method comprises the following steps: assuming that the viewing start time of user a is T1, the end time is T2, the start time of program B is T3, and the end time is T4, the percentage of user a viewing program B is:
s10: channel program profile information;
s11: acquiring program metadata; acquiring program metadata through step S9 and step S10, the metadata including information of title, category, actors, director, moderator, brief introduction, etc. of the program video;
s12: acquiring favorite records of a user television program; specifically, according to the program watching time length of a user within a period of historical time, combining metadata of corresponding programs, counting information such as the total time length of watched programs, the total time length of a certain category, the total time length of a certain actor and the like, and assuming that the time length is in direct proportion to the favorite time length of the user, so that the favorite time length of the user on the programs is converted;
s13: selecting a program list according to the mobile sliding bed; specifically, the method refers to a program information list that is currently played or is about to be played in a preset future time interval (for example, 1 hour) from the current time in the selection of a time period corresponding to the mobile sliding window, where the program information includes the above-mentioned program metadata (such as title, category, actors, director, presenter, brief introduction, etc.);
s14: acquiring the preference degree of a user for each program; matching favorite records of a television program with program metadata by a user, counting the overall favorite degree of the user on the program, wherein the overall favorite degree is the sum of favorite elements of all elements, and inversely sorting;
for example: program preference = W1 × actor preference + W2 × category preference + W3 × director preference, W1, W2, W3 being the weight of each element;
s15: selecting neighbor users similar to the user interests according to the mobile sliding window; specifically, the method includes the steps that a user group with watching records in a preset past time interval (for example, 1 hour) from selection to the current time in a time period corresponding to a mobile sliding window is selected, matching is conducted according to favorite records of the user group and favorite records of users, and N users with the most similar interests are selected as neighbor users with similar interests to the users;
s16: acquiring users watching television programs and reversely ordering the users; counting the number of watched people of the program by using the watching records of the neighbor user group selected by the mobile sliding window in the mobile sliding window time period, and performing reverse sequencing according to the counting records;
s17: judging whether the preference degree of the television program exceeds a threshold value or not; judging according to the preference degree of a user to programs and the watched times of the television programs, and displaying a recommended result to the user only when the recommended result exceeds a threshold value in order to avoid a recommendation system from excessively disturbing the video programs watched by the user currently; therefore, if yes, go to step S18; if not, go to step S12;
s18: and displaying the recommended content.
In step S7, metadata of the tv program is automatically acquired by web crawler technology, so that the burden of the administrator and the user to edit the video metadata manually can be reduced.
In the above step S12, by combining the behavior data of the user viewing the channel and the metadata of the channel program, the statistics are converted into the viewing duration of the program by the user, so as to more accurately obtain the interest point of the user.
In steps S13 and S14, the information of the program list being played and about to be played in a certain time period is selected to match with the user' S preference by the moving sliding window technique, so as to remind the user of the program in advance to avoid the user missing a possibly favorite program.
In step S15 and step S16, the existing collaborative filtering method is improved, a time dimension is added, and when a similar neighbor of a user is obtained, only the user in a moving sliding window time period is considered, so that a recommendation result can be focused on a hot spot program currently being played, and a problem that the recommendation result cannot be viewed can be avoided.
In step S14 and step S16, the preference degrees of the programs and the statistical records of the watched tv programs are inversely sorted, and this inversely sorting manner is only a specific implementation manner of managing the statistical records.
In other specific implementation processes of the invention, the preference degree and the statistical records can be sorted, or the statistical records can be directly traversed without sorting; the sorting may be forward sorting or reverse sorting.
In step S17, the accuracy of the recommendation result can be improved by controlling the number of times the recommendation result is presented using the threshold.
The steps are specific flows of live television program recommendation methods, and the invention also provides a live television program recommendation system corresponding to the live television program recommendation method. Fig. 4 is a block diagram of a live tv program recommendation system according to an embodiment of the present invention.
As shown in fig. 4, the live tv program recommendation system 400 provided by the present invention includes a program viewing record obtaining unit 410, a program metadata obtaining unit 420, a favorite record obtaining unit 430, a recommendation basis obtaining unit 440, and a program recommendation unit 450.
The program viewing record obtaining unit 410 is configured to obtain a program viewing record of a user in a program form according to a user history viewing record and a program form of a crawled channel;
a program metadata obtaining unit 420, configured to obtain program metadata according to the program viewing record in the program list of the user, which is obtained by the program viewing record obtaining unit 410;
a preference record acquiring unit 430, configured to acquire a preference record of a television program of a user according to a user history viewing record and the program metadata acquired by the program metadata acquiring unit 200;
a recommendation basis acquiring unit 440, configured to select a program form according to the mobile sliding window and acquire a user preference degree for each program in the program form according to the program form and the user television program preference record; selecting neighbor users similar to the user interests according to the mobile sliding window so as to obtain the watched statistical record of the television programs in the time period corresponding to the mobile sliding window;
the program recommending unit 450 is configured to recommend, to the user, the television program in the time period corresponding to the moving sliding window according to the statistical record and the user's preference degree for each program in the program list.
The user history watching record is a user channel watching record in a period of user history queried from a watching behavior database according to the user ID; the user channel viewing record includes channel information of viewing (e.g., CCTV 5), start time of viewing, and end time of viewing (zapping or turning off the television). The program form of the crawled channel is the program content played by the television channel acquired from the internet website by using the web crawler technology, wherein the program form comprises program titles, program actors, program introduction, the playing time periods of the programs and the channels played by the programs.
In the program viewing record obtaining unit 410, the user history viewing record unit and the crawled channel program list obtaining unit are used for matching, and according to the starting and ending time of the user viewing channel and the starting and ending time of the program playing in the channel, the user channel viewing record is converted into the percentage record of the user viewing the program.
In the recommendation basis acquiring unit 440, a program information list that is currently played or is about to be played in a preset future time interval from the current time is selected from the time period corresponding to the moving sliding window, wherein the program information list includes program metadata.
According to the live television program recommendation method and system provided by the invention, the existing collaborative filtering method is improved through the web crawler technology and the mobile sliding window technology, the time dimension is added, and the display times of the recommendation result are controlled by using the threshold value, so that the accuracy of the real-time recommendation result of the live television program is effectively improved.
The live television program recommendation method and system proposed in accordance with the present invention are described above by way of example with reference to the accompanying drawings. However, it should be understood by those skilled in the art that various modifications can be made to the live tv program recommendation method and system provided by the present invention without departing from the scope of the present invention. Therefore, the scope of the present invention should be determined by the contents of the appended claims.
Claims (10)
1. A live television program recommendation method comprises the following steps:
acquiring a program viewing record of a user in a program list according to a user history viewing record and the program list of a crawled channel;
acquiring program metadata according to a program watching record of a user in the program list;
acquiring a favorite record of a user television program according to the historical watching record of the user and the program metadata;
selecting a program form according to the mobile sliding window and acquiring the preference degree of each program in the program form by the user according to the program form and the preference record of the television program of the user; selecting neighbor users similar to the user interests according to the mobile sliding window so as to obtain a statistical record of watching television programs in a time period corresponding to the mobile sliding window;
and recommending the television programs in the time period corresponding to the mobile sliding window to the user according to the statistical record and the preference degree of the user to each program in the program list.
2. The live television program recommendation method of claim 1,
inquiring a user channel watching record in a user history within a period of time from the user watching behavior database according to the user ID to obtain the user history watching record, wherein the user channel watching record in the user history within the period of time comprises watched channel information, watching starting time and watching ending time; wherein,
and in the process of obtaining the program watching records of the user, matching the historical watching records of the user with the program form of the crawled channel, and converting the watching records of the user channel into percentage records of the programs watched by the user.
3. The live television program recommendation method of claim 1,
acquiring program content played by a television channel from an internet website by utilizing a web crawler technology to acquire a program list of the crawled channel; wherein,
the program form includes program titles, program actors, program summaries, broadcast time periods for the programs, and channels on which the programs are broadcast.
4. The live television program recommendation method of claim 1,
in the process of obtaining the favorite record of the television program of the user, according to the program watching time length in a period of user history, combining the metadata of the corresponding program list, counting the total time length of the watched program, and determining the favorite degree of the user to the program according to the total time length.
5. The live television program recommendation method of claim 1,
in the process of selecting the program list according to the mobile sliding window, selecting a program information list which is playing or is about to be played in a preset future time interval from the current time within the time period corresponding to the mobile sliding window, wherein the program information list comprises the program metadata.
6. The live television program recommendation method of claim 1,
in the process of selecting the neighbor users with similar interests to the users according to the mobile sliding window, selecting a user group with viewing records in a preset past time interval from the time period corresponding to the mobile sliding window to the current time, and determining N users with the most similar interests as the neighbor users with similar interests to the users according to the favorite records of the user group and the favorite records of the users.
7. The live television program recommendation method of claim 1,
in the process of recommending the television programs in the time period corresponding to the mobile sliding window to the user according to the statistical record and the user's preference degree for each program in the program list,
reversely ordering the statistical records to obtain a recommendation sequence of the television programs in the time period corresponding to the mobile sliding window recommended to the user; and,
and recommending the television programs to the user when the preference degree of the user to the television programs in the recommendation sequence exceeds a preset threshold value.
8. The live television program recommendation method of claim 1, further comprising,
when each watching behavior of the user is finished, adding a user channel watching record into the user watching behavior database to update the user watching record; wherein,
the user channel viewing record includes a user ID, viewed channel information, a start time of viewing, and an end time of viewing.
9. A live television program recommendation system comprising:
the program watching record acquiring unit is used for acquiring the program watching record of the user in the program list according to the historical watching record of the user and the program list of the crawled channel;
the program metadata acquisition unit is used for acquiring program metadata according to the program watching record of the user in the program list;
a favorite record acquiring unit, configured to acquire a favorite record of a user television program according to the user history viewing record and the program metadata;
the recommendation basis acquisition unit is used for selecting a program list according to the mobile sliding window and acquiring the preference degree of each program in the program list by the user according to the program list and the preference record of the television programs of the user; selecting neighbor users similar to the user interests according to the mobile sliding window so as to obtain a statistical record of watching television programs in a time period corresponding to the mobile sliding window;
and the program recommending unit is used for recommending the television programs in the time period corresponding to the mobile sliding window to the user according to the statistical record and the like degree of the user to each program in the program list.
10. The live television program recommendation system of claim 9,
and in the recommendation basis acquiring unit, selecting a program information list which is being played or is about to be played in a preset future time interval from the current time in a time period corresponding to the mobile sliding window, wherein the program information list comprises the program metadata.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310407292.6A CN103491441B (en) | 2013-09-09 | 2013-09-09 | Recommendation method and system of live television programs |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310407292.6A CN103491441B (en) | 2013-09-09 | 2013-09-09 | Recommendation method and system of live television programs |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103491441A true CN103491441A (en) | 2014-01-01 |
CN103491441B CN103491441B (en) | 2017-02-01 |
Family
ID=49831352
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310407292.6A Active CN103491441B (en) | 2013-09-09 | 2013-09-09 | Recommendation method and system of live television programs |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103491441B (en) |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945241A (en) * | 2014-05-12 | 2014-07-23 | 腾讯科技(深圳)有限公司 | Streaming data statistical method, system and related device |
CN103995875A (en) * | 2014-05-23 | 2014-08-20 | 百度在线网络技术(北京)有限公司 | Information recommendation method and device |
CN104038790A (en) * | 2014-06-30 | 2014-09-10 | 北京奇艺世纪科技有限公司 | Video playing list updating method and system |
CN104780463A (en) * | 2015-04-15 | 2015-07-15 | 天脉聚源(北京)传媒科技有限公司 | Display method and device of program menu |
CN104780464A (en) * | 2015-04-22 | 2015-07-15 | 天脉聚源(北京)传媒科技有限公司 | Method and device for generating three-dimensional menu |
CN104935968A (en) * | 2015-06-25 | 2015-09-23 | 广州视源电子科技股份有限公司 | Method and system for recommending programs by network television |
CN105245958A (en) * | 2015-11-11 | 2016-01-13 | Tcl集团股份有限公司 | Live television program recommendation method and device |
CN106028070A (en) * | 2016-05-16 | 2016-10-12 | 乐视控股(北京)有限公司 | Live broadcast or carousel channel recommending method and device and video server |
CN106060590A (en) * | 2016-07-07 | 2016-10-26 | 青岛海信电器股份有限公司 | Method, device and system for displaying recommended information |
CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技(深圳)有限公司 | Video recommendation method and device |
WO2017107453A1 (en) * | 2015-12-23 | 2017-06-29 | 乐视控股(北京)有限公司 | Video content recommendation method, device, and system |
CN106919632A (en) * | 2015-12-28 | 2017-07-04 | 广州华多网络科技有限公司 | Video recommendation method and device based on main broadcaster's appearance |
CN107079199A (en) * | 2014-10-17 | 2017-08-18 | 汤森路透全球资源公司 | Order video news program |
CN107071528A (en) * | 2017-04-20 | 2017-08-18 | 暴风集团股份有限公司 | A kind of display methods and display device of physical culture schedules |
CN107155135A (en) * | 2017-05-16 | 2017-09-12 | 腾讯科技(深圳)有限公司 | A kind of list of videos is obtained and player method, device and terminal |
CN107864234A (en) * | 2017-12-18 | 2018-03-30 | 广东省电信规划设计院有限公司 | The acquisition methods and device of address renewed treaty time |
CN107943932A (en) * | 2017-11-22 | 2018-04-20 | 广州虎牙信息科技有限公司 | Category recommends method, storage device and terminal |
CN108347652A (en) * | 2018-02-24 | 2018-07-31 | 华南理工大学 | A kind of method and system for recommending IPTV direct broadcast bands using artificial neural network |
CN108419134A (en) * | 2018-02-05 | 2018-08-17 | 华南理工大学 | The recommendation of the channels method merged with group current behavior based on individual history |
CN108737847A (en) * | 2018-06-29 | 2018-11-02 | 山东浪潮商用***有限公司 | A kind of channel real-time recommendation implementation method of IP live broadcast systems |
CN109348260A (en) * | 2018-12-06 | 2019-02-15 | 武汉瓯越网视有限公司 | A kind of direct broadcasting room recommended method, device, equipment and medium |
CN110213606A (en) * | 2019-05-30 | 2019-09-06 | 上海云甫智能科技有限公司 | A kind of live streaming content of platform recommended method and system |
CN110879944A (en) * | 2018-09-05 | 2020-03-13 | 武汉斗鱼网络科技有限公司 | Anchor recommendation method, storage medium, equipment and system based on face similarity |
CN111142740A (en) * | 2018-11-02 | 2020-05-12 | 腾讯科技(深圳)有限公司 | Data updating method, device and storage medium |
CN111488484A (en) * | 2020-04-16 | 2020-08-04 | 北京雷石天地电子技术有限公司 | Song recommendation method, medium, and apparatus based on class index distribution and TF-IDF characteristics |
TWI722924B (en) * | 2020-06-15 | 2021-03-21 | 瑞昱半導體股份有限公司 | Multimedia channel switching reminding system and method |
CN112770126A (en) * | 2020-12-29 | 2021-05-07 | 北京达佳互联信息技术有限公司 | Live broadcast room pushing method and device, server and storage medium |
CN113055722A (en) * | 2019-12-26 | 2021-06-29 | 深圳Tcl数字技术有限公司 | Program recommendation method, television and storage medium |
CN113207010A (en) * | 2021-06-02 | 2021-08-03 | 清华大学 | Model training method, live broadcast recommendation method, device and program product |
CN114501075A (en) * | 2020-11-11 | 2022-05-13 | 深圳Tcl新技术有限公司 | Program recommendation method, smart television and computer readable storage medium |
CN114518910A (en) * | 2022-02-14 | 2022-05-20 | 北京有竹居网络技术有限公司 | Application starting method and device, electronic equipment, storage medium and program product |
CN115065845A (en) * | 2022-06-17 | 2022-09-16 | 联通沃音乐文化有限公司 | Video and audio playing management method and system for community fusion recommendation |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1465177A (en) * | 2001-07-09 | 2003-12-31 | 索尼公司 | Content preference calculation method and content reception apparatus |
CN101094372A (en) * | 2007-07-25 | 2007-12-26 | 北京中星微电子有限公司 | Device and method for recommending TV programs |
CN101763351A (en) * | 2008-12-23 | 2010-06-30 | 未序网络科技(上海)有限公司 | Data fusion based video program recommendation method |
CN102917269A (en) * | 2012-09-29 | 2013-02-06 | 青岛海信电器股份有限公司 | Television program recommendation system and method |
CN103024554A (en) * | 2012-12-21 | 2013-04-03 | 深圳Tcl新技术有限公司 | Method for previewing television programs |
-
2013
- 2013-09-09 CN CN201310407292.6A patent/CN103491441B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1465177A (en) * | 2001-07-09 | 2003-12-31 | 索尼公司 | Content preference calculation method and content reception apparatus |
CN101094372A (en) * | 2007-07-25 | 2007-12-26 | 北京中星微电子有限公司 | Device and method for recommending TV programs |
CN101763351A (en) * | 2008-12-23 | 2010-06-30 | 未序网络科技(上海)有限公司 | Data fusion based video program recommendation method |
CN102917269A (en) * | 2012-09-29 | 2013-02-06 | 青岛海信电器股份有限公司 | Television program recommendation system and method |
CN103024554A (en) * | 2012-12-21 | 2013-04-03 | 深圳Tcl新技术有限公司 | Method for previewing television programs |
Cited By (42)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945241A (en) * | 2014-05-12 | 2014-07-23 | 腾讯科技(深圳)有限公司 | Streaming data statistical method, system and related device |
CN103995875A (en) * | 2014-05-23 | 2014-08-20 | 百度在线网络技术(北京)有限公司 | Information recommendation method and device |
CN104038790A (en) * | 2014-06-30 | 2014-09-10 | 北京奇艺世纪科技有限公司 | Video playing list updating method and system |
CN104038790B (en) * | 2014-06-30 | 2018-04-13 | 北京奇艺世纪科技有限公司 | Video play lists update method and system |
CN107079199A (en) * | 2014-10-17 | 2017-08-18 | 汤森路透全球资源公司 | Order video news program |
CN104780463A (en) * | 2015-04-15 | 2015-07-15 | 天脉聚源(北京)传媒科技有限公司 | Display method and device of program menu |
CN104780464A (en) * | 2015-04-22 | 2015-07-15 | 天脉聚源(北京)传媒科技有限公司 | Method and device for generating three-dimensional menu |
CN104935968A (en) * | 2015-06-25 | 2015-09-23 | 广州视源电子科技股份有限公司 | Method and system for recommending programs by network television |
CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技(深圳)有限公司 | Video recommendation method and device |
US10575037B2 (en) | 2015-07-06 | 2020-02-25 | Tencent Technology (Shenzhen) Company Limited | Video recommending method, server, and storage media |
CN105245958A (en) * | 2015-11-11 | 2016-01-13 | Tcl集团股份有限公司 | Live television program recommendation method and device |
CN105245958B (en) * | 2015-11-11 | 2020-03-24 | Tcl集团股份有限公司 | Live television program recommendation method and device |
WO2017107453A1 (en) * | 2015-12-23 | 2017-06-29 | 乐视控股(北京)有限公司 | Video content recommendation method, device, and system |
CN106919632A (en) * | 2015-12-28 | 2017-07-04 | 广州华多网络科技有限公司 | Video recommendation method and device based on main broadcaster's appearance |
CN106028070A (en) * | 2016-05-16 | 2016-10-12 | 乐视控股(北京)有限公司 | Live broadcast or carousel channel recommending method and device and video server |
CN106060590A (en) * | 2016-07-07 | 2016-10-26 | 青岛海信电器股份有限公司 | Method, device and system for displaying recommended information |
CN106060590B (en) * | 2016-07-07 | 2020-01-31 | 青岛海信电器股份有限公司 | Display method, device and system of recommendation information |
CN107071528A (en) * | 2017-04-20 | 2017-08-18 | 暴风集团股份有限公司 | A kind of display methods and display device of physical culture schedules |
CN107155135A (en) * | 2017-05-16 | 2017-09-12 | 腾讯科技(深圳)有限公司 | A kind of list of videos is obtained and player method, device and terminal |
CN107155135B (en) * | 2017-05-16 | 2019-02-12 | 腾讯科技(深圳)有限公司 | A kind of list of videos obtains and playback method, device and terminal |
CN107943932B (en) * | 2017-11-22 | 2020-06-09 | 广州虎牙信息科技有限公司 | Item recommendation method, storage device and terminal |
CN107943932A (en) * | 2017-11-22 | 2018-04-20 | 广州虎牙信息科技有限公司 | Category recommends method, storage device and terminal |
CN107864234B (en) * | 2017-12-18 | 2020-12-11 | 广东省电信规划设计院有限公司 | Method and device for acquiring address continuation time |
CN107864234A (en) * | 2017-12-18 | 2018-03-30 | 广东省电信规划设计院有限公司 | The acquisition methods and device of address renewed treaty time |
CN108419134A (en) * | 2018-02-05 | 2018-08-17 | 华南理工大学 | The recommendation of the channels method merged with group current behavior based on individual history |
CN108347652B (en) * | 2018-02-24 | 2020-01-14 | 华南理工大学 | Method and system for recommending IPTV live broadcast channel by using artificial neural network |
CN108347652A (en) * | 2018-02-24 | 2018-07-31 | 华南理工大学 | A kind of method and system for recommending IPTV direct broadcast bands using artificial neural network |
CN108737847A (en) * | 2018-06-29 | 2018-11-02 | 山东浪潮商用***有限公司 | A kind of channel real-time recommendation implementation method of IP live broadcast systems |
CN110879944A (en) * | 2018-09-05 | 2020-03-13 | 武汉斗鱼网络科技有限公司 | Anchor recommendation method, storage medium, equipment and system based on face similarity |
CN111142740A (en) * | 2018-11-02 | 2020-05-12 | 腾讯科技(深圳)有限公司 | Data updating method, device and storage medium |
CN109348260A (en) * | 2018-12-06 | 2019-02-15 | 武汉瓯越网视有限公司 | A kind of direct broadcasting room recommended method, device, equipment and medium |
CN110213606A (en) * | 2019-05-30 | 2019-09-06 | 上海云甫智能科技有限公司 | A kind of live streaming content of platform recommended method and system |
CN113055722A (en) * | 2019-12-26 | 2021-06-29 | 深圳Tcl数字技术有限公司 | Program recommendation method, television and storage medium |
CN113055722B (en) * | 2019-12-26 | 2023-07-25 | 深圳Tcl数字技术有限公司 | Program recommendation method, television and storage medium |
CN111488484A (en) * | 2020-04-16 | 2020-08-04 | 北京雷石天地电子技术有限公司 | Song recommendation method, medium, and apparatus based on class index distribution and TF-IDF characteristics |
CN111488484B (en) * | 2020-04-16 | 2023-04-28 | 北京雷石天地电子技术有限公司 | Song recommendation method, medium and device based on class index distribution and TF-IDF characteristics |
TWI722924B (en) * | 2020-06-15 | 2021-03-21 | 瑞昱半導體股份有限公司 | Multimedia channel switching reminding system and method |
CN114501075A (en) * | 2020-11-11 | 2022-05-13 | 深圳Tcl新技术有限公司 | Program recommendation method, smart television and computer readable storage medium |
CN112770126A (en) * | 2020-12-29 | 2021-05-07 | 北京达佳互联信息技术有限公司 | Live broadcast room pushing method and device, server and storage medium |
CN113207010A (en) * | 2021-06-02 | 2021-08-03 | 清华大学 | Model training method, live broadcast recommendation method, device and program product |
CN114518910A (en) * | 2022-02-14 | 2022-05-20 | 北京有竹居网络技术有限公司 | Application starting method and device, electronic equipment, storage medium and program product |
CN115065845A (en) * | 2022-06-17 | 2022-09-16 | 联通沃音乐文化有限公司 | Video and audio playing management method and system for community fusion recommendation |
Also Published As
Publication number | Publication date |
---|---|
CN103491441B (en) | 2017-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103491441B (en) | Recommendation method and system of live television programs | |
US20230388595A1 (en) | Methods and systems for generating a notification | |
CN102917269B (en) | A kind of television program recommendation system and method | |
US9635401B2 (en) | Recommendation of television content | |
US20130179925A1 (en) | Systems and methods for navigating through related content based on a profile associated with a user | |
US20130347033A1 (en) | Methods and systems for user-induced content insertion | |
DE102011056870A1 (en) | Blaster/digital receiver type remote control device i.e. smartphone, for controlling set of e.g. TVs, has computer system analyzing use information and producing set of references including information, which identify set of contents | |
CN103546778A (en) | Television program recommendation method and system, and implementation method of system | |
WO2013118198A1 (en) | Device for providing recommended content, program for providing recommended content, and method for providing recommended content | |
US11044516B2 (en) | Apparatus, systems and methods for media mosaic management | |
US20130290892A1 (en) | Information processing | |
CN106454431B (en) | TV programme suggesting method and system | |
RU2641663C1 (en) | Method of recommendation of the television program and the server | |
WO2012094352A1 (en) | Media asset usage data reporting that indicates corresponding content creator | |
US9386357B2 (en) | Display of presentation elements | |
KR101054088B1 (en) | How to automatically recommend customized IP programs using collaborative filtering | |
US11974014B2 (en) | Systems and methods for dynamically educating users on sports terminology | |
CA2731051A1 (en) | Management and delivery of audiovisual content items that correspond to scheduled programs | |
US10389779B2 (en) | Information processing | |
CN111083522A (en) | Video distribution, playing and user characteristic label obtaining method | |
KR20140076272A (en) | Apparatus and method for contents recommendation based on television viewing habits | |
US10448072B1 (en) | Systems and methods for increasing a likelihood of media asset consumption using recommendation chains | |
KR101102351B1 (en) | Method and system for providing custom-made broadcasting program | |
JP6641205B2 (en) | Program recommendation device, program recommendation method, and program recommendation program | |
CN108924655B (en) | Video client navigation generation method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |