CN108536814A - Direct broadcasting room recommends method, computer readable storage medium and electronic equipment - Google Patents
Direct broadcasting room recommends method, computer readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108536814A CN108536814A CN201810304083.1A CN201810304083A CN108536814A CN 108536814 A CN108536814 A CN 108536814A CN 201810304083 A CN201810304083 A CN 201810304083A CN 108536814 A CN108536814 A CN 108536814A
- Authority
- CN
- China
- Prior art keywords
- direct broadcasting
- broadcasting room
- direct
- room
- 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.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention provides a kind of direct broadcasting room recommendation method comprising following steps：It is recorded according to viewing, the direct broadcasting room watched in preset time each user on live streaming platform is ranked up sequentially in time；All direct broadcasting room set R being watched in live streaming platform are obtained, the weighted value between any two direct broadcasting room in direct broadcasting room set R is calculated；The similarity value between any two direct broadcasting room is calculated according to the weighted value between any two direct broadcasting room；For any source direct broadcasting room in direct broadcasting room set R, direct broadcasting room similar with any source direct broadcasting room is arranged sequentially according to similarity value is descending in the recommendation list of source direct broadcasting room；The direct broadcasting room that acquisition user finally watches recommends user successively as above-mentioned source direct broadcasting room, by the direct broadcasting room in the state that starts broadcasting in the recommendation list of source direct broadcasting room.The invention further relates to relevant computer readable storage medium and associated electronic devices.
Description
Technical field
The present invention relates to big datas, and field more particularly to a kind of direct broadcasting room based on viewing path to be recommended to recommend method.
Background technology
With the development of live streaming platform, the direct broadcasting room being broadcast live on platform is more and more, and user wants from numerous direct broadcasting rooms
One direct broadcasting room seen oneself liked of selection becomes more difficult, how to recommend direct broadcasting room to become for user and is badly in need of solution at present
Certainly the problem of.It is currently used to user recommend direct broadcasting room method be hot broadcast list recommend, that is, to user recommend one section when
According to the list of the main broadcaster of pouplarity sequence in Jian Nei webcast websites.The shortcomings that this method, does not account for user
Individual demand, has the effect of new user certain, but old user cannot not only be met the needs of users, can also be allowed
User feels to dislike.
In fact, to the viewing behavior of direct broadcasting room, there are sequencing, each users on live streaming platform by user
There is an one's own direct broadcasting room viewing path, the time sequencing that user watches direct broadcasting room is reflected in the pathway surfaces, but
From the point of view of deeper angle, viewing path represents the viewing hobby of user, often the viewing of similar direct broadcasting room when
Between interval can very little, so the viewing path of user be one be worth excavate information.
Invention content
Based on above-mentioned thinking, in order to overcome at least one aspect of the above problem, the embodiment of the present invention to provide a kind of live streaming
Between recommend method, the weight between direct broadcasting room is determined by the viewing path of user, and then determine similar between direct broadcasting room
Degree carries out user personalized recommendation further according to the viewing record of user.
According to an aspect of the present invention, a kind of direct broadcasting room recommendation method is provided, is included the following steps：
Step S1 is recorded according to viewing, and the direct broadcasting room watched in preset time each user on live streaming platform is pressed
It is ranked up according to time sequencing；
Step S2 obtains all direct broadcasting room set R being watched in live streaming platform, calculates appointing in direct broadcasting room set R
Weighted value between two direct broadcasting rooms of meaning；
Step S3 calculates the similarity between any two direct broadcasting room according to the weighted value between any two direct broadcasting room
Value；
Step S4 will live streaming similar with any source direct broadcasting room for any source direct broadcasting room in direct broadcasting room set R
Between be arranged sequentially in the recommendation list of source direct broadcasting room according to similarity value is descending；And
Step S5, the direct broadcasting room that acquisition user finally watches is as above-mentioned source direct broadcasting room, by the recommendation list of source direct broadcasting room
In recommend user successively in the direct broadcasting room of state of starting broadcasting.
Further include step before step S1 according to some embodiments：Each user single in preset time is deleted to see
See that the time is less than or equal to the viewing record of the direct broadcasting room of predetermined time.
According to some embodiments, the weighted value between any two direct broadcasting room in direct broadcasting room set R is calculated according to the following formula：
Wherein, wfbIt is weighted values of the direct broadcasting room f to direct broadcasting room b, M (f) is the number for having viewed direct broadcasting room f, and M (f → b) is
Continue to watch the number of direct broadcasting room b after having viewed direct broadcasting room f.
It is further comprising the steps of between step S2 and step S3 according to some embodiments：Obtain the direct pass of direct broadcasting room b
Join direct broadcasting room set N (b), is directly linked direct broadcasting room set N (b) and refers to that all users are watched before watching direct broadcasting room b
Adjacent direct broadcasting room set.
According to some embodiments, the similarity value between two direct broadcasting rooms is calculated according to the following formula：
Wherein, sim (a, b) is the similarity value of direct broadcasting room a and b；α is conduction decay factor, and the value range of α is 0.8
~0.9；K is iteration round, and k is positive integer, and value range is 10~20；N (b) is the direct correlation direct broadcasting room collection of direct broadcasting room b
It closes；wibIt is the weighted value of the direct correlation direct broadcasting room i to direct broadcasting room b of direct broadcasting room b；wibIt is the direct correlation direct broadcasting room of direct broadcasting room b
Weighted values of the j to direct broadcasting room b；Sim (a, i)0=wai, sim (a, a)0=1.
According to another aspect of the present invention, a kind of computer readable storage medium is provided, executable finger is stored thereon with
It enables, when executed by the processor, the step for recommending method according to the direct broadcasting room of any one of above-described embodiment may be implemented in instruction
Suddenly.
According to a further aspect of the invention, a kind of electronic equipment is provided comprising：
Memory, for storing executable instruction；And
Processor, for executing the executable instruction stored in memory, to realize according to any in above-described embodiment
The direct broadcasting room of item recommends the step of method.
Compared with prior art, the present invention has the following advantages：It is determined between direct broadcasting room by the viewing path of user
Weight, and then determine the similarity between direct broadcasting room, personalized recommendation carried out to user further according to the viewing record of user,
The accuracy of recommendation is improved, and ensures that the direct broadcasting room recommended is the direct broadcasting room that user likes viewing to the full extent.
Description of the drawings
By the description made for the present invention of below with reference to attached drawing, other objects and advantages of the present invention will be aobvious and easy
See, and can help that complete understanding of the invention will be obtained.
Fig. 1 is the overall flow figure implemented direct broadcasting room according to the ... of the embodiment of the present invention and recommend method；
Fig. 2 is the structural schematic diagram of computer readable storage medium according to the ... of the embodiment of the present invention；
Fig. 3 is the structural schematic diagram of electronic equipment according to the ... of the embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The term used in embodiments of the present invention is the purpose only merely for description specific embodiment, is not intended to be limiting
The present invention.Unless otherwise defined, the technical term or scientific terminology that the present invention uses should be tool in fields of the present invention
There is the ordinary meaning that the personage of general technical ability is understood.
The present invention provides a kind of direct broadcasting room recommendation method, and according to Fig. 1, this approach includes the following steps：
S1 is recorded according to viewing, to the direct broadcasting room watched in preset time of each user on live streaming platform according to when
Between be sequentially ranked up.
Each user on live streaming platform, which watches direct broadcasting room, can generate record, these records all preserve in the database,
Viewing of each user in preset time is recorded and is taken out from database, this preset time is can be self-defined
, for example, preset time can be 7 days in the present embodiment.Certainly, in other embodiments, can also be that other times are long
Degree, for example can be longer time span, such as 30 days, it can also be shorter time span, such as a few hours.Then,
Direct broadcasting room on record is sorted sequentially in time, time more early direct broadcasting room can come more front.
In some possible embodiments, before carrying out above-mentioned steps, following steps can also be carried out：Delete each use
Family single viewing time in preset time is less than or equal to the viewing record of the direct broadcasting room of predetermined time.User's viewing time is small
In or equal to the predetermined time viewing behavior may only accidentally point arrive the direct broadcasting room or other certain similar behaviors, and
Really to have viewed the direct broadcasting room or interesting to the direct broadcasting room, the step be in order to retain effective viewing behavior,
The error for reducing data, to maximumlly ensure the accuracy of data.This predetermined time is also can be customized, in order to
Reduce error, the predetermined time can be set in the present embodiment as 1 minute.
S2 obtains all direct broadcasting room set R being watched in live streaming platform, calculates arbitrary two in direct broadcasting room set R
Weighted value between a direct broadcasting room.
In preset time, some possible direct broadcasting rooms were not viewed by a user, these live streamings not being viewed by a user
Between will be unable to calculate and other direct broadcasting rooms between similarity need to exclude these unviewed mistakes to reduce calculation amount
Direct broadcasting room.From all direct broadcasting rooms being viewed by a user on live streaming platform are obtained in database, by these one collection of live streaming composition
R is closed, the weighted value between any two direct broadcasting room in direct broadcasting room set R is calculated, for example, direct broadcasting room can be calculated according to the following formula
Weighted value between direct broadcasting room f in set R and direct broadcasting room b：
Wherein, wfbIt is weighted values of the direct broadcasting room f to direct broadcasting room b, M (f) is the number for having viewed direct broadcasting room f, and M (f → b) is
Have viewed the number that viewing direct broadcasting room b is continued directly to after direct broadcasting room f.Weighted value can refer to that user has viewed direct broadcasting room f and is followed by
The probability of viewing direct broadcasting room b.Weighted value is bigger, illustrates that probability is higher, also just illustrates that user is having viewed direct broadcasting room f followed by
The probability for watching direct broadcasting room b is higher.This reflects the relevance of direct broadcasting room f and direct broadcasting room b to a certain extent, and probability is higher,
Illustrate that the relevance of direct broadcasting room f and direct broadcasting room b are bigger.
In some possible embodiments, also wrapped after the weighted value in set R has been calculated between any two direct broadcasting room
Include following steps：The direct correlation direct broadcasting room set N (b) of direct broadcasting room b is obtained, direct broadcasting room set N (b) is directly linked and refers to institute
There is the set for the adjacent direct broadcasting room that user watched before watching direct broadcasting room b.Here " close to " refers to that user has watched
Direct viewing direct broadcasting room b after the direct broadcasting room does not watch other direct broadcasting rooms watching between the direct broadcasting room and viewing direct broadcasting room b.
S3 calculates the similarity value between any two direct broadcasting room according to the weighted value between any two direct broadcasting room.
For example, the similarity value between direct broadcasting room a and direct broadcasting room b can be calculated according to the following formula：
Wherein, sim (a, b) is the similarity value of direct broadcasting room a and b；α is conduction decay factor, the value range of α is 0~
1, it can usually take the numerical value between 0.8-0.9；K is iteration round, and k is positive integer, and usual value range is 10~20；N(b)
It is the direct correlation direct broadcasting room set of direct broadcasting room b；wibIt is the weighted value of the direct correlation direct broadcasting room i to direct broadcasting room b of direct broadcasting room b；
wjbIt is the weighted value of the direct correlation direct broadcasting room j to direct broadcasting room b of direct broadcasting room b；Sim (a, i)0=wai, sim (a, a)0=1.
S4 presses direct broadcasting room similar with any source direct broadcasting room for any source direct broadcasting room in direct broadcasting room set R
It is arranged sequentially in the recommendation list of source direct broadcasting room according to similarity value is descending.
For example illustrate the meaning of source direct broadcasting room：The similarity value of direct broadcasting room a and direct broadcasting room b are 0.3, direct broadcasting room
The similarity value of a and direct broadcasting room c are 0.2, and the similarity value of direct broadcasting room a and direct broadcasting room d are 0.1, then source direct broadcasting room here
It is exactly direct broadcasting room a, in other words, source direct broadcasting room refers to having similarity relation with other multiple direct broadcasting rooms as basic direct broadcasting room
Direct broadcasting room.In this example, is arranged, put in order as follows according to the descending sequence of similarity value：b、c、d.
S5, the direct broadcasting room that acquisition user finally watches, will be in the recommendation lists of source direct broadcasting room as above-mentioned source direct broadcasting room
Direct broadcasting room in the state of starting broadcasting recommends user successively.
It is recorded according to the viewing of user, the direct broadcasting room that user finally watches is found, in the recommendation list by the direct broadcasting room
Direct broadcasting room recommend user before, it is also necessary to judge these direct broadcasting rooms whether in the state that starts broadcasting, if do not started broadcasting, no
Recommend these direct broadcasting rooms to user, after the state that starts broadcasting of direct broadcasting room is determined, by the direct broadcasting room in the state of starting broadcasting according to pushing away
User is recommended in the sequence recommended in list successively.For example, continuing the example above, the direct broadcasting room that user finally watches is a, live streaming
Between c do not start broadcasting, then just according to b, d sequence successively to user recommend.
A concrete instance is set forth below and illustrates the present invention is how to calculate the similarity value of two direct broadcasting rooms.
Assuming that there is four viewing paths：A → c, a → d, c → b, d → b.The number for watching direct broadcasting room a is 1000, is had viewed
Continue to watch the number of direct broadcasting room c after direct broadcasting room a to be 200, has viewed and continue to watch the number of direct broadcasting room d after direct broadcasting room a and be
600, the number of viewing direct broadcasting room c is 300, continues to watch the number of direct broadcasting room b to be 150 after having viewed direct broadcasting room c, viewing live streaming
Between the number of d be 800, continue to watch the number of direct broadcasting room b to be 240 after having viewed direct broadcasting room d.
Weighted value is calculated first, and result of calculation is as follows：
Because of sim (a, i)0=wai, so sim (a, c)0=wac, sim (a, d)0=wad。
α takes 0.8, first round iteration, and the similarity value between a and b is as follows：
It can similarly obtain, sim (a, c)1=0.16, sim (a, d)1=0.48.
Second wheel iteration, the similarity value between a and b are as follows：
……
Tenth wheel iteration, the similarity value between a and b are as follows：
In this example, for the convenience of description, there is no other direct correlation that direct broadcasting room c and direct broadcasting room d is added are straight
Between broadcasting, so the weight of direct broadcasting room a to direct broadcasting room c and direct broadcasting room a to direct broadcasting room d is all 1, this results in sim (a, c)k+1=α
Sim (a, c)k, sim (a, d)k+1=α sim (a, d)k, so that the similarity value between direct broadcasting room a and direct broadcasting room b is declined
Subtract.The scene that above-mentioned example considers is relatively simple, and in practical operation, there is also other to be associated with directly with direct broadcasting room d by direct broadcasting room c
Between broadcasting, true similarity value will not constantly decay as above-mentioned example.
Since the path of user's viewing direct broadcasting room represents the hobby of user, path can form certain cooccurrence relation,
By excavating the Analysis of Deep Implications in path in the present embodiment, the similarity relation between direct broadcasting room is found, to carry out individual character to user
The direct broadcasting room of change is recommended, and significantly enhances the effect of recommendation, and improve the accuracy of recommendation.
Based on same inventive concept, refering to what is shown in Fig. 2, the present invention also provides a kind of computer readable storage medium 201,
On be stored with executable instruction 202, executable instruction 202 when executed by the processor, may be implemented according in above-described embodiment
Any one of them direct broadcasting room recommend method the step of.
Based on same inventive concept, refering to what is shown in Fig. 3, the present invention also provides a kind of electronic equipment 301, the electronic equipment
301 include：
Memory 310 is used to store executable instruction 311；And
Processor 320 is used to execute the executable instruction 311 stored in memory 310, to realize such as above-described embodiment
Any one of described in direct broadcasting room recommend method the step of.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of ordinary skill in the art that：It still may be used
With technical scheme described in the above embodiments is modified or equivalent replacement of some of the technical features；
And these modifications or replacements, various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (7)
1. a kind of direct broadcasting room recommends method, which is characterized in that include the following steps：
Step S1 is recorded according to viewing, to the direct broadcasting room watched in preset time of each user on live streaming platform according to when
Between be sequentially ranked up；
Step S2 obtains all direct broadcasting room set R being watched in live streaming platform, calculates appointing in the direct broadcasting room set R
Weighted value between two direct broadcasting rooms of meaning；
Step S3 calculates the similarity between any two direct broadcasting room according to the weighted value between any two direct broadcasting room
Value；
Step S4 will be similar with any source direct broadcasting room for any source direct broadcasting room in the direct broadcasting room set R
Direct broadcasting room is arranged sequentially according to similarity value is descending in the recommendation list of the source direct broadcasting room；And
Step S5, the direct broadcasting room that acquisition user finally watches is as above-mentioned source direct broadcasting room, by the recommendation list of the source direct broadcasting room
In recommend the user successively in the direct broadcasting room of state of starting broadcasting.
2. according to the method described in claim 1, it is characterized in that, further comprising the steps of before step S1：It deletes each
User's single viewing time in preset time is less than or equal to the viewing record of the direct broadcasting room of predetermined time.
3. according to the method described in claim 1, it is characterized in that, calculating according to the following formula arbitrary in the direct broadcasting room set R
Weighted value between two direct broadcasting rooms：
Wherein, wfbIt is weighted values of the direct broadcasting room f to direct broadcasting room b, M (f) is the number for having viewed direct broadcasting room f, and M (f → b) is viewing
The number of viewing direct broadcasting room b is continued directly to after direct broadcasting room f.
4. according to the method described in claim 3, it is characterized in that, further comprising the steps of between step S2 and step S3：
The direct correlation direct broadcasting room set N (b) of direct broadcasting room b is obtained, the direct correlation direct broadcasting room set N (b) refers to all users
The set for the adjacent direct broadcasting room watched before watching direct broadcasting room b.
5. according to the method described in claim 4, it is characterized in that, calculating the similarity between two direct broadcasting rooms according to the following formula
Value：
Wherein, sim (a, b) is the similarity value of direct broadcasting room a and b；α is conduction decay factor, and the value range of α is 0.8-0.9；
K is iteration round, and k is positive integer, value range 10-20；N (b) is the direct correlation direct broadcasting room set of direct broadcasting room b；wbIt is
The weighted value of the direct correlation direct broadcasting room i to direct broadcasting room b of direct broadcasting room b；wjbBe direct broadcasting room b direct correlation direct broadcasting room j to live streaming
Between b weighted value；Sim (a, i)0=wai, sim (a, a)0=1.
6. a kind of computer readable storage medium, is stored thereon with executable instruction, described instruction is when executed by the processor, real
Now the direct broadcasting room according to any one of claim 1-5 recommends the step of method.
7. a kind of electronic equipment, including：
Memory, for storing executable instruction；And
Processor, for executing the executable instruction stored in the memory, to realize according to any one of claim 1-5
The direct broadcasting room recommends the step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810304083.1A CN108536814B (en) | 2018-04-04 | 2018-04-04 | Live broadcast room recommendation method, computer-readable storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810304083.1A CN108536814B (en) | 2018-04-04 | 2018-04-04 | Live broadcast room recommendation method, computer-readable storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108536814A true CN108536814A (en) | 2018-09-14 |
| CN108536814B CN108536814B (en) | 2022-06-21 |
Family
ID=63482782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810304083.1A Active CN108536814B (en) | 2018-04-04 | 2018-04-04 | Live broadcast room recommendation method, computer-readable storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108536814B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977264A (en) * | 2019-02-19 | 2019-07-05 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of user's recommended method, system, server and storage medium based on first similarity of paths |
| CN111083503A (en) * | 2018-10-22 | 2020-04-28 | 武汉斗鱼网络科技有限公司 | Method, device, equipment and storage medium for calculating similarity of live broadcast rooms |
| 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 |
| CN113592543A (en) * | 2021-07-27 | 2021-11-02 | 北京达佳互联信息技术有限公司 | Method and device for evaluating live broadcast guide effect |
| CN113766263A (en) * | 2021-09-08 | 2021-12-07 | 北京快来文化传播集团有限公司 | Live broadcast room recommendation method and device |
| CN113938700A (en) * | 2021-10-27 | 2022-01-14 | 广州方硅信息技术有限公司 | Live broadcast room switching method and device and computer equipment |
| CN114969514A (en) * | 2022-05-06 | 2022-08-30 | 北京百度网讯科技有限公司 | Live broadcast recommendation method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080222295A1 (en) * | 2006-11-02 | 2008-09-11 | Addnclick, Inc. | Using internet content as a means to establish live social networks by linking internet users to each other who are simultaneously engaged in the same and/or similar content |
| CN105338408A (en) * | 2015-12-02 | 2016-02-17 | 南京理工大学 | Video recommending method based on time factor |
| CN105847984A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommending method and apparatus |
| CN106658083A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Watching channel path counting method and watching channel path counting device |
| CN107835441A (en) * | 2017-10-10 | 2018-03-23 | 武汉斗鱼网络科技有限公司 | Live recommendation method, storage medium, equipment and system based on path prediction |
-
2018
- 2018-04-04 CN CN201810304083.1A patent/CN108536814B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080222295A1 (en) * | 2006-11-02 | 2008-09-11 | Addnclick, Inc. | Using internet content as a means to establish live social networks by linking internet users to each other who are simultaneously engaged in the same and/or similar content |
| CN106658083A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Watching channel path counting method and watching channel path counting device |
| CN105338408A (en) * | 2015-12-02 | 2016-02-17 | 南京理工大学 | Video recommending method based on time factor |
| CN105847984A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Video recommending method and apparatus |
| CN107835441A (en) * | 2017-10-10 | 2018-03-23 | 武汉斗鱼网络科技有限公司 | Live recommendation method, storage medium, equipment and system based on path prediction |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111083503A (en) * | 2018-10-22 | 2020-04-28 | 武汉斗鱼网络科技有限公司 | Method, device, equipment and storage medium for calculating similarity of live broadcast rooms |
| CN109977264A (en) * | 2019-02-19 | 2019-07-05 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of user's recommended method, system, server and storage medium based on first similarity of paths |
| CN109977264B (en) * | 2019-02-19 | 2022-09-09 | 武汉斗鱼鱼乐网络科技有限公司 | User recommendation method, system, server and storage medium based on meta-path similarity |
| 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 |
| CN113592543A (en) * | 2021-07-27 | 2021-11-02 | 北京达佳互联信息技术有限公司 | Method and device for evaluating live broadcast guide effect |
| CN113766263A (en) * | 2021-09-08 | 2021-12-07 | 北京快来文化传播集团有限公司 | Live broadcast room recommendation method and device |
| CN113938700A (en) * | 2021-10-27 | 2022-01-14 | 广州方硅信息技术有限公司 | Live broadcast room switching method and device and computer equipment |
| CN113938700B (en) * | 2021-10-27 | 2024-03-12 | 广州方硅信息技术有限公司 | Live broadcast room switching method and device and computer equipment |
| CN114969514A (en) * | 2022-05-06 | 2022-08-30 | 北京百度网讯科技有限公司 | Live broadcast recommendation method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108536814B (en) | 2022-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108536814A (en) | Direct broadcasting room recommends method, computer readable storage medium and electronic equipment | |
| CN105142028B (en) | The content of TV program search of triple play oriented is with recommending method | |
| US9467744B2 (en) | Comment-based media classification | |
| CN106791966B (en) | A kind of direct broadcasting room recommended method and system based on modified correlation rule | |
| US9264769B2 (en) | User viewing data collection for generating media viewing achievements | |
| US9535992B2 (en) | Recommendation engine | |
| CN104284216B (en) | A kind of method and its system generating video essence editing | |
| US9965776B2 (en) | Digital content recommendations based on user comments | |
| US20070219994A1 (en) | Methods and systems for displaying media utilizing user-generated data | |
| US9679018B1 (en) | Document ranking based on entity frequency | |
| KR20150135196A (en) | Tailoring user experience for unrecognized and new users | |
| CN106131703A (en) | A kind of method of video recommendations and terminal | |
| AU2013370480A1 (en) | Presenting recommended content in search pages | |
| US10476976B1 (en) | Consuming content items collaboratively | |
| CN109587527B (en) | Personalized video recommendation method and device | |
| CN105183925A (en) | Content association recommending method and content association recommending device | |
| US20170238043A1 (en) | Touch gesture control of video playback | |
| McNally et al. | Towards a reputation-based model of social web search | |
| CN105956061B (en) | Method and device for determining similarity between users | |
| US8825698B1 (en) | Showing prominent users for information retrieval requests | |
| JP6388506B2 (en) | Content recommendation device and program | |
| CN109241450A (en) | The recommended method and device of screen locking content | |
| CN106445922B (en) | Method and device for determining title of multimedia resource | |
| CN105912544A (en) | Method and device for matching video content, server, and video playing system | |
| Gligorov et al. | An evaluation of labelling-game data for video retrieval |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |