CN104216883A - Video recommendation reason generating system and method - Google Patents
Video recommendation reason generating system and method Download PDFInfo
- Publication number
- CN104216883A CN104216883A CN201310206861.0A CN201310206861A CN104216883A CN 104216883 A CN104216883 A CN 104216883A CN 201310206861 A CN201310206861 A CN 201310206861A CN 104216883 A CN104216883 A CN 104216883A
- Authority
- CN
- China
- Prior art keywords
- video
- recommendation
- rationale
- recommendations
- reason
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
Abstract
The invention discloses a video recommendation reason generating system and method. The video recommendation reason generating system comprises a filter unit, a selection unit and a recommendation reason unit composed of video sets. The recommendation reason unit is used for videos based on various recommendation reasons for the filter unit. The filter unit is used for filtering the videos based on the recommendation reasons so as to remove the videos which do not satisfy the condition. The selection unit is used for conducting recommendation and display on the videos filtered through the filter unit. Various video resource data are collected and classified to form the videos based on various recommendation reasons, the classified videos are screened and filtered, and therefore high-quality videos are recommended and displayed to users.
Description
Technical field
The present invention relates to network Online Video technology, particularly relate to a kind of video recommendations reason generation system and method.
Background technology
Along with the development of infotech and internet, people have entered into the epoch of information overload from the epoch of absence of information gradually.For the consumer of information, from magnanimity information, oneself interested information is found to be a very difficult thing; Meanwhile, for information producer, the information allowing oneself produce is shown one's talent, and is subject to users and pays close attention to, and is also the very difficult thing of part.Recommended engine produces to address this problem just., there is the problem of following several aspect in the recommended engine of prior art:
1. represent more single:
The recommendation results of existing recommended engine, the recommendation results list of a flat structure often, in list, the importance degree of recommendation results only can be supplied to user according to clooating sequence, and user can not see " bright spot " of each recommendation results wherein at a glance, cannot give top priority to what is the most important.
2. information is not forbidden entirely:
Such as video website, some video that user uploads, although be the content of video own be high-quality, the title of user's input describes accurate not, and thumbnail quality is not ideal enough.If these videos appear in the middle of recommendation results, owing to there is no additional supplementary notes, be difficult to attract user to click in recommendation list.
3. recommend agnogenio:
User does not understand system usually, feels obscure to the result that commending system is recommended out.Good rationale for the recommendation can allow user better understand system, knows why system recommends this video, and this video advantage somewhere.
Therefore in commending system, how to recommend out the video of high-quality to attract user's eyeball, become and increase commending system click problem demanding prompt solution.
Summary of the invention
The object of the present invention is to provide a kind of video recommendations reason generation system and method, by collecting various video resource data, classification forms the video of various rationale for the recommendation, and screens the video of these classification and filter, thus recommends out the video of high-quality to present to user.
For reaching above-mentioned and other object, the invention provides a kind of video recommendations reason generation system, comprising: filter element, selection unit and the rationale for the recommendation unit be made up of video set, wherein,
Rationale for the recommendation unit is in order to provide the video based on various rationale for the recommendation to filter element;
Filter element, in order to filter the video of rationale for the recommendation unit, removes ineligible video;
Selection unit is shown in order to carry out recommendation to the video after filter element filters.
Further, described rationale for the recommendation unit comprises homepage recommending module, ranking list recommending module, statistics recommending module, comment recommending module, artificial recommending module, uploader recommending module or combination in any wherein, wherein,
Homepage recommending module once appeared at the video of homepage in order to collect, generate the rationale for the recommendation that homepage is relevant;
Ranking list recommending module, in order to collect the forward video of all kinds of ranking list rank, generates ranking list rationale for the recommendation;
Statistics recommending module in order to collect the statistics of video playback behavior, and based on the generating recommendations reason of this statistics;
Comment recommending module is in order to based on the comment generating recommendations reason of user to video;
Uploader recommending module is in order to carry out generating recommendations reason based on to the historical record of uploader uploaded videos.
Further, described video recommendations reason generation system also comprises weight setting module, in order to distribute the weight of importance degree to each recommendation unit.
Further, described filter element, comprises click volume filtering module or/and ranking list filtering module, wherein, described click volume filtering module filters in order to the click volume of the video provided described rationale for the recommendation unit, and the video recommendations reason that prioritizing selection click volume is large generates to selection unit; Ranking list filtering module filters in order to the rank of the video provided described rationale for the recommendation unit, and the forward video recommendations reason of prioritizing selection point rank generates to selection unit.
Further, the statistics of described statistics recommending module, comprises a kind of or combination in any wherein of one of scoring, certain regional most popular degree based on the accumulative click volume of this video, reprinting amount, user.
Further, described statistics recommending module is set with a statistical threshold, when the data of this statistical module counts exceed this statistical threshold, and just generating recommendations rationale for the recommendation.
For reaching above-mentioned and other object, the present invention also provides a kind of video recommendations reason generation method, comprises step:
1) video resource is provided;
2) video provided is filtered, remove ineligible video;
3) carry out recommendation to the video after filtering to show.
Further, step 1) comprise following rationale for the recommendation and recommend:
Collect the video once appearing at homepage and generate the relevant rationale for the recommendation of homepage;
Collect the forward video of all kinds of ranking list rank and generate ranking list rationale for the recommendation;
Collect the statistics of video playback behavior, and based on the generating recommendations reason of this statistics;
Based on the comment generating recommendations reason of user to video;
Generating recommendations reason is carried out based on to the historical record of uploader uploaded videos.
Further, step 2) filtration is carried out to the video provided comprise:
Filter the click volume of the video provided, the large video recommendations reason of prioritizing selection click volume generates, or and the rank of the video provided is filtered, the forward video recommendations reason of prioritizing selection point rank generates.
Further, step 1) when video resource is provided, also comprise the weight allocation of the video resource provided being carried out to significance level.
Further, regularly various rationale for the recommendation is upgraded.
Further, the statistics of collecting video playback behavior comprises based on the accumulative click volume of this video, reprinting amount, the scoring of user, a kind of of certain regional most popular degree or combination in any wherein.
Further, arrange a threshold value for described statistics, after its statistics exceedes threshold value, this video just becomes rationale for the recommendation.
Compared with prior art, a kind of video recommendations reason generation system provided by the invention and method, by collecting various video resource data, classification forms the video of various rationale for the recommendation, and screen the video of these classification and filter, thus the video of high-quality is recommended out to present to user.
Accompanying drawing explanation
Fig. 1 is the video recommendations reason generation system schematic diagram of the embodiment of the present invention one;
Fig. 2 is the video recommendations reason generation system schematic diagram comprising rationale for the recommendation unit detailed construction of the embodiment of the present invention one;
Fig. 3 is the video recommendations reason generation system schematic diagram of the embodiment of the present invention two.
Embodiment
For enabling above-mentioned purpose of the present invention, feature and advantage become apparent more, and below in conjunction with the drawings and specific embodiments, the present invention is further detailed explanation.
Embodiment one
Refer to Fig. 1, Fig. 1 is the video recommendations reason generation system schematic diagram of the present embodiment, the rationale for the recommendation unit 1 comprising filter element 2, selection unit 3 and be made up of video set, rationale for the recommendation unit 1 is in order to provide the video based on various rationale for the recommendation to filter element 2; Filter element 2 filters in order to the video recommended rationale for the recommendation unit 1, removes ineligible video; Selection unit 3, in order to recommend the video after filter element 2 filters, shows user.
Refer to Fig. 2, Fig. 2 is the schematic diagram comprising the detailed module of rationale for the recommendation unit 1 in the video recommendations reason generation system of the present embodiment, rationale for the recommendation unit 1 comprises homepage recommending module 10, ranking list recommending module 11, statistics recommending module 12, comment recommending module 13, uploader recommending module 14, also can be as required, by among above-mentioned multiple recommending module an arbitrarily block combiner form, such as by the recommendation unit of wherein arbitrary three or four module compositions.
Particularly, homepage recommending module 10 once appeared at the various videos of homepage in order to collect, thus generated the relevant rationale for the recommendation of homepage, such as " homepage top news video today ".For the channel page that some are important, also similar rationale for the recommendation can be generated.
Ranking list recommending module 11, in order to collect the forward video of each classification ranking list rank, generates ranking list rationale for the recommendation, such as collects each the first five video of ten of classification ranking list rank, generates ranking list rationale for the recommendation.For class of making laughs, if rank is greater than front 10, then rationale for the recommendation be roughly " class of making laughs to comment on today maximum rank first three/five/ten "; If rank be greater than front ten be less than the first five ten.Rationale for the recommendation is roughly " class of making laughs comment today at most ".
Statistics recommending module 12 in order to collect the statistics of video playback behavior, and based on the generating recommendations reason of this statistics.Comprise the video based on accumulative click volume, or based on microblogging reprinting amount video and add up.Due to habits and customs and the hobby difference of the user in each area, the interest of each area to all kinds of video is also distinguished to some extent, also can add up based on the video that certain area (such as Beijing) is most popular, or user give a mark height etc. add up.Utilize these statisticss, generate the rationale for the recommendation of Corpus--based Method, such as " accumulative click is greater than 10,000 ", " spectators' favorite of Beijing area is seen ", " microblogging heat is carried " etc.In order to obtain better, video that quality is higher, system can set a threshold value, after statistic is greater than certain threshold value, just can generate corresponding rationale for the recommendation, thus ensures that rationale for the recommendation is all high-quality, the video audient multi-user accreditation of recommendation.
The statistics of statistics recommending module 12, as required, can be made up of a kind of or wherein combination in any of the scoring of accumulative click volume, reprinting amount, user, certain regional most popular degree.
Comment recommending module 13 is based on the comment generating recommendations reason of user to video, some high quality reviews is the annotation to video highlight, excellent comment can be carried out to the plot of video, story, bright spot or personage etc., very be applicable to generating recommendations reason, allow the splendid contents of not seen the user of this video understand video fast, the user comment data of collecting high-quality constitute one of important recommending module.
Uploader recommending module 14 carries out generating recommendations reason based on to the historical record of uploader uploaded videos.Some user or clap visitor and once uploaded much good video, the dark favorable comment by user, and it is propagated and reprints, to be commented on or clicked higher.Therefore for the video uploaded from same bat visitor or this user or similar video, can anticipate that its video also can cause the interest of user, its video also can get high clicking rate under normal circumstances, therefore generates this kind of rationale for the recommendation also helpful for raising commending system clicking rate.
Filter element 2, comprise click volume filtering module or ranking list filtering module, or be made up of click volume filtering module and ranking list filtering module, described click volume filtering module filters in order to the click volume of the video provided described rationale for the recommendation unit 1, and the large video recommendations of prioritizing selection click volume is to selection unit 3; Ranking list filtering module filters in order to the rank of the video provided described rationale for the recommendation unit 1, and the forward video recommendations of prioritizing selection point rank is to selection unit 3.Such as only select to play the video of sum more than 100,000 times, or select to be in the video of before ranking list ten, ensure that filtration obtains high-quality video.
Embodiment two
Refer to Fig. 3, Fig. 3 is another embodiment of the present invention.This enforcement, on the basis of embodiment one, adds weight setting unit 4, in order to distribute significance level weight to each recommendation unit.For same video, the multiple rationale for the recommendation among above-mentioned various rationale for the recommendation may being met simultaneously, thus there is multiple rationale for the recommendation, recommending out high-quality video to improve further, usual synchronization, only can show a rationale for the recommendation for same video.Therefore need to carry out preferably, selecting a top quality rationale for the recommendation to each above-mentioned rationale for the recommendation.One is improve diversity, and prevent visual fatigue, multiple rationale for the recommendation all should have certain display machine meeting.Two is prevent certain rationale for the recommendation too much, produces a large amount of rationale for the recommendation repeated.
Therefore according to business demand, increase weight setting unit 4, distribute an importance degree weight to each recommending module, then according to this weight, in multiple rationale for the recommendation preferably one at random.The rationale for the recommendation that weight is higher, final displaying probability is larger.By adjustment weight, thus representing of various rationale for the recommendation can be controlled.Such as there are recommendation unit T1, T2, T3, its candidate result number generated is respectively c1, c2, c3, then the weight of each recommendation unit can be set to w1=(c1+c2+c3)/c1, w2=(c1+c2+c3)/c2, w3=(c1+c2+c3)/c3 respectively.If the result number of this unit is fewer, then the weight calculated is higher.
Rationale for the recommendation module regular update, generates new rationale for the recommendation, and according to weight stochastic generation rationale for the recommendation, each renewal all can to the rationale for the recommendation be not demonstrated last time chance represented.
Embodiment three
The present invention also provides a kind of video recommendations reason generation method, comprises step as follows:
1): video resource is provided;
2): the video provided is filtered, ineligible video is removed;
3): recommendation is carried out to the video after filtering and shows.
Wherein, for the video resource provided, based on following a b c d the rationale for the recommendation that forms of e or combination in any wherein recommend,
A. collect the video once appearing at homepage and generate the relevant rationale for the recommendation of homepage; Such as " homepage top news video today ".For the channel page that some are important, also similar rationale for the recommendation can be generated.
B. collect the forward video of all kinds of ranking list rank and generate ranking list rationale for the recommendation, such as collect each the first five video of ten of classification ranking list rank, generate ranking list rationale for the recommendation.For class of making laughs, if rank is greater than front 10, then rationale for the recommendation be roughly " class of making laughs to comment on today maximum rank first three/five/ten "; If rank be greater than front ten be less than the first five ten.Rationale for the recommendation is roughly " class of making laughs comment today at most ".As required, can be made up of a kind of or wherein combination in any of the scoring of accumulative click volume, reprinting amount, user, certain regional most popular degree.
C. collect the statistics of video playback behavior, and based on the generating recommendations reason of this statistics, comprise the video based on accumulative click volume, or based on microblogging reprinting amount video and add up.Due to habits and customs and the hobby difference of the user in each area, the interest of each area to all kinds of video is also distinguished to some extent, also can add up based on the video that certain area (such as Beijing) is most popular, or user give a mark height etc. add up.Utilize these statisticss, generate the rationale for the recommendation of Corpus--based Method, such as " accumulative click is greater than 10,000 ", " spectators' favorite of Beijing area is seen ", " microblogging heat is carried " etc.In order to the video obtained better, quality is higher.In addition, system can set a threshold value, after statistic is greater than certain threshold value, just can generate corresponding rationale for the recommendation, thus ensures that rationale for the recommendation is all high-quality, the video audient multi-user accreditation of recommendation.
D. based on the comment generating recommendations reason of user to video, some high quality reviews is the annotation to video highlight, excellent comment can be carried out to the plot of video, story, bright spot or personage etc., very be applicable to generating recommendations reason, allow the splendid contents of not seen the user of this video understand video fast, the user comment data of collecting high-quality constitute one of important recommending module.
E. generating recommendations reason is carried out based on to the historical record of uploader uploaded videos.Some user or clap visitor and once uploaded much good video, the dark favorable comment by user, and it is propagated and reprints, to be commented on or clicked higher.Therefore for the video uploaded from same bat visitor or this user or similar video, can anticipate that its video also can cause the interest of user, its video also can get high clicking rate under normal circumstances, therefore generates this kind of rationale for the recommendation also helpful for raising commending system clicking rate.
In order to improve the video quality provided further, remove low-quality video, for step 2), its method of filtering comprises:
Filter the click volume of the video provided, the video recommendations reason that prioritizing selection click volume is large generates, or filters the rank of the video provided, the video recommendations reason generation that prioritizing selection point rank is forward.Also can filter in the lump the rank of click volume and video as required simultaneously.
In addition, for step 1) video resource that provides, each rationale for the recommendation is provided with importance degree weight, then according to this weight, in multiple rationale for the recommendation preferably one at random.The rationale for the recommendation that weight is higher, final displaying probability is larger.By adjustment weight, thus representing of various rationale for the recommendation can be controlled.
Recommend the quality of video to improve further, for above-mentioned a b c d the various recommendations of e recommend reason, carry out regular update, make each renewal can to the rationale for the recommendation be not demonstrated last time chance represented.Relative to existing video recommendations reason generation method, the video recommendations reason that the present invention proposes generates reason system and method.Can according to the demand of user, by collecting various video resource data, classification forms the video of various rationale for the recommendation, and the video of these classification is screened and filtered, thus recommend out the video of high-quality to present to user, and and then can effectively increase commending system clicking rate, increase website traffic and business revenue.
In order to obtain better, video that quality is higher, system can set a threshold value, after statistic is greater than certain threshold value, just can generate corresponding rationale for the recommendation, thus ensures that rationale for the recommendation is all high-quality, the video audient multi-user accreditation of recommendation.
In this instructions, each embodiment adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar portion mutually see.For system disclosed in embodiment, owing to corresponding to the method disclosed in Example, so description is fairly simple, relevant part illustrates see method part.
Professional can also recognize further, in conjunction with unit and the algorithm steps of each example of embodiment disclosed herein description, can realize with electronic hardware, computer software or the combination of the two, in order to the interchangeability of hardware and software is clearly described, generally describe composition and the step of each example in the above description according to function.These functions perform with hardware or software mode actually, depend on application-specific and the design constraint of technical scheme.Professional and technical personnel can use distinct methods to realize described function to each specifically should being used for, but this realization should not thought and exceeds scope of the present invention.
Obviously, those skilled in the art can carry out various change and modification to invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (13)
1. a video recommendations reason generation system, is characterized in that, the rationale for the recommendation unit comprising filter element, selection unit and be made up of video set, wherein,
Rationale for the recommendation unit is in order to provide the video based on various rationale for the recommendation to filter element;
Filter element, in order to filter the video of rationale for the recommendation unit, removes ineligible video;
Selection unit is shown in order to carry out recommendation to the video after filter element filters.
2. video recommendations reason generation system as claimed in claim 1, it is characterized in that, described rationale for the recommendation unit comprises homepage recommending module, ranking list recommending module, statistics recommending module, comment recommending module, artificial recommending module, uploader recommending module or combination in any wherein, wherein
Homepage recommending module once appeared at the video of homepage in order to collect, generate the rationale for the recommendation that homepage is relevant;
Ranking list recommending module, in order to collect the forward video of all kinds of ranking list rank, generates ranking list rationale for the recommendation;
Statistics recommending module in order to collect the statistics of video playback behavior, and based on the generating recommendations reason of this statistics;
Comment recommending module is in order to based on the comment generating recommendations reason of user to video;
Uploader recommending module is in order to carry out generating recommendations reason based on to the historical record of uploader uploaded videos.
3. video recommendations reason generation system as claimed in claim 1, it is characterized in that, described video recommendations reason generation system also comprises weight setting module, in order to distribute the weight of importance degree to each recommendation unit.
4. video recommendations reason generation system as claimed in claim 1, is characterized in that, described filter element, comprises click volume filtering module or/and ranking list filtering module, wherein,
Described click volume filtering module filters in order to the click volume of the video provided described rationale for the recommendation unit, and the video recommendations reason that prioritizing selection click volume is large generates to selection unit;
Ranking list filtering module filters in order to the rank of the video provided described rationale for the recommendation unit, and the forward video recommendations reason of prioritizing selection point rank generates to selection unit.
5. video recommendations reason generation system as claimed in claim 2, it is characterized in that, the statistics of described statistics recommending module, comprises a kind of or combination in any wherein of one of scoring, certain regional most popular degree based on the accumulative click volume of this video, reprinting amount, user.
6. video recommendations reason generation system as claimed in claim 2, it is characterized in that, described statistics recommending module is set with a statistical threshold, when the data of this statistical module counts exceed this statistical threshold, just generating recommendations rationale for the recommendation.
7. a video recommendations reason generation method, is characterized in that, comprise step:
1) video resource is provided;
2) video provided is filtered, remove ineligible video;
3) carry out recommendation to the video after filtering to show.
8. video recommendations reason generation method as claimed in claim 7, is characterized in that, step 1) comprise following rationale for the recommendation and recommend:
Collect the video once appearing at homepage and generate the relevant rationale for the recommendation of homepage;
Collect the forward video of all kinds of ranking list rank and generate ranking list rationale for the recommendation;
Collect the statistics of video playback behavior, and based on the generating recommendations reason of this statistics;
Based on the comment generating recommendations reason of user to video;
Generating recommendations reason is carried out based on to the historical record of uploader uploaded videos.
9. video recommendations reason generation method as claimed in claim 7, is characterized in that, step 2) filtration is carried out to the video provided comprise:
Filter the click volume of the video provided, the large video recommendations reason of prioritizing selection click volume generates, or and
The rank of the video provided is filtered, the video recommendations reason generation that prioritizing selection point rank is forward.
10. video recommendations reason generation method as claimed in claim 7, is characterized in that, step 1) when video resource is provided, also comprise the weight allocation of the video resource provided being carried out to significance level.
11. video recommendations reason generation methods according to claim 8, is characterized in that, regularly upgrade various rationale for the recommendation.
12. video recommendations reason generation methods as claimed in claim 8, it is characterized in that, the statistics of collecting video playback behavior comprises based on the accumulative click volume of this video, reprinting amount, the scoring of user, a kind of of certain regional most popular degree or combination in any wherein.
13. video recommendations reason generation methods as claimed in claim 12, it is characterized in that, arrange a threshold value for described statistics, after its statistics exceedes threshold value, this video just becomes rationale for the recommendation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310206861.0A CN104216883A (en) | 2013-05-29 | 2013-05-29 | Video recommendation reason generating system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310206861.0A CN104216883A (en) | 2013-05-29 | 2013-05-29 | Video recommendation reason generating system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104216883A true CN104216883A (en) | 2014-12-17 |
Family
ID=52098389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310206861.0A Pending CN104216883A (en) | 2013-05-29 | 2013-05-29 | Video recommendation reason generating system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104216883A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462482A (en) * | 2014-12-18 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Content providing method and system for medium display |
| CN105095431A (en) * | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and device for pushing videos based on behavior information of user |
| CN105447087A (en) * | 2015-11-06 | 2016-03-30 | 腾讯科技（深圳）有限公司 | Video recommendation method and apparatus |
| CN106385634A (en) * | 2016-09-07 | 2017-02-08 | 合智能科技（深圳）有限公司 | Video recommendation method and device |
| CN106411679A (en) * | 2015-07-27 | 2017-02-15 | 北京盒陶软件科技有限公司 | Method and system of generating videos based on social information |
| CN106777360A (en) * | 2017-01-18 | 2017-05-31 | 广东小天才科技有限公司 | Content recommendation method and device |
| CN107196999A (en) * | 2017-05-03 | 2017-09-22 | 网易传媒科技（北京）有限公司 | Method and apparatus for issuing information flow propelling data |
| CN108259939A (en) * | 2017-12-25 | 2018-07-06 | 广州华多网络科技有限公司 | new video push control method, device and server |
| CN110609963A (en) * | 2019-08-09 | 2019-12-24 | 北京三快在线科技有限公司 | Recommendation list generation method and device, electronic equipment and storage medium |
| CN112001776A (en) * | 2020-08-24 | 2020-11-27 | 上海风秩科技有限公司 | Service information pushing method and device, storage medium and electronic equipment |
| CN112115300A (en) * | 2020-09-28 | 2020-12-22 | 北京奇艺世纪科技有限公司 | Text processing method and device, electronic equipment and readable storage medium |
| CN112270564A (en) * | 2020-10-23 | 2021-01-26 | 司富钱 | Information pushing method and system |
| CN113688335A (en) * | 2021-07-23 | 2021-11-23 | 北京三快在线科技有限公司 | Sort reason generation method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073720A (en) * | 2011-01-10 | 2011-05-25 | 北京航空航天大学 | FR method for optimizing personalized recommendation results |
| CA2829484A1 (en) * | 2011-03-08 | 2012-09-13 | Tivo Inc. | Multi source and destination media discovery and management platform |
-
2013
- 2013-05-29 CN CN201310206861.0A patent/CN104216883A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073720A (en) * | 2011-01-10 | 2011-05-25 | 北京航空航天大学 | FR method for optimizing personalized recommendation results |
| CA2829484A1 (en) * | 2011-03-08 | 2012-09-13 | Tivo Inc. | Multi source and destination media discovery and management platform |
Non-Patent Citations (1)
| Title |
|---|
| 蔡丽艳: "《数据挖掘算法及其应用研究》", 28 February 2013, 电子科技大学出版社 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462482A (en) * | 2014-12-18 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Content providing method and system for medium display |
| CN105095431A (en) * | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and device for pushing videos based on behavior information of user |
| CN106411679B (en) * | 2015-07-27 | 2019-10-22 | 北京盒陶软件科技有限公司 | One kind generating video method and system based on social information |
| CN106411679A (en) * | 2015-07-27 | 2017-02-15 | 北京盒陶软件科技有限公司 | Method and system of generating videos based on social information |
| CN105447087A (en) * | 2015-11-06 | 2016-03-30 | 腾讯科技（深圳）有限公司 | Video recommendation method and apparatus |
| CN105447087B (en) * | 2015-11-06 | 2021-08-24 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN106385634A (en) * | 2016-09-07 | 2017-02-08 | 合智能科技（深圳）有限公司 | Video recommendation method and device |
| CN106777360A (en) * | 2017-01-18 | 2017-05-31 | 广东小天才科技有限公司 | Content recommendation method and device |
| CN107196999A (en) * | 2017-05-03 | 2017-09-22 | 网易传媒科技（北京）有限公司 | Method and apparatus for issuing information flow propelling data |
| CN107196999B (en) * | 2017-05-03 | 2020-01-24 | 网易传媒科技（北京）有限公司 | Method and equipment for transmitting information flow push data |
| CN108259939A (en) * | 2017-12-25 | 2018-07-06 | 广州华多网络科技有限公司 | new video push control method, device and server |
| WO2019128941A1 (en) * | 2017-12-25 | 2019-07-04 | 广州华多网络科技有限公司 | Method and device for controlling new video pushing, and server. |
| CN108259939B (en) * | 2017-12-25 | 2020-08-07 | 广州华多网络科技有限公司 | New video push control method and device and server |
| CN110609963A (en) * | 2019-08-09 | 2019-12-24 | 北京三快在线科技有限公司 | Recommendation list generation method and device, electronic equipment and storage medium |
| CN110609963B (en) * | 2019-08-09 | 2022-08-26 | 北京三快在线科技有限公司 | Recommendation list generation method and device, electronic equipment and storage medium |
| CN112001776A (en) * | 2020-08-24 | 2020-11-27 | 上海风秩科技有限公司 | Service information pushing method and device, storage medium and electronic equipment |
| CN112115300A (en) * | 2020-09-28 | 2020-12-22 | 北京奇艺世纪科技有限公司 | Text processing method and device, electronic equipment and readable storage medium |
| CN112270564A (en) * | 2020-10-23 | 2021-01-26 | 司富钱 | Information pushing method and system |
| CN113688335A (en) * | 2021-07-23 | 2021-11-23 | 北京三快在线科技有限公司 | Sort reason generation method and device, electronic equipment and storage medium |
| CN113688335B (en) * | 2021-07-23 | 2023-09-01 | 北京三快在线科技有限公司 | Ranking reason generation method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104216883A (en) | Video recommendation reason generating system and method | |
| CN103747343B (en) | The method and apparatus that resource is recommended at times | |
| US9491509B2 (en) | Assessing digital content across a communications network | |
| CN105404700B (en) | A kind of video column recommendation system and recommended method based on collaborative filtering | |
| US9230352B2 (en) | Information processing apparatus, information processing method, and computer program product | |
| CN104216879A (en) | Video quality excavation system and method | |
| CN104053023B (en) | A kind of method and device of determining video similarity | |
| CN103686237A (en) | Method and system for recommending video resource | |
| CN105701226A (en) | Multimedia resource assessment method and device | |
| CN103136275A (en) | System and method for recommending personalized video | |
| CN101345852A (en) | Method and system for choosing and playing on-line video fragment | |
| KR20130090344A (en) | Apparatus, system, method and computer readable recording media storing the program for related recommendation of tv program contents and web contents | |
| CN102957949A (en) | Device and method for recommending video to user | |
| CN111435371B (en) | Video recommendation method and system, computer program product and readable storage medium | |
| CN107018408A (en) | The Quality of experience appraisal procedure of mobile terminal HTTP video flowings | |
| Kosterich | Reconfiguring the “hits”: The new portrait of television program success in an era of big data | |
| CN104699682B (en) | Information processing method and device | |
| CN105163183A (en) | Screening method and device for video pictures | |
| CN109213933B (en) | Content item recommendation method, device, equipment and storage medium | |
| CN107613323A (en) | A kind of intelligent EPG recommended engines implementation method | |
| CN105608158A (en) | Method and apparatus for displaying picture in waterfall flow manner | |
| CA2993311C (en) | News production system with program schedule modification feature | |
| CN105898421A (en) | Network film and television program intelligent recommendation method and system | |
| CN107608792B (en) | Resource scheduling method and device | |
| CN101662665A (en) | Real-time VOD system and VOD method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180608 Address after: 201203 7, 1 Lane 666 lane, Zhang Heng Road, Pudong New Area, Shanghai. Applicant after: SHANGHAI ZHANGMEN SCIENCE AND TECHNOLOGY Co.,Ltd. Address before: 300467 Tianjin Binhai New Area Tianjin eco city animation road 126 anime building B1 area two layer 201-243 Applicant before: KUSHENG (TIANJIN) SCIENCE & TECHNOLOGY CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180806 Address after: 300450 Tianjin eco city anime road 126 anime building B1 area two layer 201-243 Applicant after: KUSHENG (TIANJIN) SCIENCE & TECHNOLOGY CO.,LTD. Address before: 201203 7, 1 Lane 666 lane, Zhang Heng Road, Pudong New Area, Shanghai. Applicant before: SHANGHAI ZHANGMEN SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181219 Address after: 201306 N2025 room 24, 2 New Town Road, mud town, Pudong New Area, Shanghai Applicant after: SHANGHAI LIANSHANG NETWORK TECHNOLOGY Co.,Ltd. Address before: 300450 Tianjin eco city anime road 126 anime building B1 area two layer 201-243 Applicant before: KUSHENG (TIANJIN) SCIENCE & TECHNOLOGY CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141217 |
|
| RJ01 | Rejection of invention patent application after publication |